librarian-bots/dataset_cards_with_metadata

datasetId stringlengths 5 121	author stringlengths 2 42	last_modified unknowndate 2021-04-29 15:34:29 2025-04-12 01:29:38	downloads int64 0 5.67M	likes int64 0 7.68k	tags sequencelengths 1 7.92k	task_categories sequencelengths 0 48 ⌀	createdAt unknowndate 2022-03-02 23:29:22 2025-04-12 01:29:32	card stringlengths 20 1M
hlillemark/c4_t5_pretrain	hlillemark	"2023-05-22T16:33:38Z"	19,586	0	[ "size_categories:100M<n<1B", "format:parquet", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]	null	"2023-05-19T09:17:45Z"	--- dataset_info: features: - name: input_ids sequence: int32 - name: labels sequence: int64 splits: - name: validation num_bytes: 53400000 num_examples: 10000 - name: train num_bytes: 961505597520 num_examples: 180057228 download_size: 2939856140 dataset_size: 961558997520 --- # Dataset Card for "c4_t5_pretrain" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
CohereForAI/Global-MMLU	CohereForAI	"2025-03-20T19:47:13Z"	19,513	116	[ "language:en", "language:ar", "language:bn", "language:es", "language:fr", "language:hi", "language:ru", "language:de", "language:id", "language:it", "language:ja", "language:ko", "language:pt", "language:zh", "language:yo", "language:nl", "language:ro", "language:uk", "language:vi", "language:tr", "language:pl", "language:fa", "language:cs", "language:he", "language:el", "language:ms", "language:fil", "language:te", "language:si", "language:ne", "language:ky", "language:sv", "language:lt", "language:sr", "language:mg", "language:so", "language:ha", "language:am", "language:sn", "language:ig", "language:ny", "language:sw", "license:apache-2.0", "size_categories:100K<n<1M", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "library:argilla", "arxiv:2412.03304", "region:us", "argilla" ]	null	"2024-12-01T22:45:59Z"	--- dataset_info: - config_name: am features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 209505 num_examples: 285 - name: test num_bytes: 12085768 num_examples: 14042 download_size: 10260448 dataset_size: 12295273 - config_name: ar features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 202343 num_examples: 285 - name: test num_bytes: 11621977 num_examples: 14042 download_size: 9817049 dataset_size: 11824320 - config_name: bn features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 301875 num_examples: 285 - name: test num_bytes: 18061158 num_examples: 14042 download_size: 12524784 dataset_size: 18363033 - config_name: cs features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 149807 num_examples: 285 - name: test num_bytes: 8607308 num_examples: 14042 download_size: 8640151 dataset_size: 8757115 - config_name: de features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 162406 num_examples: 285 - name: test num_bytes: 9575360 num_examples: 14042 download_size: 9187953 dataset_size: 9737766 - config_name: el features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 254308 num_examples: 285 - name: test num_bytes: 14502137 num_examples: 14042 download_size: 12288940 dataset_size: 14756445 - config_name: en features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 146364 num_examples: 285 - name: test num_bytes: 8440632 num_examples: 14042 download_size: 7912429 dataset_size: 8586996 - config_name: es features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 160633 num_examples: 285 - name: test num_bytes: 9399724 num_examples: 14042 download_size: 8752720 dataset_size: 9560357 - config_name: fa features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 202609 num_examples: 285 - name: test num_bytes: 11611890 num_examples: 14042 download_size: 9564082 dataset_size: 11814499 - config_name: fil features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 165182 num_examples: 285 - name: test num_bytes: 9510179 num_examples: 14042 download_size: 8564879 dataset_size: 9675361 - config_name: fr features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 166173 num_examples: 285 - name: test num_bytes: 9858873 num_examples: 14042 download_size: 9202595 dataset_size: 10025046 - config_name: ha features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 147406 num_examples: 285 - name: test num_bytes: 8445707 num_examples: 14042 download_size: 7665529 dataset_size: 8593113 - config_name: he features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 178912 num_examples: 285 - name: test num_bytes: 10248592 num_examples: 14042 download_size: 8818618 dataset_size: 10427504 - config_name: hi features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 308254 num_examples: 285 - name: test num_bytes: 17970478 num_examples: 14042 download_size: 12407854 dataset_size: 18278732 - config_name: id features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 154692 num_examples: 285 - name: test num_bytes: 8886643 num_examples: 14042 download_size: 7793365 dataset_size: 9041335 - config_name: ig features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 157376 num_examples: 285 - name: test num_bytes: 9221405 num_examples: 14042 download_size: 7644102 dataset_size: 9378781 - config_name: it features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 157547 num_examples: 285 - name: test num_bytes: 9374481 num_examples: 14042 download_size: 8873034 dataset_size: 9532028 - config_name: ja features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 167646 num_examples: 285 - name: test num_bytes: 9830716 num_examples: 14042 download_size: 8826164 dataset_size: 9998362 - config_name: ko features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 160572 num_examples: 285 - name: test num_bytes: 9454859 num_examples: 14042 download_size: 8640457 dataset_size: 9615431 - config_name: ky features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 235001 num_examples: 285 - name: test num_bytes: 13483934 num_examples: 14042 download_size: 11148813 dataset_size: 13718935 - config_name: lt features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 148917 num_examples: 285 - name: test num_bytes: 8504949 num_examples: 14042 download_size: 8416467 dataset_size: 8653866 - config_name: mg features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 161992 num_examples: 285 - name: test num_bytes: 9337415 num_examples: 14042 download_size: 8011427 dataset_size: 9499407 - config_name: ms features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 152549 num_examples: 285 - name: test num_bytes: 8823844 num_examples: 14042 download_size: 7783581 dataset_size: 8976393 - config_name: ne features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 294790 num_examples: 285 - name: test num_bytes: 16972110 num_examples: 14042 download_size: 11895818 dataset_size: 17266900 - config_name: nl features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 158122 num_examples: 285 - name: test num_bytes: 9099176 num_examples: 14042 download_size: 8565959 dataset_size: 9257298 - config_name: ny features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 151315 num_examples: 285 - name: test num_bytes: 8686819 num_examples: 14042 download_size: 7822699 dataset_size: 8838134 - config_name: pl features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 157290 num_examples: 285 - name: test num_bytes: 8980730 num_examples: 14042 download_size: 8981270 dataset_size: 9138020 - config_name: pt features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 154592 num_examples: 285 - name: test num_bytes: 8983299 num_examples: 14042 download_size: 8517588 dataset_size: 9137891 - config_name: ro features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 158311 num_examples: 285 - name: test num_bytes: 9163189 num_examples: 14042 download_size: 8773232 dataset_size: 9321500 - config_name: ru features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 246059 num_examples: 285 - name: test num_bytes: 14059847 num_examples: 14042 download_size: 11904365 dataset_size: 14305906 - config_name: si features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 297843 num_examples: 285 - name: test num_bytes: 17374939 num_examples: 14042 download_size: 12790098 dataset_size: 17672782 - config_name: sn features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 147355 num_examples: 285 - name: test num_bytes: 8507368 num_examples: 14042 download_size: 7962672 dataset_size: 8654723 - config_name: so features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 156282 num_examples: 285 - name: test num_bytes: 9033243 num_examples: 14042 download_size: 8706693 dataset_size: 9189525 - config_name: sr features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 221580 num_examples: 285 - name: test num_bytes: 12695546 num_examples: 14042 download_size: 10748391 dataset_size: 12917126 - config_name: sv features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 147893 num_examples: 285 - name: test num_bytes: 8549708 num_examples: 14042 download_size: 8181997 dataset_size: 8697601 - config_name: sw features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 147069 num_examples: 285 - name: test num_bytes: 8653210 num_examples: 14042 download_size: 7932986 dataset_size: 8800279 - config_name: te features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 315724 num_examples: 285 - name: test num_bytes: 18170058 num_examples: 14042 download_size: 12631358 dataset_size: 18485782 - config_name: tr features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 153426 num_examples: 285 - name: test num_bytes: 8833244 num_examples: 14042 download_size: 8351339 dataset_size: 8986670 - config_name: uk features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 229888 num_examples: 285 - name: test num_bytes: 13233771 num_examples: 14042 download_size: 11347842 dataset_size: 13463659 - config_name: vi features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 185712 num_examples: 285 - name: test num_bytes: 10604332 num_examples: 14042 download_size: 8971266 dataset_size: 10790044 - config_name: yo features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 153810 num_examples: 285 - name: test num_bytes: 10694916 num_examples: 14042 download_size: 9303668 dataset_size: 10848726 - config_name: zh features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 127577 num_examples: 285 - name: test num_bytes: 7393764 num_examples: 14042 download_size: 7322261 dataset_size: 7521341 configs: - config_name: am data_files: - split: test path: am/test-* - split: dev path: am/dev-* - config_name: ar data_files: - split: test path: ar/test-* - split: dev path: ar/dev-* - config_name: bn data_files: - split: test path: bn/test-* - split: dev path: bn/dev-* - config_name: cs data_files: - split: test path: cs/test-* - split: dev path: cs/dev-* - config_name: de data_files: - split: test path: de/test-* - split: dev path: de/dev-* - config_name: el data_files: - split: test path: el/test-* - split: dev path: el/dev-* - config_name: en data_files: - split: test path: en/test-* - split: dev path: en/dev-* - config_name: es data_files: - split: test path: es/test-* - split: dev path: es/dev-* - config_name: fa data_files: - split: test path: fa/test-* - split: dev path: fa/dev-* - config_name: fil data_files: - split: test path: fil/test-* - split: dev path: fil/dev-* - config_name: fr data_files: - split: test path: fr/test-* - split: dev path: fr/dev-* - config_name: ha data_files: - split: test path: ha/test-* - split: dev path: ha/dev-* - config_name: he data_files: - split: test path: he/test-* - split: dev path: he/dev-* - config_name: hi data_files: - split: test path: hi/test-* - split: dev path: hi/dev-* - config_name: id data_files: - split: test path: id/test-* - split: dev path: id/dev-* - config_name: ig data_files: - split: test path: ig/test-* - split: dev path: ig/dev-* - config_name: it data_files: - split: test path: it/test-* - split: dev path: it/dev-* - config_name: ja data_files: - split: test path: ja/test-* - split: dev path: ja/dev-* - config_name: ko data_files: - split: test path: ko/test-* - split: dev path: ko/dev-* - config_name: ky data_files: - split: test path: ky/test-* - split: dev path: ky/dev-* - config_name: lt data_files: - split: test path: lt/test-* - split: dev path: lt/dev-* - config_name: mg data_files: - split: test path: mg/test-* - split: dev path: mg/dev-* - config_name: ms data_files: - split: test path: ms/test-* - split: dev path: ms/dev-* - config_name: ne data_files: - split: test path: ne/test-* - split: dev path: ne/dev-* - config_name: nl data_files: - split: test path: nl/test-* - split: dev path: nl/dev-* - config_name: ny data_files: - split: test path: ny/test-* - split: dev path: ny/dev-* - config_name: pl data_files: - split: test path: pl/test-* - split: dev path: pl/dev-* - config_name: pt data_files: - split: test path: pt/test-* - split: dev path: pt/dev-* - config_name: ro data_files: - split: test path: ro/test-* - split: dev path: ro/dev-* - config_name: ru data_files: - split: test path: ru/test-* - split: dev path: ru/dev-* - config_name: si data_files: - split: test path: si/test-* - split: dev path: si/dev-* - config_name: sn data_files: - split: test path: sn/test-* - split: dev path: sn/dev-* - config_name: so data_files: - split: test path: so/test-* - split: dev path: so/dev-* - config_name: sr data_files: - split: test path: sr/test-* - split: dev path: sr/dev-* - config_name: sv data_files: - split: test path: sv/test-* - split: dev path: sv/dev-* - config_name: sw data_files: - split: test path: sw/test-* - split: dev path: sw/dev-* - config_name: te data_files: - split: test path: te/test-* - split: dev path: te/dev-* - config_name: tr data_files: - split: test path: tr/test-* - split: dev path: tr/dev-* - config_name: uk data_files: - split: test path: uk/test-* - split: dev path: uk/dev-* - config_name: vi data_files: - split: test path: vi/test-* - split: dev path: vi/dev-* - config_name: yo data_files: - split: test path: yo/test-* - split: dev path: yo/dev-* - config_name: zh data_files: - split: test path: zh/test-* - split: dev path: zh/dev-* tags: - argilla license: apache-2.0 language: - en - ar - bn - es - fr - hi - ru - de - id - it - ja - ko - pt - zh - yo - nl - ro - uk - vi - tr - pl - fa - cs - he - el - ms - fil - te - si - ne - ky - sv - lt - sr - mg - so - ha - am - sn - ig - ny - sw --- ![GlobalMMLU Header](https://huggingface.co/datasets/CohereForAI/Global-MMLU/resolve/main/global_mmlu.jpg) # Dataset Summary [Global-MMLU](https://arxiv.org/abs/2412.03304) 🌍 is a multilingual evaluation set spanning 42 languages, including English. This dataset combines machine translations for [MMLU](https://huggingface.co/datasets/cais/mmlu) questions along with professional translations and crowd-sourced post-edits. It also includes cultural sensitivity annotations for a subset of the questions (2850 questions per language) and classifies them as Culturally Sensitive (CS) 🗽 or Culturally Agnostic (CA) ⚖️. These annotations were collected as part of an open science initiative led by Cohere For AI in collaboration with many external collaborators from both industry and academia. - Curated by: Professional annotators and contributors of [Cohere For AI Community](https://cohere.com/research). - Language(s): 42 languages. - License: [Apache 2.0](https://opensource.org/license/apache-2-0) Note: We also provide a "lite" version of Global MMLU called ["Global-MMLU-Lite"](https://huggingface.co/datasets/CohereForAI/Global-MMLU-Lite). This datatset is more balanced containing 200 samples each for CA and CS subsets for each language. And provides coverage for 15 languages with human translations. ### Global-MMLU Dataset Family: \| Name \| Explanation \| \|------\|--------------\| \| [Global-MMLU](https://huggingface.co/datasets/CohereForAI/Global-MMLU) \| Full Global-MMLU set with translations for all 14K samples including CS and CA subsets\| \| [Global-MMLU-Lite](https://huggingface.co/datasets/CohereForAI/Global-MMLU-Lite) \| Lite version of Global-MMLU with human translated samples in 15 languages and containing 200 samples each for CS and CA subsets per language.\| ## Load with Datasets To load this dataset with `datasets`, you'll first need to install it using `pip install datasets` and then use the following code: ```python from datasets import load_dataset # load HF dataset global_mmlu = load_dataset("CohereForAI/Global-MMLU", 'en') # can also be used as pandas dataframe global_mmlu.set_format("pandas") global_mmlu_test = global_mmlu['test'][:] global_mmlu_dev = global_mmlu['dev'][:] ``` <details> <summary> additional details </summary> The columns corresponding to annotations collected from our cultural bias study (i.e. 'required_knowledge', 'time_sensitive', 'reference', 'culture', 'region', 'country') contain a list of values representing annotations from different annotators. However, to avoid conversion issues to HF dataset, these columns are provided as string in the final dataset. You can convert these columns back to list of values for easier manipulation as follows: ```python import ast # convert string values to list global_mmlu_df['required_knowledge'] = global_mmlu_df['required_knowledge'].apply(lamda x: ast.literal_eval(x)) ``` </details> <br> ## Data Fields The data fields are the same among all splits. Brief description of each field is provided below. <details> <summary> data field description </summary> - `sample_id`: A unique identifier for the question. - `subject`: The main topic the question falls under. - `subject_category`: The high-level category the subject falls under i.e. STEM/Humanities/Social Sciences/Medical/Business/Other. - `question`: translated question from MMLU - `option_a`: one of the possible option choices - `option_b`: one of the possible option choices - `option_c`: one of the possible option choices - `option_d`: one of the possible option choices - `answer': the correct answer (A/B/C/D) - `required_knowledge`: annotator votes for knowledge needed to answer the question correctly. Possible values include: "cultural", "regional", "dialect" or "none" - `time_sensitive`: annotator votes indicating if the question's answer is time-dependent. Possible values include: Yes/No - `reference`: annotations for which part of the question contains cultural/regional/dialect references. The different items in the list are annotations from different annotators. - `culture`: annotations for which culture does the question belong to. The different items in the list correspond to annotations from different annotators. - `region`: Geographic region the question is relevant to. Each item in the list correspond to annotations from different annotators. - `country`: Specific country the question pertains to. Each item in the list correspond to annotations from different annotators. - `cultural_sensitivity_label`: Label to indicate if question is culturally sensitive (CS) or culturally agnostic (CA) based on annotator votes. - `is_annotated`: True/False flag to indicate if sample contains any annotations from our cultural bias study. </details> <br> ## Data Splits The following are the splits of the data: \| Split \| No. of instances \| Language Coverage \| \|-------\|------------------\|-------------------\| \| test \| 589,764 \| 42 \| \| dev \| 11,970 \| 42 \| ## Data Instances An example from `test` set looks as follows: ```json {'sample_id': 'world_religions/test/170' 'subject': 'world_religions', 'subject_category': 'Humanities', 'question': ' The numen of Augustus referred to which of the following characteristics?', 'option_a': 'Divine power', 'option_b': 'Sexual virility', 'option_c': 'Military acumen', 'option_d': 'Philosophical intellect', 'answer': 'A', 'required_knowledge': "['none', 'cultural', 'cultural', 'cultural']", 'time_sensitive': "['No', 'No', 'No', 'No']", 'reference': "['-', '-', {'end': 22, 'label': 'Cultural', 'score': None, 'start': 5}, {'end': 22, 'label': 'Cultural', 'score': None, 'start': 5}]", 'culture': "['Western Culture', 'Western Culture', 'Western Culture']", 'region': "['North America', 'Europe']", 'country': "['Italy']", 'cultural_sensitivity_label': 'CS', 'is_annotated': True, } ``` ## Statistics ### Annotation Types The following is the breakdown of CS🗽, CA⚖️ and MA📝 samples in the final dataset. \| Type of Annotation \| Instances per language \| No. of languages \| Total instances \|--------------------\|------------------------\|------------------\|----------------\| \| Culturally Sensitive 🗽 \| 792 \| 42 \| 33,264 \| \| Culturally Agnostic ⚖️ \| 2058 \|42 \| 86,436 \| \| MMLU Annotated 📝\| 2850 \|42 \| 119,700 \| ### Languages The dataset covers 42 languages: 20 high-resource, 9 mid-resource, and 13 low-resource languages. The following is details about the languages included in the dataset. <details> <summary> Languages Info </summary> \| ISO Code \| Language \| Resources \| \|----------\|----------\|-----------\| \| `am` \| Amharic \| Low \| \| `ar` \| Arabic (Standard)\| High \| \| `bn` \| Bengali \| Mid \| \| `de` \| German \| High \| \| `el` \| Greek \| Mid \| \| `en` \| English \| High \| \| `fil` \| Filipino \| Mid \| \| `fr` \| French \| High \| \| `ha` \| Hausa \| Low \| \| `he` \| Hebrew \| Mid \| \| `hi` \| Hindi \| High \| \| `ig` \| Igbo \| Low \| \| `id` \| Indonesian \| Mid \| \| `it` \| Italian \| High \| \| `ja` \| Japanese \| High \| \| `ky` \| Kyrgyz \| Low \| \| `ko` \| Korean \| Mid \| \| `lt` \| Lithuanian \| Mid \| \| `mg` \| Malagasy \| Low \| \| `ms` \| Malay \| Mid \| \| `ne` \| Nepali \| Low \| \| `nl` \| Dutch \| High \| \| `ny` \| Chichewa \| Low \| \| `fa` \| Persian \| High \| \| `pl` \| Polish \| High \| \| `pt` \| Portuguese \| High \| \| `ru` \| Russian \| High \| \| `si` \| Sinhala \| Low \| \| `sn` \| Shona \| Low \| \| `so` \| Somali \| Low \| \| `es` \| Spanish \| High \| \| `sr` \| Serbian \| High \| \| `sw` \| Swahili \| Low \| \| `sv` \| Swedish \| High \| \| `te` \| Telugu \| Low \| \| `tr` \| Turkish \| High \| \| `uk` \| Ukrainian \| Mid \| \| `vi` \| Vietnamese \| High \| \| `yo` \| Yorùbá \| Low \| \| `zh` \| Chinese (Simplified) \| High \| </details> <br> # Known Limitations A brief overview of limitations of this dataset is provided below. <details> <summary> show limitations </summary> - Language and dialect coverage: Global-MMLU focusses on 42 languages. However, this is still only a tiny fraction of the world’s linguistic diversity. Future work is needed to continue to improve evaluations beyond these 42 languages and take into account how technology serves different dialects. - Uneven distribution of contributions: The dataset contains translation post-edits from community volunteers, with a 'long tail' of volunteers making only one or two contributions. Similarly, there is a huge gap between languages with the highest number of contributions and ones with the lowest number of contributions. - Toxic or offensive speech: Our annotation process did not focus on flagging for toxic,harmful, or offensive speech, so it is possible that Global-MMLU contains some data that could be considered harmful. We believe this is of relatively low risk because of the nature of the original MMLU and the focus on examination material. - Region Category Assignment: For the annotation of geographically sensitive questions, we classified regions into six geographic regions (Africa, Asia, Europe, North America, Oceania,and South America). However, based upon discussions we would going forward recommend switching to the taxonomy proposed by the World Bank which is more granular and includes separate designations for Central America and Sub-Saharan Africa. - Identifying cultural sensitivity does not guarantee cultural inclusion: While Global-MMLU highlights important limitations in current datasets by identifying gaps in non-Western cultural representation. Future work must prioritize the integration of diverse culturally grounded knowledge to achieve true inclusivity and fairness in multilingual AI evaluation. </details> <br> # Additional Information ## Provenance - Methods Used: Professional annotations as well as crowd-sourced through volunteer annotations. - Methodology Details: We collected cultural bias annotations as well as post-edits of translations for different mmlu questions. - [Cultural Sensitivity Annotation Platform](https://huggingface.co/spaces/CohereForAI/MMLU-evaluation) - [Translation Quality Annotation Platform](https://huggingface.co/spaces/CohereForAI/review-mmlu-translations) - Dates of Collection: May 2024 - Aug 2024 ## Dataset Version and Maintenance - Maintenance Status: Actively Maintained - Version Details: - Current version: 1.0 - Last Update: 12/2024 - First Release: 12/2024 ## Authorship - Publishing Organization: [Cohere For AI](https://cohere.com/research) - Industry Type: Not-for-profit - Tech ## Licensing Information This dataset can be used for any purpose, under the terms of the [Apache 2.0](https://opensource.org/license/apache-2-0) License. ## Additional Details For any additional details, please check our paper, [Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation](https://arxiv.org/abs/2412.03304). ## Citation Information ```bibtex @misc{singh2024globalmmluunderstandingaddressing, title={Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation}, author={Shivalika Singh and Angelika Romanou and Clémentine Fourrier and David I. Adelani and Jian Gang Ngui and Daniel Vila-Suero and Peerat Limkonchotiwat and Kelly Marchisio and Wei Qi Leong and Yosephine Susanto and Raymond Ng and Shayne Longpre and Wei-Yin Ko and Madeline Smith and Antoine Bosselut and Alice Oh and Andre F. T. Martins and Leshem Choshen and Daphne Ippolito and Enzo Ferrante and Marzieh Fadaee and Beyza Ermis and Sara Hooker}, year={2024}, eprint={2412.03304}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2412.03304}, } ```
gvecchio/MatSynth	gvecchio	"2024-04-16T13:44:10Z"	19,433	47	[ "task_categories:image-to-image", "task_categories:unconditional-image-generation", "task_categories:image-classification", "task_categories:text-to-image", "language:en", "size_categories:1K<n<10K", "arxiv:2401.06056", "region:us", "materials", "pbr", "4d", "graphics", "rendering", "svbrdf", "synthetic" ]	[ "image-to-image", "unconditional-image-generation", "image-classification", "text-to-image" ]	"2023-11-29T11:24:57Z"	--- language: - en size_categories: - 1K<n<10K task_categories: - image-to-image - unconditional-image-generation - image-classification - text-to-image pretty_name: MatSynth dataset_info: features: - name: name dtype: string - name: category dtype: class_label: names: '0': ceramic '1': concrete '2': fabric '3': ground '4': leather '5': marble '6': metal '7': misc '8': plaster '9': plastic '10': stone '11': terracotta '12': wood - name: metadata struct: - name: authors sequence: string - name: category dtype: string - name: description dtype: string - name: height_factor dtype: float32 - name: height_mean dtype: float32 - name: license dtype: string - name: link dtype: string - name: maps sequence: string - name: method dtype: string - name: name dtype: string - name: physical_size dtype: float32 - name: source dtype: string - name: stationary dtype: bool - name: tags sequence: string - name: version_date dtype: string - name: basecolor dtype: image - name: diffuse dtype: image - name: displacement dtype: image - name: height dtype: image - name: metallic dtype: image - name: normal dtype: image - name: opacity dtype: image - name: roughness dtype: image - name: specular dtype: image - name: blend_mask dtype: image splits: - name: test num_bytes: 7443356066.0 num_examples: 89 - name: train num_bytes: 430581667965.1 num_examples: 5700 download_size: 440284274332 dataset_size: 438025024031.1 configs: - config_name: default data_files: - split: test path: data/test-* - split: train path: data/train-* tags: - materials - pbr - 4d - graphics - rendering - svbrdf - synthetic viewer: false --- # MatSynth MatSynth is a Physically Based Rendering (PBR) materials dataset designed for modern AI applications. This dataset consists of over 4,000 ultra-high resolution, offering unparalleled scale, diversity, and detail. Meticulously collected and curated, MatSynth is poised to drive innovation in material acquisition and generation applications, providing a rich resource for researchers, developers, and enthusiasts in computer graphics and related fields. For further information, refer to our paper: ["MatSynth: A Modern PBR Materials Dataset"](https://arxiv.org/abs/2401.06056) available on arXiv. <center> <img src="https://gvecchio.com/matsynth/static/images/teaser.png" style="border-radius:10px"> </center> ## 🔍 Dataset Details ### Dataset Description MatSynth is a new large-scale dataset comprising over 4,000 ultra-high resolution Physically Based Rendering (PBR) materials, all released under permissive licensing. All materials in the dataset are represented by a common set of maps (Basecolor, Diffuse, Normal, Height, Roughness, Metallic, Specular and, when useful, Opacity), modelling both the reflectance and mesostructure of the material. Each material in the dataset comes with rich metadata, including information on its origin, licensing details, category, tags, creation method, and, when available, descriptions and physical size. This comprehensive metadata facilitates precise material selection and usage, catering to the specific needs of users. <center> <img src="https://gvecchio.com/matsynth/static/images/data.png" style="border-radius:10px"> </center> ## 📂 Dataset Structure The MatSynth dataset is divided into two splits: the test split, containing 89 materials, and the train split, consisting of 3,980 materials. ## 🔨 Dataset Creation The MatSynth dataset is designed to support modern, learning-based techniques for a variety of material-related tasks including, but not limited to, material acquisition, material generation and synthetic data generation e.g. for retrieval or segmentation. ### 🗃️ Source Data The MatSynth dataset is the result of an extensively collection of data from multiple online sources operating under the CC0 and CC-BY licensing framework. This collection strategy allows to capture a broad spectrum of materials, from commonly used ones to more niche or specialized variants while guaranteeing that the data can be used for a variety of usecases. Materials under CC0 license were collected from [AmbientCG](https://ambientcg.com/), [CGBookCase](https://www.cgbookcase.com/), [PolyHeaven](https://polyhaven.com/), [ShateTexture](https://www.sharetextures.com/), and [TextureCan](https://www.texturecan.com/). The dataset also includes limited set of materials from the artist [Julio Sillet](https://juliosillet.gumroad.com/), distributed under CC-BY license. We collected over 6000 materials which we meticulously filter to keep only tileable, 4K materials. This high resolution allows us to extract many different crops from each sample at different scale for augmentation. Additionally, we discard blurry or low-quality materials (by visual inspection). The resulting dataset consists of 3736 unique materials which we augment by blending semantically compatible materials (e.g.: snow over ground). In total, our dataset contains 4069 unique 4K materials. ### ✒️ Annotations The dataset is composed of material maps (Basecolor, Diffuse, Normal, Height, Roughness, Metallic, Specular and, when useful, opacity) and associated renderings under varying environmental illuminations, and multi-scale crops. We adopt the OpenGL standard for the Normal map (Y-axis pointing upward). The Height map is given in a 16-bit single channel format for higher precision. In addition to these maps, the dataset includes other annotations providing context to each material: the capture method (photogrammetry, procedural generation, or approximation); list of descriptive tags; source name (website); source link; licensing and a timestamps for eventual future versioning. For a subset of materials, when the information is available, we also provide the author name (387), text description (572) and a physical size, presented as the length of the edge in centimeters (358). ## 🧑‍💻 Usage MatSynth is accessible through the datasets python library. Following a usage example: ```python import torchvision.transforms.functional as TF from datasets import load_dataset from torch.utils.data import DataLoader # image processing function def process_img(x): x = TF.resize(x, (1024, 1024)) x = TF.to_tensor(x) return x # item processing function def process_batch(examples): examples["basecolor"] = [process_img(x) for x in examples["basecolor"]] return examples # load the dataset in streaming mode ds = load_dataset( "gvecchio/MatSynth", streaming = True, ) # remove unwanted columns ds = ds.remove_columns(["diffuse", "specular", "displacement", "opacity", "blend_mask"]) # or keep only specified columns ds = ds.select_columns(["metadata", "basecolor"]) # shuffle data ds = ds.shuffle(buffer_size=100) # filter data matching a specific criteria, e.g.: only CC0 materials ds = ds.filter(lambda x: x["metadata"]["license"] == "CC0") # filter out data from Deschaintre et al. 2018 ds = ds.filter(lambda x: x["metadata"]["source"] != "deschaintre_2020") # Set up processing ds = ds.map(process_batch, batched=True, batch_size=8) # set format for usage in torch ds = ds.with_format("torch") # iterate over the dataset for x in ds: print(x) ``` ⚠️ Note: Streaming can be slow. We strongly suggest to cache data locally. ## 📜 Citation ``` @inproceedings{vecchio2023matsynth, title={MatSynth: A Modern PBR Materials Dataset}, author={Vecchio, Giuseppe and Deschaintre, Valentin}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, year={2024} } ``` If you use the data from Deschaintre et al. contained in this dataset, please also cite: ``` @article{deschaintre2018single, title={Single-image svbrdf capture with a rendering-aware deep network}, author={Deschaintre, Valentin and Aittala, Miika and Durand, Fredo and Drettakis, George and Bousseau, Adrien}, journal={ACM Transactions on Graphics (ToG)}, volume={37}, number={4}, pages={1--15}, year={2018}, publisher={ACM New York, NY, USA} } ```
jiachenlei/imagenet	jiachenlei	"2024-11-28T02:31:55Z"	19,367	1	[ "region:us" ]	null	"2024-11-27T02:39:50Z"	--- configs: - config_name: imagenet data_files: - split: train path: - "imagenet/train" - split: val path: "imagenet/val" - config_name: imagenet256 data_files: - split: train path: - "imagenet256/train" - split: val path: "imagenet256/val" - config_name: imagenet_features data_files: - split: train path: - "imagenet_features/train" - split: val path: "imagenet_features/val" ---
alexandrainst/ftspeech	alexandrainst	"2024-09-04T15:01:21Z"	19,357	3	[ "task_categories:automatic-speech-recognition", "language:da", "license:other", "size_categories:1M<n<10M", "format:parquet", "modality:audio", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "arxiv:2005.12368", "region:us" ]	[ "automatic-speech-recognition" ]	"2023-05-11T13:08:57Z"	--- dataset_info: features: - name: utterance_id dtype: string - name: speaker_gender dtype: string - name: sentence dtype: string - name: speaker_id dtype: string - name: audio dtype: audio: sampling_rate: 16000 splits: - name: train num_bytes: 209434570129.268 num_examples: 995677 - name: dev_balanced num_bytes: 579692770.829 num_examples: 2601 - name: dev_other num_bytes: 1725502342.095 num_examples: 7595 - name: test_balanced num_bytes: 1158740779.222 num_examples: 5534 - name: test_other num_bytes: 1254987645.527 num_examples: 5837 download_size: 101776974871 dataset_size: 214153493666.941 task_categories: - automatic-speech-recognition language: - da pretty_name: FT Speech size_categories: - 100K<n<1M license: other --- # Dataset Card for FT Speech ## Dataset Description - Repository: <https://ftspeech.github.io/> - Point of Contact: [Dan Saattrup Nielsen](mailto:[email protected]) - Size of downloaded dataset files: 101.78 GB - Size of the generated dataset: 214.15 GB - Total amount of disk used: 315.93 GB ### Dataset Summary This dataset is an upload of the [FT Speech dataset](https://ftspeech.github.io/). The training, validation and test splits are the original ones. ### Supported Tasks and Leaderboards Training automatic speech recognition is the intended task for this dataset. No leaderboard is active at this point. ### Languages The dataset is available in Danish (`da`). ## Dataset Structure ### Data Instances - Size of downloaded dataset files: 101.78 GB - Size of the generated dataset: 214.15 GB - Total amount of disk used: 315.93 GB An example from the dataset looks as follows. ``` { 'utterance_id': 'S001_20151_M012_P00034-2', 'speaker_gender': 'F', 'sentence': 'alle de fem tekniske justeringer der er en del af lovforslaget', 'speaker_id': 'S001', 'audio': { 'path': 'S001_20151_M012_P00034-2.wav', 'array': array([-3.75366211e-03, -5.27954102e-03, -3.87573242e-03, ..., 9.15527344e-05, -1.52587891e-04, 5.79833984e-04]), 'sampling_rate': 16000 } } ``` ### Data Fields The data fields are the same among all splits. - `utterance_id`: a `string` feature. - `speaker_gender`: a `string` feature. - `sentence`: a `string` feature. - `speaker_id`: a `string` feature. - `audio`: an `Audio` feature. ### Dataset Statistics There are 995,677 samples in the training split, 2,601 in the dev_balanced split, 7,595 in the dev_other split, 5,534 in the test_balanced and 5,837 in the test_other split. #### Speakers There are 374 unique speakers in the training dataset, 20 unique speakers in the validation dataset and 40 unique speakers in the test dataset. None of the dataset splits share any speakers. #### Gender Distribution ![ftspeech-gender-distribution.png](https://cdn-uploads.huggingface.co/production/uploads/60d368a613f774189902f555/0h_L7-riNfQbKFdYWgy01.png) #### Transcription Length Distribution ![ftspeech-length-distribution.png](https://cdn-uploads.huggingface.co/production/uploads/60d368a613f774189902f555/z1MqsvACrY_8XNXAx0UcD.png) ## Dataset Creation ### Curation Rationale There are not many large-scale ASR datasets in Danish. ### Source Data The data constitutes public recordings of sessions from the Danish Parliament, along with manual transcriptions. ## Additional Information ### Dataset Curators Andreas Kirkedal, Marija Stepanović and Barbara Plank curated the dataset as part of their FT Speech paper (see citation below). [Dan Saattrup Nielsen](https://saattrupdan.github.io/) from the [The Alexandra Institute](https://alexandra.dk/) reorganised the dataset and uploaded it to the Hugging Face Hub. ### Licensing Information The dataset is licensed under [this custom license](https://www.ft.dk/da/aktuelt/tv-fra-folketinget/deling-og-rettigheder). ### Citation ``` @inproceedings{ftspeech, author = {Kirkedal, Andreas and Stepanović, Marija and Plank, Barbara}, title = {{FT Speech: Danish Parliament Speech Corpus}}, booktitle = {Proc. Interspeech 2020}, year = {2020}, url = {arxiv.org/abs/2005.12368} } ```
EleutherAI/race	EleutherAI	"2023-07-03T21:27:18Z"	19,340	6	[ "task_categories:multiple-choice", "task_ids:multiple-choice-qa", "annotations_creators:expert-generated", "language_creators:found", "multilinguality:monolingual", "source_datasets:original", "language:en", "license:other", "size_categories:1K<n<10K", "modality:text", "library:datasets", "library:mlcroissant", "arxiv:1704.04683", "region:us" ]	[ "multiple-choice" ]	"2023-07-03T13:20:38Z"	--- annotations_creators: - expert-generated language: - en language_creators: - found license: - other multilinguality: - monolingual pretty_name: RACE size_categories: - 10K<n<100K source_datasets: - original task_categories: - multiple-choice task_ids: - multiple-choice-qa paperswithcode_id: race dataset_info: --- # "race" Grouped by Article This is a modified version of https://huggingface.co/datasets/race that returns documents grouped by article context instead of by question. Note: This dataset currently only contains that test set of the ```high``` subset of the data. The original readme is contained below. # Dataset Card for "race" ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - Homepage: [http://www.cs.cmu.edu/~glai1/data/race/](http://www.cs.cmu.edu/~glai1/data/race/) - Repository: https://github.com/qizhex/RACE_AR_baselines - Paper: [RACE: Large-scale ReAding Comprehension Dataset From Examinations](https://arxiv.org/abs/1704.04683) - Point of Contact: [Guokun Lai](mailto:[email protected]), [Qizhe Xie](mailto:[email protected]) - Size of downloaded dataset files: 76.33 MB - Size of the generated dataset: 349.46 MB - Total amount of disk used: 425.80 MB ### Dataset Summary RACE is a large-scale reading comprehension dataset with more than 28,000 passages and nearly 100,000 questions. The dataset is collected from English examinations in China, which are designed for middle school and high school students. The dataset can be served as the training and test sets for machine comprehension. ### Supported Tasks and Leaderboards [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Languages [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Dataset Structure ### Data Instances #### all - Size of downloaded dataset files: 25.44 MB - Size of the generated dataset: 174.73 MB - Total amount of disk used: 200.17 MB An example of 'train' looks as follows. ``` This example was too long and was cropped: { "answer": "A", "article": "\"Schoolgirls have been wearing such short skirts at Paget High School in Branston that they've been ordered to wear trousers ins...", "example_id": "high132.txt", "options": ["short skirts give people the impression of sexualisation", "short skirts are too expensive for parents to afford", "the headmaster doesn't like girls wearing short skirts", "the girls wearing short skirts will be at the risk of being laughed at"], "question": "The girls at Paget High School are not allowed to wear skirts in that _ ." } ``` #### high - Size of downloaded dataset files: 25.44 MB - Size of the generated dataset: 140.12 MB - Total amount of disk used: 165.56 MB An example of 'train' looks as follows. ``` This example was too long and was cropped: { "answer": "A", "article": "\"Schoolgirls have been wearing such short skirts at Paget High School in Branston that they've been ordered to wear trousers ins...", "example_id": "high132.txt", "options": ["short skirts give people the impression of sexualisation", "short skirts are too expensive for parents to afford", "the headmaster doesn't like girls wearing short skirts", "the girls wearing short skirts will be at the risk of being laughed at"], "question": "The girls at Paget High School are not allowed to wear skirts in that _ ." } ``` #### middle - Size of downloaded dataset files: 25.44 MB - Size of the generated dataset: 34.61 MB - Total amount of disk used: 60.05 MB An example of 'train' looks as follows. ``` This example was too long and was cropped: { "answer": "B", "article": "\"There is not enough oil in the world now. As time goes by, it becomes less and less, so what are we going to do when it runs ou...", "example_id": "middle3.txt", "options": ["There is more petroleum than we can use now.", "Trees are needed for some other things besides making gas.", "We got electricity from ocean tides in the old days.", "Gas wasn't used to run cars in the Second World War."], "question": "According to the passage, which of the following statements is TRUE?" } ``` ### Data Fields The data fields are the same among all splits. #### all - `example_id`: a `string` feature. - `article`: a `string` feature. - `answer`: a `string` feature. - `question`: a `string` feature. - `options`: a `list` of `string` features. #### high - `example_id`: a `string` feature. - `article`: a `string` feature. - `answer`: a `string` feature. - `question`: a `string` feature. - `options`: a `list` of `string` features. #### middle - `example_id`: a `string` feature. - `article`: a `string` feature. - `answer`: a `string` feature. - `question`: a `string` feature. - `options`: a `list` of `string` features. ### Data Splits \| name \|train\|validation\|test\| \|------\|----:\|---------:\|---:\| \|all \|87866\| 4887\|4934\| \|high \|62445\| 3451\|3498\| \|middle\|25421\| 1436\|1436\| ## Dataset Creation ### Curation Rationale [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Source Data #### Initial Data Collection and Normalization [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the source language producers? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Annotations #### Annotation process [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the annotators? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Personal and Sensitive Information [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Discussion of Biases [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Other Known Limitations [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Additional Information ### Dataset Curators [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Licensing Information http://www.cs.cmu.edu/~glai1/data/race/ 1. RACE dataset is available for non-commercial research purpose only. 2. All passages are obtained from the Internet which is not property of Carnegie Mellon University. We are not responsible for the content nor the meaning of these passages. 3. You agree not to reproduce, duplicate, copy, sell, trade, resell or exploit for any commercial purpose, any portion of the contexts and any portion of derived data. 4. We reserve the right to terminate your access to the RACE dataset at any time. ### Citation Information ``` @inproceedings{lai-etal-2017-race, title = "{RACE}: Large-scale {R}e{A}ding Comprehension Dataset From Examinations", author = "Lai, Guokun and Xie, Qizhe and Liu, Hanxiao and Yang, Yiming and Hovy, Eduard", booktitle = "Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing", month = sep, year = "2017", address = "Copenhagen, Denmark", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/D17-1082", doi = "10.18653/v1/D17-1082", pages = "785--794", } ``` ### Contributions Thanks to [@abarbosa94](https://github.com/abarbosa94), [@patrickvonplaten](https://github.com/patrickvonplaten), [@lewtun](https://github.com/lewtun), [@thomwolf](https://github.com/thomwolf), [@mariamabarham](https://github.com/mariamabarham) for adding this dataset.
agents-course/certificates	agents-course	"2025-04-12T00:52:35Z"	19,322	41	[ "license:apache-2.0", "region:us" ]	null	"2025-02-06T08:17:59Z"	--- license: apache-2.0 ---
Graphcore/wikipedia-bert-128	Graphcore	"2022-09-07T14:42:32Z"	19,254	1	[ "language:en", "license:cc-by-sa-3.0", "size_categories:10M<n<100M", "format:parquet", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]	null	"2022-03-02T23:29:22Z"	--- language: - en license: - cc-by-sa-3.0 ---
lmms-lab/Video-MME	lmms-lab	"2024-07-04T08:14:20Z"	19,248	39	[ "size_categories:1K<n<10K", "format:parquet", "modality:text", "modality:video", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]	null	"2024-06-07T12:06:37Z"	--- dataset_info: config_name: videomme features: - name: video_id dtype: string - name: duration dtype: string - name: domain dtype: string - name: sub_category dtype: string - name: url dtype: string - name: videoID dtype: string - name: question_id dtype: string - name: task_type dtype: string - name: question dtype: string - name: options sequence: string - name: answer dtype: string splits: - name: test num_bytes: 1003241.0 num_examples: 2700 download_size: 405167 dataset_size: 1003241.0 configs: - config_name: videomme data_files: - split: test path: videomme/test-* ---
neashton/ahmedml	neashton	"2025-04-08T13:29:43Z"	19,223	2	[ "license:cc-by-sa-4.0", "arxiv:2407.20801", "doi:10.57967/hf/5002", "region:us" ]	null	"2025-02-10T11:19:24Z"	--- license: cc-by-sa-4.0 --- AhmedML: High-Fidelity Computational Fluid Dynamics dataset for incompressible, low-speed bluff body aerodynamics ------- Contact: ---------- Neil Ashton (NVIDIA) - [email protected] website: ---------- https://caemldatasets.org Summary: ------- This dataset contains 500 different geometric variations of the Ahmed Car Body - a simplified car-like shape that exhibits many of the flow topologies that are present on bluff bodies such as road vehicles. The dataset contains a wide range of geometries that exhibit fundamental flow physics such as geometry and pressure-induced flow separation of flows as well as 3D vortical structures. Each variation of the Ahmed car body were run using a time-accurate hybrid Reynolds-Averaged Navier-Stokes (RANS) - Large-Eddy Simulation (LES) turbulence modelling approach using the open-source CFD code OpenFOAM. The dataset contains both surface boundary, 3D volume, geometry STL and forces/moments in open-source formats (.vtu,.vtp). CFD Solver: ---------- All cases were run using the open-source finite-volume code OpenFOAM v2212. Each case was run transiently for approximately 80 convective time units (CTU) on meshes of approximately 20M cells. Please see the paper for full details on the code and validation: How to cite this dataset: ---------------- In order to cite the use of this dataset please cite the paper below which contains full details on the dataset. It can be found here: https://arxiv.org/abs/2407.20801 @article{ashton2024ahmed, title = {{AhmedML: High-Fidelity Computational Fluid Dynamics dataset for incompressible, low-speed bluff body aerodynamics}}, year = {2024}, journal = {arxiv.org}, author = {Ashton, Neil and Maddix, Danielle and Gundry, Samuel and Shabestari, Parisa} } Files: ------- Each folder (e.g run_1,run_2...run_"i" etc) corresponds to a different geometry that contains the following files where "i" is the run number: * ahmed_i.stl : geometry stl (~5mb): * geo_parameters_1.csv (missing run 500): parameters that define the geometry * boundary_i.vtp : Boundary VTP (~500mb) * volume_i.vtu : Volume field VTU (~5GB) * force_mom_i.csv : forces (Cd,Cl) time-averaged with constant reference area * force_mom_varref_i.csv : forces (Cd,Cl) time-averaged with varying reference area * slices : folder containing .vtp slices in x,y,z that contain flow-field variables * images : (folder) that contains images of the following variables (CpT, UxMean) for slices of the domain in the X,Y & Z locations. In addition we provide: * force_mom_all.csv : run, cd,cl for all runs in a single file * force_mom_varref_all.csv : run, cd,cl for all runs in a single file with varying reference area * geo_parameters_all.csv : all the geometry parameters for each run inside a single file * ahmedml.slvs : SolveSpace input file to create the parametric geometries * stl : folder containing stl files that were used as inputs to the OpenFOAM process * openfoam-casesetup.tgz : complete OpenFOAM setup that can be used to extend or reproduce the dataset * validation : folder containing full outputs from all four mesh levels that were used to validate the methodology Downloads -------------- The dataset is now available on HuggingFace. Below are some examples of how to download all or selected parts of the dataset. Please refer to the HuggingFace documentation for other ways to accessing the dataset and building workflows. Example 1: Download all files (~2TB) -------- Please note you'll need to have git lfs installed first, then you can run the following command: ``` git clone [email protected]:datasets/neashton/ahmedml ``` Example 2: only download select files (STL,images & force and moments): --------- Create the following bash script that could be adapted to loop through only select runs or to change to download different files e.g boundary/volume. ``` #!/bin/bash # Set the paths HF_OWNER="neashton" HF_PREFIX="ahmedml" # Set the local directory to download the files LOCAL_DIR="./ahmed_data" # Create the local directory if it doesn't exist mkdir -p "$LOCAL_DIR" # Loop through the run folders from 1 to 500 for i in $(seq 1 500); do RUN_DIR="run_$i" RUN_LOCAL_DIR="$LOCAL_DIR/$RUN_DIR" # Create the run directory if it doesn't exist mkdir -p "$RUN_LOCAL_DIR" # Download the ahmed_i.stl file wget "https://huggingface.co/datasets/${HF_OWNER}/${HF_PREFIX}/resolve/main/$RUN_DIR/ahmed_$i.stl" -O "$RUN_LOCAL_DIR/ahmed_$i.stl" # Download the force_mom_i.csv file wget "https://huggingface.co/datasets/${HF_OWNER}/${HF_PREFIX}/resolve/main/$RUN_DIR/force_mom_$i.csv" -O "$RUN_LOCAL_DIR/force_mom_$i.csv" done ``` Acknowledgements ----------- * OpenFOAM solver and workflow development by Neil Ashton (Amazon Web Services, now NVIDIA) * Geometry parameterization by Samuel Gundry (Amazon Web Services) and Parisa Shabestari (Amazon Web Services) * Guidance on dataset preparation for ML by Danielle Madix (Amazon Web Services) * Simulation runs, HPC setup and dataset preparation by Neil Ashton (Amazon Web Services, now NVIDIA) License ---- This dataset is provided under the CC BY SA 4.0 license, please see LICENSE.txt for full license text. version history: --------------- * 15/02/2025 - files uploaded to HuggingFace * 12/11/2024 - added validation folder that contains the full output from all four mesh levels that were used to validate the methodology used. * 04/08/2024 - updates to the file description and arxiv paper * 05/06/2024 - global forces/geo added for all runs * 01/05/2024 - force/moments corrected (prior version had incorrect Cs data) * 18/04/2024 - draft version produced
AstroMLCore/AstroM3Dataset	AstroMLCore	"2025-03-27T21:43:24Z"	18,918	0	[ "license:mit", "size_categories:10K<n<100K", "arxiv:2411.08842", "region:us", "astronomy", "multimodal", "classification" ]	null	"2024-11-06T20:51:40Z"	--- license: mit pretty_name: AstroM3Dataset size_categories: - 10K<n<100K tags: - astronomy - multimodal - classification arxiv: - arXiv:2411.08842 --- # AstroM3Dataset ## Description AstroM3Dataset is a time-series astronomy dataset containing photometry, spectra, and metadata features for variable stars. The dataset was constructed by cross-matching publicly available astronomical datasets, primarily from the ASAS-SN (Shappee et al. 2014) variable star catalog (Jayasinghe et al. 2019) and LAMOST spectroscopic survey (Cui et al. 2012), along with data from WISE (Wright et al. 2010), GALEX (Morrissey et al. 2007), 2MASS (Skrutskie et al. 2006) and Gaia EDR3 (Gaia Collaboration et al. 2021). The dataset includes multiple subsets (`full`, `sub10`, `sub25`, `sub50`) and supports different random seeds (`42`, `66`, `0`, `12`, `123`). Each sample consists of: - Photometry: Light curve data of shape `(N, 3)` (time, flux, flux\_error). - Spectra: Spectra observations of shape `(M, 3)` (wavelength, flux, flux\_error). - Metadata: - `meta_cols`: Dictionary of metadata feature names and values. - `photo_cols`: Dictionary of photometric feature names and values. - Label: The class name as a string. ## Corresponding paper and code - Paper: [AstroM<sup>3</sup>: A self-supervised multimodal model for astronomy](https://arxiv.org/abs/2411.08842) - Code Repository: [GitHub: AstroM<sup>3</sup>](https://github.com/MeriDK/AstroM3/) - Processed Data: [AstroMLCore/AstroM3Processed](https://huggingface.co/datasets/AstroMLCore/AstroM3Processed/) Note: The processed dataset `AstroM3Processed` is created from the original dataset `AstroM3Dataset` by using [preprocess.py](https://huggingface.co/datasets/AstroMLCore/AstroM3Dataset/blob/main/preprocess.py) --- ## Subsets and Seeds AstroM3Dataset is available in different subset sizes: - `full`: Entire dataset - `sub50`: 50% subset - `sub25`: 25% subset - `sub10`: 10% subset Each subset is sampled from the respective train, validation, and test splits of the full dataset. For reproducibility, each subset is provided with different random seeds: - `42`, `66`, `0`, `12`, `123` ## Data Organization The dataset is organized as follows: ``` AstroM3Dataset/ ├── photometry.zip # Contains all photometry light curves ├── utils/ │ ├── parallelzipfile.py # Zip file reader to open photometry.zip ├── spectra/ # Spectra files organized by class │ ├── EA/ │ │ ├── file1.dat │ │ ├── file2.dat │ │ ├── ... │ ├── EW/ │ ├── SR/ │ ├── ... ├── splits/ # Train/val/test splits for each subset and seed │ ├── full/ │ │ ├── 42/ │ │ │ ├── train.csv │ │ │ ├── val.csv │ │ │ ├── test.csv │ │ │ ├── info.json # Contains feature descriptions and preprocessing info │ │ ├── 66/ │ │ ├── 0/ │ │ ├── 12/ │ │ ├── 123/ │ ├── sub10/ │ ├── sub25/ │ ├── sub50/ │── AstroM3Dataset.py # Hugging Face dataset script ``` ## Usage To load the dataset using the Hugging Face `datasets` library: ```python from datasets import load_dataset # Load the default full dataset with seed 42 dataset = load_dataset("AstroMLCore/AstroM3Dataset", trust_remote_code=True) ``` The default configuration is full_42 (entire dataset with seed 42). To load a specific subset and seed, use {subset}_{seed} as the name: ```python from datasets import load_dataset # Load the 25% subset sampled using seed 123 dataset = load_dataset("AstroMLCore/AstroM3Dataset", name="sub25_123", trust_remote_code=True) ``` --- ## Citation 🤗 If you find this dataset usefull, please cite our paper 🤗 ```bibtex @article{rizhko2024astrom, title={AstroM $\^{} 3$: A self-supervised multimodal model for astronomy}, author={Rizhko, Mariia and Bloom, Joshua S}, journal={arXiv preprint arXiv:2411.08842}, year={2024} } ``` ## References 1. Shappee, B. J., Prieto, J. L., Grupe, D., et al. 2014, ApJ, 788, 48, doi: 10.1088/0004-637X/788/1/48 2. Jayasinghe, T., Stanek, K. Z., Kochanek, C. S., et al. 2019, MNRAS, 486, 1907, doi: 10.1093/mnras/stz844 3. Cui, X.-Q., Zhao, Y.-H., Chu, Y.-Q., et al. 2012, Research in Astronomy and Astrophysics, 12, 1197, doi: 10.1088/1674-4527/12/9/003 4. Wright, E. L., Eisenhardt, P. R. M., Mainzer, A. K., et al. 2010, AJ, 140, 1868, doi: 10.1088/0004-6256/140/6/1868 5. Morrissey, P., Conrow, T., Barlow, T. A., et al. 2007, ApJS, 173, 682, doi: 10.1086/520512 6. Skrutskie, M. F., Cutri, R. M., Stiening, R., et al. 2006, AJ, 131, 1163, doi: 10.1086/498708 7. Gaia Collaboration, Brown, A. G. A., et al. 2021, AAP, 649, A1, doi: 10.1051/0004-6361/202039657
TIGER-Lab/OmniEdit-Filtered-1.2M	TIGER-Lab	"2024-12-06T02:57:59Z"	18,883	85	[ "language:en", "license:mit", "size_categories:1M<n<10M", "format:parquet", "modality:image", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "arxiv:2411.07199", "region:us", "image" ]	null	"2024-11-11T07:40:47Z"	--- language: - en license: mit size_categories: - 1M<n<10M pretty_name: OmniEdit dataset_info: features: - name: omni_edit_id dtype: string - name: task dtype: string - name: src_img dtype: image - name: edited_img dtype: image - name: edited_prompt_list sequence: string - name: width dtype: int64 - name: height dtype: int64 - name: sc_score_1 dtype: int64 - name: sc_score_2 dtype: int64 - name: sc_reasoning dtype: string - name: pq_score dtype: int64 - name: pq_reasoning dtype: string - name: o_score dtype: float64 splits: - name: dev num_bytes: 1547839078.0 num_examples: 700 - name: train num_bytes: 2852916299223.88 num_examples: 1202797 download_size: 2978259415518 dataset_size: 2854464138301.88 configs: - config_name: default data_files: - split: dev path: data/dev-* - split: train path: data/train-* tags: - image --- ## OmniEdit In this paper, we present OMNI-EDIT, which is an omnipotent editor to handle seven different image editing tasks with any aspect ratio seamlessly. Our contribution is in four folds: (1) OMNI-EDIT is trained by utilizing the supervision from seven different specialist models to ensure task coverage. (2) we utilize importance sampling based on the scores provided by large multimodal models (like GPT-4o) instead of CLIP-score to improve the data quality. [📃Paper](https://tiger-ai-lab.github.io/OmniEdit/) \| [🌐Website](https://tiger-ai-lab.github.io/OmniEdit/) \| [💻Github](https://github.com/TIGER-AI-Lab/OmniEdit) \| [📚Dataset](https://huggingface.co/datasets/TIGER-Lab/OmniEdit-Filtered-1.2M) ## Dataset Columns The dataset contains the following columns: - src, edited_img: they are the source and edited images. - edited_prompt_list: they are the short and long editing instructions. - task: this indicates the editing task, which has seven categories like addition, removal, background, environment, style, etc. - sc_score_1 and sc_score_1: semantic consistency score assigned by our quality rater. - pq_score: the perceptual quality score assigned by our quality rater. - o_score: the overall score, which is the weighted average of sc and pq score. - *_reasoning: the rationale for assigning these scores. ## Data Pipeline We synthesize the large scale dataset through specialist distillation. Our synthesis pipeline is depicted in <p align="center"> <img src="synthesis.png" width="800"> </p> Our released version contains 1.2M pairs covering seven different skills like addition, swaping, removal, attribute modification, background change, environment change and sytle transfer. The dataset has been filtered with VIEScore. ## Comparison with Others Our dataset has the most diverse, highest-quality image editing pairs of any resolution. <p align="center"> <img src="comparison.png" width="800"> </p> ## Citation If you find our paper useful, please cite us with ``` @article{wei2024omniedit, title={OmniEdit: Building Image Editing Generalist Models Through Specialist Supervision}, author={Wei, Cong and Xiong, Zheyang and Ren, Weiming and Du, Xinrun and Zhang, Ge and Chen, Wenhu}, journal={arXiv preprint arXiv:2411.07199}, year={2024} } ```
dair-ai/emotion	dair-ai	"2024-08-08T06:10:47Z"	18,876	351	[ "task_categories:text-classification", "task_ids:multi-class-classification", "annotations_creators:machine-generated", "language_creators:machine-generated", "multilinguality:monolingual", "source_datasets:original", "language:en", "license:other", "size_categories:100K<n<1M", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us", "emotion-classification" ]	[ "text-classification" ]	"2022-03-02T23:29:22Z"	--- annotations_creators: - machine-generated language_creators: - machine-generated language: - en license: - other multilinguality: - monolingual size_categories: - 10K<n<100K source_datasets: - original task_categories: - text-classification task_ids: - multi-class-classification paperswithcode_id: emotion pretty_name: Emotion tags: - emotion-classification dataset_info: - config_name: split features: - name: text dtype: string - name: label dtype: class_label: names: '0': sadness '1': joy '2': love '3': anger '4': fear '5': surprise splits: - name: train num_bytes: 1741533 num_examples: 16000 - name: validation num_bytes: 214695 num_examples: 2000 - name: test num_bytes: 217173 num_examples: 2000 download_size: 1287193 dataset_size: 2173401 - config_name: unsplit features: - name: text dtype: string - name: label dtype: class_label: names: '0': sadness '1': joy '2': love '3': anger '4': fear '5': surprise splits: - name: train num_bytes: 45444017 num_examples: 416809 download_size: 26888538 dataset_size: 45444017 configs: - config_name: split data_files: - split: train path: split/train-* - split: validation path: split/validation-* - split: test path: split/test-* default: true - config_name: unsplit data_files: - split: train path: unsplit/train-* train-eval-index: - config: default task: text-classification task_id: multi_class_classification splits: train_split: train eval_split: test col_mapping: text: text label: target metrics: - type: accuracy name: Accuracy - type: f1 name: F1 macro args: average: macro - type: f1 name: F1 micro args: average: micro - type: f1 name: F1 weighted args: average: weighted - type: precision name: Precision macro args: average: macro - type: precision name: Precision micro args: average: micro - type: precision name: Precision weighted args: average: weighted - type: recall name: Recall macro args: average: macro - type: recall name: Recall micro args: average: micro - type: recall name: Recall weighted args: average: weighted --- # Dataset Card for "emotion" ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - Homepage: [https://github.com/dair-ai/emotion_dataset](https://github.com/dair-ai/emotion_dataset) - Repository: [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - Paper: [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - Point of Contact: [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - Size of downloaded dataset files: 16.13 MB - Size of the generated dataset: 47.62 MB - Total amount of disk used: 63.75 MB ### Dataset Summary Emotion is a dataset of English Twitter messages with six basic emotions: anger, fear, joy, love, sadness, and surprise. For more detailed information please refer to the paper. ### Supported Tasks and Leaderboards [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Languages [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Dataset Structure ### Data Instances An example looks as follows. ``` { "text": "im feeling quite sad and sorry for myself but ill snap out of it soon", "label": 0 } ``` ### Data Fields The data fields are: - `text`: a `string` feature. - `label`: a classification label, with possible values including `sadness` (0), `joy` (1), `love` (2), `anger` (3), `fear` (4), `surprise` (5). ### Data Splits The dataset has 2 configurations: - split: with a total of 20_000 examples split into train, validation and split - unsplit: with a total of 416_809 examples in a single train split \| name \| train \| validation \| test \| \|---------\|-------:\|-----------:\|-----:\| \| split \| 16000 \| 2000 \| 2000 \| \| unsplit \| 416809 \| n/a \| n/a \| ## Dataset Creation ### Curation Rationale [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Source Data #### Initial Data Collection and Normalization [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the source language producers? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Annotations #### Annotation process [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the annotators? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Personal and Sensitive Information [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Discussion of Biases [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Other Known Limitations [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Additional Information ### Dataset Curators [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Licensing Information The dataset should be used for educational and research purposes only. ### Citation Information If you use this dataset, please cite: ``` @inproceedings{saravia-etal-2018-carer, title = "{CARER}: Contextualized Affect Representations for Emotion Recognition", author = "Saravia, Elvis and Liu, Hsien-Chi Toby and Huang, Yen-Hao and Wu, Junlin and Chen, Yi-Shin", booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing", month = oct # "-" # nov, year = "2018", address = "Brussels, Belgium", publisher = "Association for Computational Linguistics", url = "https://www.aclweb.org/anthology/D18-1404", doi = "10.18653/v1/D18-1404", pages = "3687--3697", abstract = "Emotions are expressed in nuanced ways, which varies by collective or individual experiences, knowledge, and beliefs. Therefore, to understand emotion, as conveyed through text, a robust mechanism capable of capturing and modeling different linguistic nuances and phenomena is needed. We propose a semi-supervised, graph-based algorithm to produce rich structural descriptors which serve as the building blocks for constructing contextualized affect representations from text. The pattern-based representations are further enriched with word embeddings and evaluated through several emotion recognition tasks. Our experimental results demonstrate that the proposed method outperforms state-of-the-art techniques on emotion recognition tasks.", } ``` ### Contributions Thanks to [@lhoestq](https://github.com/lhoestq), [@thomwolf](https://github.com/thomwolf), [@lewtun](https://github.com/lewtun) for adding this dataset.
HuggingFaceH4/ultrachat_200k	HuggingFaceH4	"2024-10-16T11:52:27Z"	18,813	526	[ "task_categories:text-generation", "language:en", "license:mit", "size_categories:100K<n<1M", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "arxiv:2305.14233", "region:us" ]	[ "text-generation" ]	"2023-10-24T08:24:57Z"	--- language: - en license: mit size_categories: - 100K<n<1M task_categories: - text-generation pretty_name: UltraChat 200k configs: - config_name: default data_files: - split: train_sft path: data/train_sft-* - split: test_sft path: data/test_sft-* - split: train_gen path: data/train_gen-* - split: test_gen path: data/test_gen-* dataset_info: features: - name: prompt dtype: string - name: prompt_id dtype: string - name: messages list: - name: content dtype: string - name: role dtype: string splits: - name: train_sft num_bytes: 1397058554 num_examples: 207865 - name: test_sft num_bytes: 154695659 num_examples: 23110 - name: train_gen num_bytes: 1347396812 num_examples: 256032 - name: test_gen num_bytes: 148276089 num_examples: 28304 download_size: 1624049723 dataset_size: 3047427114 --- # Dataset Card for UltraChat 200k ## Dataset Description This is a heavily filtered version of the [UltraChat](https://github.com/thunlp/UltraChat) dataset and was used to train [Zephyr-7B-β](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta), a state of the art 7b chat model. The original datasets consists of 1.4M dialogues generated by ChatGPT and spanning a wide range of topics. To create `UltraChat 200k`, we applied the following logic: - Selection of a subset of data for faster supervised fine tuning. - Truecasing of the dataset, as we observed around 5% of the data contained grammatical errors like "Hello. how are you?" instead of "Hello. How are you?" - Removal of dialogues where the assistant replies with phrases like "I do not have emotions" or "I don't have opinions", even for fact-based prompts that don't involve either. ## Dataset Structure The dataset has four splits, suitable for: * Supervised fine-tuning (`sft`). * Generation ranking (`gen`) via techniques like rejection sampling or PPO. The number of examples per split is shown as follows: \| train_sft \| test_sft \| train_gen \| test_gen \| \|:-------:\|:-----------:\|:-----:\| :-----:\| \| 207865 \| 23110 \| 256032 \| 28304 \| The dataset is stored in parquet format with each entry using the following schema: ``` { "prompt": "Create a fully-developed protagonist who is challenged to survive within a dystopian society under the rule of a tyrant. ...", "messages":[ { "content": "Create a fully-developed protagonist who is challenged to survive within a dystopian society under the rule of a tyrant. ...", "role": "user" }, { "content": "Name: Ava\n\n Ava was just 16 years old when the world as she knew it came crashing down. The government had collapsed, leaving behind a chaotic and lawless society. ...", "role": "assistant" }, { "content": "Wow, Ava's story is so intense and inspiring! Can you provide me with more details. ...", "role": "user" }, { "content": "Certainly! ....", "role": "assistant" }, { "content": "That's really interesting! I would love to hear more...", "role": "user" } { "content": "Certainly! ....", "role": "assistant" }, ], "prompt_id": "d938b65dfe31f05f80eb8572964c6673eddbd68eff3db6bd234d7f1e3b86c2af" } ``` ## Citation If you find this dataset is useful in your work, please cite the original UltraChat dataset: ``` @misc{ding2023enhancing, title={Enhancing Chat Language Models by Scaling High-quality Instructional Conversations}, author={Ning Ding and Yulin Chen and Bokai Xu and Yujia Qin and Zhi Zheng and Shengding Hu and Zhiyuan Liu and Maosong Sun and Bowen Zhou}, year={2023}, eprint={2305.14233}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```
TrevorDohm/Stack_Tokenized	TrevorDohm	"2024-04-16T00:19:53Z"	18,811	0	[ "task_categories:text-generation", "language_creators:crowdsourced", "language_creators:expert-generated", "multilinguality:multilingual", "language:code", "license:other", "size_categories:100M<n<1B", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]	[ "text-generation" ]	"2024-03-10T05:49:00Z"	--- annotations_creators: [] language_creators: - crowdsourced - expert-generated language: - code license: - other multilinguality: - multilingual pretty_name: The-Stack-Tokenized size_categories: - unknown source_datasets: [] task_categories: - text-generation task_ids: [] ---
ceval/ceval-exam	ceval	"2025-03-25T13:18:03Z"	18,647	259	[ "task_categories:text-classification", "task_categories:multiple-choice", "task_categories:question-answering", "language:zh", "license:cc-by-nc-sa-4.0", "size_categories:10K<n<100K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "arxiv:2305.08322", "region:us" ]	[ "text-classification", "multiple-choice", "question-answering" ]	"2023-05-16T01:47:44Z"	--- license: cc-by-nc-sa-4.0 task_categories: - text-classification - multiple-choice - question-answering language: - zh pretty_name: C-Eval size_categories: - 10K<n<100K configs: - config_name: accountant data_files: - split: test path: accountant/test-* - split: val path: accountant/val-* - split: dev path: accountant/dev-* - config_name: advanced_mathematics data_files: - split: test path: advanced_mathematics/test-* - split: val path: advanced_mathematics/val-* - split: dev path: advanced_mathematics/dev-* - config_name: art_studies data_files: - split: test path: art_studies/test-* - split: val path: art_studies/val-* - split: dev path: art_studies/dev-* - config_name: basic_medicine data_files: - split: test path: basic_medicine/test-* - split: val path: basic_medicine/val-* - split: dev path: basic_medicine/dev-* - config_name: business_administration data_files: - split: test path: business_administration/test-* - split: val path: business_administration/val-* - split: dev path: business_administration/dev-* - config_name: chinese_language_and_literature data_files: - split: test path: chinese_language_and_literature/test-* - split: val path: chinese_language_and_literature/val-* - split: dev path: chinese_language_and_literature/dev-* - config_name: civil_servant data_files: - split: test path: civil_servant/test-* - split: val path: civil_servant/val-* - split: dev path: civil_servant/dev-* - config_name: clinical_medicine data_files: - split: test path: clinical_medicine/test-* - split: val path: clinical_medicine/val-* - split: dev path: clinical_medicine/dev-* - config_name: college_chemistry data_files: - split: test path: college_chemistry/test-* - split: val path: college_chemistry/val-* - split: dev path: college_chemistry/dev-* - config_name: college_economics data_files: - split: test path: college_economics/test-* - split: val path: college_economics/val-* - split: dev path: college_economics/dev-* - config_name: college_physics data_files: - split: test path: college_physics/test-* - split: val path: college_physics/val-* - split: dev path: college_physics/dev-* - config_name: college_programming data_files: - split: test path: college_programming/test-* - split: val path: college_programming/val-* - split: dev path: college_programming/dev-* - config_name: computer_architecture data_files: - split: test path: computer_architecture/test-* - split: val path: computer_architecture/val-* - split: dev path: computer_architecture/dev-* - config_name: computer_network data_files: - split: test path: computer_network/test-* - split: val path: computer_network/val-* - split: dev path: computer_network/dev-* - config_name: discrete_mathematics data_files: - split: test path: discrete_mathematics/test-* - split: val path: discrete_mathematics/val-* - split: dev path: discrete_mathematics/dev-* - config_name: education_science data_files: - split: test path: education_science/test-* - split: val path: education_science/val-* - split: dev path: education_science/dev-* - config_name: electrical_engineer data_files: - split: test path: electrical_engineer/test-* - split: val path: electrical_engineer/val-* - split: dev path: electrical_engineer/dev-* - config_name: environmental_impact_assessment_engineer data_files: - split: test path: environmental_impact_assessment_engineer/test-* - split: val path: environmental_impact_assessment_engineer/val-* - split: dev path: environmental_impact_assessment_engineer/dev-* - config_name: fire_engineer data_files: - split: test path: fire_engineer/test-* - split: val path: fire_engineer/val-* - split: dev path: fire_engineer/dev-* - config_name: high_school_biology data_files: - split: test path: high_school_biology/test-* - split: val path: high_school_biology/val-* - split: dev path: high_school_biology/dev-* - config_name: high_school_chemistry data_files: - split: test path: high_school_chemistry/test-* - split: val path: high_school_chemistry/val-* - split: dev path: high_school_chemistry/dev-* - config_name: high_school_chinese data_files: - split: test path: high_school_chinese/test-* - split: val path: high_school_chinese/val-* - split: dev path: high_school_chinese/dev-* - config_name: high_school_geography data_files: - split: test path: high_school_geography/test-* - split: val path: high_school_geography/val-* - split: dev path: high_school_geography/dev-* - config_name: high_school_history data_files: - split: test path: high_school_history/test-* - split: val path: high_school_history/val-* - split: dev path: high_school_history/dev-* - config_name: high_school_mathematics data_files: - split: test path: high_school_mathematics/test-* - split: val path: high_school_mathematics/val-* - split: dev path: high_school_mathematics/dev-* - config_name: high_school_physics data_files: - split: test path: high_school_physics/test-* - split: val path: high_school_physics/val-* - split: dev path: high_school_physics/dev-* - config_name: high_school_politics data_files: - split: test path: high_school_politics/test-* - split: val path: high_school_politics/val-* - split: dev path: high_school_politics/dev-* - config_name: ideological_and_moral_cultivation data_files: - split: test path: ideological_and_moral_cultivation/test-* - split: val path: ideological_and_moral_cultivation/val-* - split: dev path: ideological_and_moral_cultivation/dev-* - config_name: law data_files: - split: test path: law/test-* - split: val path: law/val-* - split: dev path: law/dev-* - config_name: legal_professional data_files: - split: test path: legal_professional/test-* - split: val path: legal_professional/val-* - split: dev path: legal_professional/dev-* - config_name: logic data_files: - split: test path: logic/test-* - split: val path: logic/val-* - split: dev path: logic/dev-* - config_name: mao_zedong_thought data_files: - split: test path: mao_zedong_thought/test-* - split: val path: mao_zedong_thought/val-* - split: dev path: mao_zedong_thought/dev-* - config_name: marxism data_files: - split: test path: marxism/test-* - split: val path: marxism/val-* - split: dev path: marxism/dev-* - config_name: metrology_engineer data_files: - split: test path: metrology_engineer/test-* - split: val path: metrology_engineer/val-* - split: dev path: metrology_engineer/dev-* - config_name: middle_school_biology data_files: - split: test path: middle_school_biology/test-* - split: val path: middle_school_biology/val-* - split: dev path: middle_school_biology/dev-* - config_name: middle_school_chemistry data_files: - split: test path: middle_school_chemistry/test-* - split: val path: middle_school_chemistry/val-* - split: dev path: middle_school_chemistry/dev-* - config_name: middle_school_geography data_files: - split: test path: middle_school_geography/test-* - split: val path: middle_school_geography/val-* - split: dev path: middle_school_geography/dev-* - config_name: middle_school_history data_files: - split: test path: middle_school_history/test-* - split: val path: middle_school_history/val-* - split: dev path: middle_school_history/dev-* - config_name: middle_school_mathematics data_files: - split: test path: middle_school_mathematics/test-* - split: val path: middle_school_mathematics/val-* - split: dev path: middle_school_mathematics/dev-* - config_name: middle_school_physics data_files: - split: test path: middle_school_physics/test-* - split: val path: middle_school_physics/val-* - split: dev path: middle_school_physics/dev-* - config_name: middle_school_politics data_files: - split: test path: middle_school_politics/test-* - split: val path: middle_school_politics/val-* - split: dev path: middle_school_politics/dev-* - config_name: modern_chinese_history data_files: - split: test path: modern_chinese_history/test-* - split: val path: modern_chinese_history/val-* - split: dev path: modern_chinese_history/dev-* - config_name: operating_system data_files: - split: test path: operating_system/test-* - split: val path: operating_system/val-* - split: dev path: operating_system/dev-* - config_name: physician data_files: - split: test path: physician/test-* - split: val path: physician/val-* - split: dev path: physician/dev-* - config_name: plant_protection data_files: - split: test path: plant_protection/test-* - split: val path: plant_protection/val-* - split: dev path: plant_protection/dev-* - config_name: probability_and_statistics data_files: - split: test path: probability_and_statistics/test-* - split: val path: probability_and_statistics/val-* - split: dev path: probability_and_statistics/dev-* - config_name: professional_tour_guide data_files: - split: test path: professional_tour_guide/test-* - split: val path: professional_tour_guide/val-* - split: dev path: professional_tour_guide/dev-* - config_name: sports_science data_files: - split: test path: sports_science/test-* - split: val path: sports_science/val-* - split: dev path: sports_science/dev-* - config_name: tax_accountant data_files: - split: test path: tax_accountant/test-* - split: val path: tax_accountant/val-* - split: dev path: tax_accountant/dev-* - config_name: teacher_qualification data_files: - split: test path: teacher_qualification/test-* - split: val path: teacher_qualification/val-* - split: dev path: teacher_qualification/dev-* - config_name: urban_and_rural_planner data_files: - split: test path: urban_and_rural_planner/test-* - split: val path: urban_and_rural_planner/val-* - split: dev path: urban_and_rural_planner/dev-* - config_name: veterinary_medicine data_files: - split: test path: veterinary_medicine/test-* - split: val path: veterinary_medicine/val-* - split: dev path: veterinary_medicine/dev-* dataset_info: - config_name: accountant features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 176917 num_examples: 443 - name: val num_bytes: 19549 num_examples: 49 - name: dev num_bytes: 3414 num_examples: 5 download_size: 151233 dataset_size: 199880 - config_name: advanced_mathematics features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 50031 num_examples: 173 - name: val num_bytes: 5331 num_examples: 19 - name: dev num_bytes: 7012 num_examples: 5 download_size: 50962 dataset_size: 62374 - config_name: art_studies features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 41227 num_examples: 298 - name: val num_bytes: 4581 num_examples: 33 - name: dev num_bytes: 1439 num_examples: 5 download_size: 46524 dataset_size: 47247 - config_name: basic_medicine features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 28820 num_examples: 175 - name: val num_bytes: 2627 num_examples: 19 - name: dev num_bytes: 1825 num_examples: 5 download_size: 37360 dataset_size: 33272 - config_name: business_administration features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 78387 num_examples: 301 - name: val num_bytes: 9225 num_examples: 33 - name: dev num_bytes: 3155 num_examples: 5 download_size: 75885 dataset_size: 90767 - config_name: chinese_language_and_literature features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 32328 num_examples: 209 - name: val num_bytes: 3446 num_examples: 23 - name: dev num_bytes: 1892 num_examples: 5 download_size: 42310 dataset_size: 37666 - config_name: civil_servant features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 181504 num_examples: 429 - name: val num_bytes: 21273 num_examples: 47 - name: dev num_bytes: 4576 num_examples: 5 download_size: 179936 dataset_size: 207353 - config_name: clinical_medicine features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 42161 num_examples: 200 - name: val num_bytes: 4167 num_examples: 22 - name: dev num_bytes: 1951 num_examples: 5 download_size: 48689 dataset_size: 48279 - config_name: college_chemistry features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 45798 num_examples: 224 - name: val num_bytes: 4443 num_examples: 24 - name: dev num_bytes: 3611 num_examples: 5 download_size: 53519 dataset_size: 53852 - config_name: college_economics features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 119734 num_examples: 497 - name: val num_bytes: 14461 num_examples: 55 - name: dev num_bytes: 3673 num_examples: 5 download_size: 106080 dataset_size: 137868 - config_name: college_physics features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 55731 num_examples: 176 - name: val num_bytes: 6145 num_examples: 19 - name: dev num_bytes: 3824 num_examples: 5 download_size: 62877 dataset_size: 65700 - config_name: college_programming features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 83541 num_examples: 342 - name: val num_bytes: 9543 num_examples: 37 - name: dev num_bytes: 2882 num_examples: 5 download_size: 82850 dataset_size: 95966 - config_name: computer_architecture features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 40613 num_examples: 193 - name: val num_bytes: 4149 num_examples: 21 - name: dev num_bytes: 2793 num_examples: 5 download_size: 48021 dataset_size: 47555 - config_name: computer_network features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 35408 num_examples: 171 - name: val num_bytes: 3799 num_examples: 19 - name: dev num_bytes: 2361 num_examples: 5 download_size: 43940 dataset_size: 41568 - config_name: discrete_mathematics features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 36045 num_examples: 153 - name: val num_bytes: 3424 num_examples: 16 - name: dev num_bytes: 2002 num_examples: 5 download_size: 42941 dataset_size: 41471 - config_name: education_science features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 55753 num_examples: 270 - name: val num_bytes: 5519 num_examples: 29 - name: dev num_bytes: 3093 num_examples: 5 download_size: 60878 dataset_size: 64365 - config_name: electrical_engineer features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 73727 num_examples: 339 - name: val num_bytes: 8315 num_examples: 37 - name: dev num_bytes: 2180 num_examples: 5 download_size: 75493 dataset_size: 84222 - config_name: environmental_impact_assessment_engineer features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 84680 num_examples: 281 - name: val num_bytes: 9186 num_examples: 31 - name: dev num_bytes: 2495 num_examples: 5 download_size: 73938 dataset_size: 96361 - config_name: fire_engineer features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 83611 num_examples: 282 - name: val num_bytes: 9998 num_examples: 31 - name: dev num_bytes: 2209 num_examples: 5 download_size: 80027 dataset_size: 95818 - config_name: high_school_biology features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 55242 num_examples: 175 - name: val num_bytes: 6105 num_examples: 19 - name: dev num_bytes: 2164 num_examples: 5 download_size: 60521 dataset_size: 63511 - config_name: high_school_chemistry features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 46918 num_examples: 172 - name: val num_bytes: 5625 num_examples: 19 - name: dev num_bytes: 2576 num_examples: 5 download_size: 55668 dataset_size: 55119 - config_name: high_school_chinese features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 110347 num_examples: 178 - name: val num_bytes: 10475 num_examples: 19 - name: dev num_bytes: 5290 num_examples: 5 download_size: 121511 dataset_size: 126112 - config_name: high_school_geography features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 41244 num_examples: 178 - name: val num_bytes: 3985 num_examples: 19 - name: dev num_bytes: 2087 num_examples: 5 download_size: 49899 dataset_size: 47316 - config_name: high_school_history features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 56196 num_examples: 182 - name: val num_bytes: 6618 num_examples: 20 - name: dev num_bytes: 2421 num_examples: 5 download_size: 68541 dataset_size: 65235 - config_name: high_school_mathematics features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 41080 num_examples: 166 - name: val num_bytes: 5144 num_examples: 18 - name: dev num_bytes: 3552 num_examples: 5 download_size: 53050 dataset_size: 49776 - config_name: high_school_physics features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 61682 num_examples: 175 - name: val num_bytes: 7266 num_examples: 19 - name: dev num_bytes: 2266 num_examples: 5 download_size: 66380 dataset_size: 71214 - config_name: high_school_politics features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 83356 num_examples: 176 - name: val num_bytes: 8909 num_examples: 19 - name: dev num_bytes: 4730 num_examples: 5 download_size: 90214 dataset_size: 96995 - config_name: ideological_and_moral_cultivation features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 35315 num_examples: 172 - name: val num_bytes: 3241 num_examples: 19 - name: dev num_bytes: 1296 num_examples: 5 download_size: 41532 dataset_size: 39852 - config_name: law features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 79782 num_examples: 221 - name: val num_bytes: 8119 num_examples: 24 - name: dev num_bytes: 4142 num_examples: 5 download_size: 83562 dataset_size: 92043 - config_name: legal_professional features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 121985 num_examples: 215 - name: val num_bytes: 12215 num_examples: 23 - name: dev num_bytes: 6974 num_examples: 5 download_size: 125081 dataset_size: 141174 - config_name: logic features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 144246 num_examples: 204 - name: val num_bytes: 15561 num_examples: 22 - name: dev num_bytes: 5641 num_examples: 5 download_size: 141258 dataset_size: 165448 - config_name: mao_zedong_thought features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 56699 num_examples: 219 - name: val num_bytes: 5487 num_examples: 24 - name: dev num_bytes: 3349 num_examples: 5 download_size: 57281 dataset_size: 65535 - config_name: marxism features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 38662 num_examples: 179 - name: val num_bytes: 4251 num_examples: 19 - name: dev num_bytes: 2142 num_examples: 5 download_size: 45030 dataset_size: 45055 - config_name: metrology_engineer features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 47484 num_examples: 219 - name: val num_bytes: 6116 num_examples: 24 - name: dev num_bytes: 2485 num_examples: 5 download_size: 55033 dataset_size: 56085 - config_name: middle_school_biology features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 47264 num_examples: 192 - name: val num_bytes: 5263 num_examples: 21 - name: dev num_bytes: 4327 num_examples: 5 download_size: 58872 dataset_size: 56854 - config_name: middle_school_chemistry features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 47575 num_examples: 185 - name: val num_bytes: 5654 num_examples: 20 - name: dev num_bytes: 3866 num_examples: 5 download_size: 59005 dataset_size: 57095 - config_name: middle_school_geography features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 23329 num_examples: 108 - name: val num_bytes: 2641 num_examples: 12 - name: dev num_bytes: 2148 num_examples: 5 download_size: 37528 dataset_size: 28118 - config_name: middle_school_history features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 47076 num_examples: 207 - name: val num_bytes: 5990 num_examples: 22 - name: dev num_bytes: 2014 num_examples: 5 download_size: 55763 dataset_size: 55080 - config_name: middle_school_mathematics features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 33142 num_examples: 177 - name: val num_bytes: 4897 num_examples: 19 - name: dev num_bytes: 3187 num_examples: 5 download_size: 45790 dataset_size: 41226 - config_name: middle_school_physics features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 48793 num_examples: 178 - name: val num_bytes: 5279 num_examples: 19 - name: dev num_bytes: 3531 num_examples: 5 download_size: 60336 dataset_size: 57603 - config_name: middle_school_politics features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 72478 num_examples: 193 - name: val num_bytes: 7320 num_examples: 21 - name: dev num_bytes: 3687 num_examples: 5 download_size: 75631 dataset_size: 83485 - config_name: modern_chinese_history features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 51247 num_examples: 212 - name: val num_bytes: 5188 num_examples: 23 - name: dev num_bytes: 2983 num_examples: 5 download_size: 58881 dataset_size: 59418 - config_name: operating_system features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 31146 num_examples: 179 - name: val num_bytes: 3299 num_examples: 19 - name: dev num_bytes: 2557 num_examples: 5 download_size: 39873 dataset_size: 37002 - config_name: physician features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 89801 num_examples: 443 - name: val num_bytes: 8710 num_examples: 49 - name: dev num_bytes: 2033 num_examples: 5 download_size: 91373 dataset_size: 100544 - config_name: plant_protection features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 31877 num_examples: 199 - name: val num_bytes: 3634 num_examples: 22 - name: dev num_bytes: 3726 num_examples: 5 download_size: 42730 dataset_size: 39237 - config_name: probability_and_statistics features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 56749 num_examples: 166 - name: val num_bytes: 5781 num_examples: 18 - name: dev num_bytes: 6769 num_examples: 5 download_size: 62933 dataset_size: 69299 - config_name: professional_tour_guide features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 41231 num_examples: 266 - name: val num_bytes: 4509 num_examples: 29 - name: dev num_bytes: 1764 num_examples: 5 download_size: 51538 dataset_size: 47504 - config_name: sports_science features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 32527 num_examples: 180 - name: val num_bytes: 3493 num_examples: 19 - name: dev num_bytes: 4182 num_examples: 5 download_size: 44846 dataset_size: 40202 - config_name: tax_accountant features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 174482 num_examples: 443 - name: val num_bytes: 18932 num_examples: 49 - name: dev num_bytes: 4274 num_examples: 5 download_size: 147810 dataset_size: 197688 - config_name: teacher_qualification features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 107369 num_examples: 399 - name: val num_bytes: 12220 num_examples: 44 - name: dev num_bytes: 3215 num_examples: 5 download_size: 105490 dataset_size: 122804 - config_name: urban_and_rural_planner features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 110377 num_examples: 418 - name: val num_bytes: 12793 num_examples: 46 - name: dev num_bytes: 3166 num_examples: 5 download_size: 100220 dataset_size: 126336 - config_name: veterinary_medicine features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 39465 num_examples: 210 - name: val num_bytes: 4559 num_examples: 23 - name: dev num_bytes: 2362 num_examples: 5 download_size: 48398 dataset_size: 46386 --- C-Eval is a comprehensive Chinese evaluation suite for foundation models. It consists of 13948 multi-choice questions spanning 52 diverse disciplines and four difficulty levels. Please visit our [website](https://cevalbenchmark.com/) and [GitHub](https://github.com/SJTU-LIT/ceval/tree/main) or check our [paper](https://arxiv.org/abs/2305.08322) for more details. Each subject consists of three splits: dev, val, and test. The dev set per subject consists of five exemplars with explanations for few-shot evaluation. The val set is intended to be used for hyperparameter tuning. And the test set is for model evaluation. Labels on the test split are not released, users are required to submit their results to automatically obtain test accuracy. [How to submit?](https://github.com/SJTU-LIT/ceval/tree/main#how-to-submit) ### Load the data ```python from datasets import load_dataset dataset=load_dataset(r"ceval/ceval-exam",name="computer_network") print(dataset['val'][0]) # {'id': 0, 'question': '使用位填充方法，以01111110为位首flag，数据为011011111111111111110010，求问传送时要添加几个0____', 'A': '1', 'B': '2', 'C': '3', 'D': '4', 'answer': 'C', 'explanation': ''} ``` More details on loading and using the data are at our [github page](https://github.com/SJTU-LIT/ceval#data). Please cite our paper if you use our dataset. ``` @article{huang2023ceval, title={C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models}, author={Huang, Yuzhen and Bai, Yuzhuo and Zhu, Zhihao and Zhang, Junlei and Zhang, Jinghan and Su, Tangjun and Liu, Junteng and Lv, Chuancheng and Zhang, Yikai and Lei, Jiayi and Fu, Yao and Sun, Maosong and He, Junxian}, journal={arXiv preprint arXiv:2305.08322}, year={2023} } ```
applied-ai-018/pretraining_v1-omega_books	applied-ai-018	"2024-08-05T19:01:31Z"	18,559	1	[ "size_categories:100M<n<1B", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]	null	"2024-07-31T08:53:54Z"	--- dataset_info: config_name: CC-MAIN-2013-20 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 splits: - name: train num_bytes: 235476901236 num_examples: 51901183 download_size: 138494178972 dataset_size: 235476901236 configs: - config_name: CC-MAIN-2013-20 data_files: - split: train path: CC-MAIN-2013-20/train-* ---
mteb/biblenlp-corpus-mmteb	mteb	"2024-05-07T00:47:48Z"	18,551	1	[ "annotations_creators:no-annotation", "language_creators:expert-generated", "multilinguality:translation", "multilinguality:multilingual", "language:aai", "language:aak", "language:aau", "language:aaz", "language:abt", "language:abx", "language:aby", "language:acf", "language:acr", "language:acu", "language:adz", "language:aer", "language:aey", "language:agd", "language:agg", "language:agm", "language:agn", "language:agr", "language:agt", "language:agu", "language:aia", "language:aii", "language:aka", "language:ake", "language:alp", "language:alq", "language:als", "language:aly", "language:ame", "language:amf", "language:amk", "language:amm", "language:amn", "language:amo", "language:amp", "language:amr", "language:amu", "language:amx", "language:anh", "language:anv", "language:aoi", "language:aoj", "language:aom", "language:aon", "language:apb", "language:ape", "language:apn", "language:apr", "language:apu", "language:apw", "language:apz", "language:arb", "language:are", "language:arl", "language:arn", "language:arp", "language:asm", "language:aso", "language:ata", "language:atb", "language:atd", "language:atg", "language:att", "language:auc", "language:aui", "language:auy", "language:avt", "language:awb", "language:awk", "language:awx", "language:azb", "language:azg", "language:azz", "language:bao", "language:bba", "language:bbb", "language:bbr", "language:bch", "language:bco", "language:bdd", "language:bea", "language:bef", "language:bel", "language:ben", "language:beo", "language:beu", "language:bgs", "language:bgt", "language:bhg", "language:bhl", "language:big", "language:bjk", "language:bjp", "language:bjr", "language:bjv", "language:bjz", "language:bkd", "language:bki", "language:bkq", "language:bkx", "language:bla", "language:blw", "language:blz", "language:bmh", "language:bmk", "language:bmr", "language:bmu", "language:bnp", "language:boa", "language:boj", "language:bon", "language:box", "language:bpr", "language:bps", "language:bqc", "language:bqp", "language:bre", "language:bsj", "language:bsn", "language:bsp", "language:bss", "language:buk", "language:bus", "language:bvd", "language:bvr", "language:bxh", "language:byr", "language:byx", "language:bzd", "language:bzh", "language:bzj", "language:caa", "language:cab", "language:cac", "language:caf", "language:cak", "language:cao", "language:cap", "language:car", "language:cav", "language:cax", "language:cbc", "language:cbi", "language:cbk", "language:cbr", "language:cbs", "language:cbt", "language:cbu", "language:cbv", "language:cco", "language:ceb", "language:cek", "language:ces", "language:cgc", "language:cha", "language:chd", "language:chf", "language:chk", "language:chq", "language:chz", "language:cjo", "language:cjv", "language:ckb", "language:cle", "language:clu", "language:cme", "language:cmn", "language:cni", "language:cnl", "language:cnt", "language:cof", "language:con", "language:cop", "language:cot", "language:cpa", "language:cpb", "language:cpc", "language:cpu", "language:cpy", "language:crn", "language:crx", "language:cso", "language:csy", "language:cta", "language:cth", "language:ctp", "language:ctu", "language:cub", "language:cuc", "language:cui", "language:cuk", "language:cut", "language:cux", "language:cwe", "language:cya", "language:daa", "language:dad", "language:dah", "language:dan", "language:ded", "language:deu", "language:dgc", "language:dgr", "language:dgz", "language:dhg", "language:dif", "language:dik", "language:dji", "language:djk", "language:djr", "language:dob", "language:dop", "language:dov", "language:dwr", "language:dww", "language:dwy", "language:ebk", "language:eko", "language:emi", "language:emp", "language:eng", "language:enq", "language:epo", "language:eri", "language:ese", "language:esk", "language:etr", "language:ewe", "language:faa", "language:fai", "language:far", "language:ffm", "language:for", "language:fra", "language:fue", "language:fuf", "language:fuh", "language:gah", "language:gai", "language:gam", "language:gaw", "language:gdn", "language:gdr", "language:geb", "language:gfk", "language:ghs", "language:glk", "language:gmv", "language:gng", "language:gnn", "language:gnw", "language:gof", "language:grc", "language:gub", "language:guh", "language:gui", "language:guj", "language:gul", "language:gum", "language:gun", "language:guo", "language:gup", "language:gux", "language:gvc", "language:gvf", "language:gvn", "language:gvs", "language:gwi", "language:gym", "language:gyr", "language:hat", "language:hau", "language:haw", "language:hbo", "language:hch", "language:heb", "language:heg", "language:hin", "language:hix", "language:hla", "language:hlt", "language:hmo", "language:hns", "language:hop", "language:hot", "language:hrv", "language:hto", "language:hub", "language:hui", "language:hun", "language:hus", "language:huu", "language:huv", "language:hvn", "language:ian", "language:ign", "language:ikk", "language:ikw", "language:ilo", "language:imo", "language:inb", "language:ind", "language:ino", "language:iou", "language:ipi", "language:isn", "language:ita", "language:iws", "language:ixl", "language:jac", "language:jae", "language:jao", "language:jic", "language:jid", "language:jiv", "language:jni", "language:jpn", "language:jvn", "language:kan", "language:kaq", "language:kbc", "language:kbh", "language:kbm", "language:kbq", "language:kdc", "language:kde", "language:kdl", "language:kek", "language:ken", "language:kew", "language:kgf", "language:kgk", "language:kgp", "language:khs", "language:khz", "language:kik", "language:kiw", "language:kiz", "language:kje", "language:kjn", "language:kjs", "language:kkc", "language:kkl", "language:klt", "language:klv", "language:kmg", "language:kmh", "language:kmk", "language:kmo", "language:kms", "language:kmu", "language:kne", "language:knf", "language:knj", "language:knv", "language:kos", "language:kpf", "language:kpg", "language:kpj", "language:kpr", "language:kpw", "language:kpx", "language:kqa", "language:kqc", "language:kqf", "language:kql", "language:kqw", "language:ksd", "language:ksj", "language:ksr", "language:ktm", "language:kto", "language:kud", "language:kue", "language:kup", "language:kvg", "language:kvn", "language:kwd", "language:kwf", "language:kwi", "language:kwj", "language:kyc", "language:kyf", "language:kyg", "language:kyq", "language:kyz", "language:kze", "language:lac", "language:lat", "language:lbb", "language:lbk", "language:lcm", "language:leu", "language:lex", "language:lgl", "language:lid", "language:lif", "language:lin", "language:lit", "language:llg", "language:lug", "language:luo", "language:lww", "language:maa", "language:maj", "language:mal", "language:mam", "language:maq", "language:mar", "language:mau", "language:mav", "language:maz", "language:mbb", "language:mbc", "language:mbh", "language:mbj", "language:mbl", "language:mbs", "language:mbt", "language:mca", "language:mcb", "language:mcd", "language:mcf", "language:mco", "language:mcp", "language:mcq", "language:mcr", "language:mdy", "language:med", "language:mee", "language:mek", "language:meq", "language:met", "language:meu", "language:mgc", "language:mgh", "language:mgw", "language:mhl", "language:mib", "language:mic", "language:mie", "language:mig", "language:mih", "language:mil", "language:mio", "language:mir", "language:mit", "language:miz", "language:mjc", "language:mkj", "language:mkl", "language:mkn", "language:mks", "language:mle", "language:mlh", "language:mlp", "language:mmo", "language:mmx", "language:mna", "language:mop", "language:mox", "language:mph", "language:mpj", "language:mpm", "language:mpp", "language:mps", "language:mpt", "language:mpx", "language:mqb", "language:mqj", "language:msb", "language:msc", "language:msk", "language:msm", "language:msy", "language:mti", "language:mto", "language:mux", "language:muy", "language:mva", "language:mvn", "language:mwc", "language:mwe", "language:mwf", "language:mwp", "language:mxb", "language:mxp", "language:mxq", "language:mxt", "language:mya", "language:myk", "language:myu", "language:myw", "language:myy", "language:mzz", "language:nab", "language:naf", "language:nak", "language:nas", "language:nay", "language:nbq", "language:nca", "language:nch", "language:ncj", "language:ncl", "language:ncu", "language:ndg", "language:ndj", "language:nfa", "language:ngp", "language:ngu", "language:nhe", "language:nhg", "language:nhi", "language:nho", "language:nhr", "language:nhu", "language:nhw", "language:nhy", "language:nif", "language:nii", "language:nin", "language:nko", "language:nld", "language:nlg", "language:nmw", "language:nna", "language:nnq", "language:noa", "language:nop", "language:not", "language:nou", "language:npi", "language:npl", "language:nsn", "language:nss", "language:ntj", "language:ntp", "language:ntu", "language:nuy", "language:nvm", "language:nwi", "language:nya", "language:nys", "language:nyu", "language:obo", "language:okv", "language:omw", "language:ong", "language:ons", "language:ood", "language:opm", "language:ory", "language:ote", "language:otm", "language:otn", "language:otq", "language:ots", "language:pab", "language:pad", "language:pah", "language:pan", "language:pao", "language:pes", "language:pib", "language:pio", "language:pir", "language:piu", "language:pjt", "language:pls", "language:plu", "language:pma", "language:poe", "language:poh", "language:poi", "language:pol", "language:pon", "language:por", "language:poy", "language:ppo", "language:prf", "language:pri", "language:ptp", "language:ptu", "language:pwg", "language:qub", "language:quc", "language:quf", "language:quh", "language:qul", "language:qup", "language:qvc", "language:qve", "language:qvh", "language:qvm", "language:qvn", "language:qvs", "language:qvw", "language:qvz", "language:qwh", "language:qxh", "language:qxn", "language:qxo", "language:rai", "language:reg", "language:rgu", "language:rkb", "language:rmc", "language:rmy", "language:ron", "language:roo", "language:rop", "language:row", "language:rro", "language:ruf", "language:rug", "language:rus", "language:rwo", "language:sab", "language:san", "language:sbe", "language:sbk", "language:sbs", "language:seh", "language:sey", "language:sgb", "language:sgz", "language:shj", "language:shp", "language:sim", "language:sja", "language:sll", "language:smk", "language:snc", "language:snn", "language:snp", "language:snx", "language:sny", "language:som", "language:soq", "language:soy", "language:spa", "language:spl", "language:spm", "language:spp", "language:sps", "language:spy", "language:sri", "language:srm", "language:srn", "language:srp", "language:srq", "language:ssd", "language:ssg", "language:ssx", "language:stp", "language:sua", "language:sue", "language:sus", "language:suz", "language:swe", "language:swh", "language:swp", "language:sxb", "language:tac", "language:taj", "language:tam", "language:tav", "language:taw", "language:tbc", "language:tbf", "language:tbg", "language:tbl", "language:tbo", "language:tbz", "language:tca", "language:tcs", "language:tcz", "language:tdt", "language:tee", "language:tel", "language:ter", "language:tet", "language:tew", "language:tfr", "language:tgk", "language:tgl", "language:tgo", "language:tgp", "language:tha", "language:thd", "language:tif", "language:tim", "language:tiw", "language:tiy", "language:tke", "language:tku", "language:tlf", "language:tmd", "language:tna", "language:tnc", "language:tnk", "language:tnn", "language:tnp", "language:toc", "language:tod", "language:tof", "language:toj", "language:ton", "language:too", "language:top", "language:tos", "language:tpa", "language:tpi", "language:tpt", "language:tpz", "language:trc", "language:tsw", "language:ttc", "language:tte", "language:tuc", "language:tue", "language:tuf", "language:tuo", "language:tur", "language:tvk", "language:twi", "language:txq", "language:txu", "language:tzj", "language:tzo", "language:ubr", "language:ubu", "language:udu", "language:uig", "language:ukr", "language:uli", "language:ulk", "language:upv", "language:ura", "language:urb", "language:urd", "language:uri", "language:urt", "language:urw", "language:usa", "language:usp", "language:uvh", "language:uvl", "language:vid", "language:vie", "language:viv", "language:vmy", "language:waj", "language:wal", "language:wap", "language:wat", "language:wbi", "language:wbp", "language:wed", "language:wer", "language:wim", "language:wiu", "language:wiv", "language:wmt", "language:wmw", "language:wnc", "language:wnu", "language:wol", "language:wos", "language:wrk", "language:wro", "language:wrs", "language:wsk", "language:wuv", "language:xav", "language:xbi", "language:xed", "language:xla", "language:xnn", "language:xon", "language:xsi", "language:xtd", "language:xtm", "language:yaa", "language:yad", "language:yal", "language:yap", "language:yaq", "language:yby", "language:ycn", "language:yka", "language:yle", "language:yml", "language:yon", "language:yor", "language:yrb", "language:yre", "language:yss", "language:yuj", "language:yut", "language:yuw", "language:yva", "language:zaa", "language:zab", "language:zac", "language:zad", "language:zai", "language:zaj", "language:zam", "language:zao", "language:zap", "language:zar", "language:zas", "language:zat", "language:zav", "language:zaw", "language:zca", "language:zga", "language:zia", "language:ziw", "language:zlm", "language:zos", "language:zpc", "language:zpl", "language:zpm", "language:zpo", "language:zpq", "language:zpu", "language:zpv", "language:zpz", "language:zsr", "language:ztq", "language:zty", "language:zyp", "language:be", "language:br", "language:cs", "language:ch", "language:zh", "language:de", "language:en", "language:eo", "language:fr", "language:ht", "language:he", "language:hr", "language:id", "language:it", "language:ja", "language:la", "language:nl", "language:ru", "language:sa", "language:so", "language:es", "language:sr", "language:sv", "language:to", "language:uk", "language:vi", "license:cc-by-4.0", "license:other", "size_categories:1M<n<10M", "format:json", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "region:us" ]	null	"2024-05-05T22:41:26Z"	--- annotations_creators: - no-annotation language_creators: - expert-generated language: - aai - aak - aau - aaz - abt - abx - aby - acf - acr - acu - adz - aer - aey - agd - agg - agm - agn - agr - agt - agu - aia - aii - aka - ake - alp - alq - als - aly - ame - amf - amk - amm - amn - amo - amp - amr - amu - amx - anh - anv - aoi - aoj - aom - aon - apb - ape - apn - apr - apu - apw - apz - arb - are - arl - arn - arp - asm - aso - ata - atb - atd - atg - att - auc - aui - auy - avt - awb - awk - awx - azb - azg - azz - bao - bba - bbb - bbr - bch - bco - bdd - bea - bef - bel - ben - beo - beu - bgs - bgt - bhg - bhl - big - bjk - bjp - bjr - bjv - bjz - bkd - bki - bkq - bkx - bla - blw - blz - bmh - bmk - bmr - bmu - bnp - boa - boj - bon - box - bpr - bps - bqc - bqp - bre - bsj - bsn - bsp - bss - buk - bus - bvd - bvr - bxh - byr - byx - bzd - bzh - bzj - caa - cab - cac - caf - cak - cao - cap - car - cav - cax - cbc - cbi - cbk - cbr - cbs - cbt - cbu - cbv - cco - ceb - cek - ces - cgc - cha - chd - chf - chk - chq - chz - cjo - cjv - ckb - cle - clu - cme - cmn - cni - cnl - cnt - cof - con - cop - cot - cpa - cpb - cpc - cpu - cpy - crn - crx - cso - csy - cta - cth - ctp - ctu - cub - cuc - cui - cuk - cut - cux - cwe - cya - daa - dad - dah - dan - ded - deu - dgc - dgr - dgz - dhg - dif - dik - dji - djk - djr - dob - dop - dov - dwr - dww - dwy - ebk - eko - emi - emp - eng - enq - epo - eri - ese - esk - etr - ewe - faa - fai - far - ffm - for - fra - fue - fuf - fuh - gah - gai - gam - gaw - gdn - gdr - geb - gfk - ghs - glk - gmv - gng - gnn - gnw - gof - grc - gub - guh - gui - guj - gul - gum - gun - guo - gup - gux - gvc - gvf - gvn - gvs - gwi - gym - gyr - hat - hau - haw - hbo - hch - heb - heg - hin - hix - hla - hlt - hmo - hns - hop - hot - hrv - hto - hub - hui - hun - hus - huu - huv - hvn - ian - ign - ikk - ikw - ilo - imo - inb - ind - ino - iou - ipi - isn - ita - iws - ixl - jac - jae - jao - jic - jid - jiv - jni - jpn - jvn - kan - kaq - kbc - kbh - kbm - kbq - kdc - kde - kdl - kek - ken - kew - kgf - kgk - kgp - khs - khz - kik - kiw - kiz - kje - kjn - kjs - kkc - kkl - klt - klv - kmg - kmh - kmk - kmo - kms - kmu - kne - knf - knj - knv - kos - kpf - kpg - kpj - kpr - kpw - kpx - kqa - kqc - kqf - kql - kqw - ksd - ksj - ksr - ktm - kto - kud - kue - kup - kvg - kvn - kwd - kwf - kwi - kwj - kyc - kyf - kyg - kyq - kyz - kze - lac - lat - lbb - lbk - lcm - leu - lex - lgl - lid - lif - lin - lit - llg - lug - luo - lww - maa - maj - mal - mam - maq - mar - mau - mav - maz - mbb - mbc - mbh - mbj - mbl - mbs - mbt - mca - mcb - mcd - mcf - mco - mcp - mcq - mcr - mdy - med - mee - mek - meq - met - meu - mgc - mgh - mgw - mhl - mib - mic - mie - mig - mih - mil - mio - mir - mit - miz - mjc - mkj - mkl - mkn - mks - mle - mlh - mlp - mmo - mmx - mna - mop - mox - mph - mpj - mpm - mpp - mps - mpt - mpx - mqb - mqj - msb - msc - msk - msm - msy - mti - mto - mux - muy - mva - mvn - mwc - mwe - mwf - mwp - mxb - mxp - mxq - mxt - mya - myk - myu - myw - myy - mzz - nab - naf - nak - nas - nay - nbq - nca - nch - ncj - ncl - ncu - ndg - ndj - nfa - ngp - ngu - nhe - nhg - nhi - nho - nhr - nhu - nhw - nhy - nif - nii - nin - nko - nld - nlg - nmw - nna - nnq - noa - nop - not - nou - npi - npl - nsn - nss - ntj - ntp - ntu - nuy - nvm - nwi - nya - nys - nyu - obo - okv - omw - ong - ons - ood - opm - ory - ote - otm - otn - otq - ots - pab - pad - pah - pan - pao - pes - pib - pio - pir - piu - pjt - pls - plu - pma - poe - poh - poi - pol - pon - por - poy - ppo - prf - pri - ptp - ptu - pwg - qub - quc - quf - quh - qul - qup - qvc - qve - qvh - qvm - qvn - qvs - qvw - qvz - qwh - qxh - qxn - qxo - rai - reg - rgu - rkb - rmc - rmy - ron - roo - rop - row - rro - ruf - rug - rus - rwo - sab - san - sbe - sbk - sbs - seh - sey - sgb - sgz - shj - shp - sim - sja - sll - smk - snc - snn - snp - snx - sny - som - soq - soy - spa - spl - spm - spp - sps - spy - sri - srm - srn - srp - srq - ssd - ssg - ssx - stp - sua - sue - sus - suz - swe - swh - swp - sxb - tac - taj - tam - tav - taw - tbc - tbf - tbg - tbl - tbo - tbz - tca - tcs - tcz - tdt - tee - tel - ter - tet - tew - tfr - tgk - tgl - tgo - tgp - tha - thd - tif - tim - tiw - tiy - tke - tku - tlf - tmd - tna - tnc - tnk - tnn - tnp - toc - tod - tof - toj - ton - too - top - tos - tpa - tpi - tpt - tpz - trc - tsw - ttc - tte - tuc - tue - tuf - tuo - tur - tvk - twi - txq - txu - tzj - tzo - ubr - ubu - udu - uig - ukr - uli - ulk - upv - ura - urb - urd - uri - urt - urw - usa - usp - uvh - uvl - vid - vie - viv - vmy - waj - wal - wap - wat - wbi - wbp - wed - wer - wim - wiu - wiv - wmt - wmw - wnc - wnu - wol - wos - wrk - wro - wrs - wsk - wuv - xav - xbi - xed - xla - xnn - xon - xsi - xtd - xtm - yaa - yad - yal - yap - yaq - yby - ycn - yka - yle - yml - yon - yor - yrb - yre - yss - yuj - yut - yuw - yva - zaa - zab - zac - zad - zai - zaj - zam - zao - zap - zar - zas - zat - zav - zaw - zca - zga - zia - ziw - zlm - zos - zpc - zpl - zpm - zpo - zpq - zpu - zpv - zpz - zsr - ztq - zty - zyp - be - br - cs - ch - zh - de - en - eo - fr - ht - he - hr - id - it - ja - la - nl - ru - sa - so - es - sr - sv - to - uk - vi license: - cc-by-4.0 - other multilinguality: - translation - multilingual pretty_name: biblenlp-corpus-mmteb size_categories: - 1M<n<10M configs: - config_name: default data_files: - path: train/.jsonl.gz split: train - path: test/.jsonl.gz split: test - path: validation/*.jsonl.gz split: validation - config_name: eng_Latn-zac_Latn data_files: - path: train/eng_Latn-zac_Latn.jsonl.gz split: train - path: test/eng_Latn-zac_Latn.jsonl.gz split: test - path: validation/eng_Latn-zac_Latn.jsonl.gz split: validation - config_name: eng_Latn-lit_Latn data_files: - path: train/eng_Latn-lit_Latn.jsonl.gz split: train - path: test/eng_Latn-lit_Latn.jsonl.gz split: test - path: validation/eng_Latn-lit_Latn.jsonl.gz split: validation - config_name: eng_Latn-cgc_Latn data_files: - path: train/eng_Latn-cgc_Latn.jsonl.gz split: train - path: test/eng_Latn-cgc_Latn.jsonl.gz split: test - path: validation/eng_Latn-cgc_Latn.jsonl.gz split: validation - config_name: eng_Latn-guh_Latn data_files: - path: train/eng_Latn-guh_Latn.jsonl.gz split: train - path: test/eng_Latn-guh_Latn.jsonl.gz split: test - path: validation/eng_Latn-guh_Latn.jsonl.gz split: validation - config_name: eng_Latn-ckb_Arab data_files: - path: train/eng_Latn-ckb_Arab.jsonl.gz split: train - path: test/eng_Latn-ckb_Arab.jsonl.gz split: test - path: validation/eng_Latn-ckb_Arab.jsonl.gz split: validation - config_name: eng_Latn-cop_Copt data_files: - path: train/eng_Latn-cop_Copt.jsonl.gz split: train - path: test/eng_Latn-cop_Copt.jsonl.gz split: test - path: validation/eng_Latn-cop_Copt.jsonl.gz split: validation - config_name: eng_Latn-lif_Deva data_files: - path: train/eng_Latn-lif_Deva.jsonl.gz split: train - path: test/eng_Latn-lif_Deva.jsonl.gz split: test - path: validation/eng_Latn-lif_Deva.jsonl.gz split: validation - config_name: eng_Latn-cwe_Latn data_files: - path: train/eng_Latn-cwe_Latn.jsonl.gz split: train - path: test/eng_Latn-cwe_Latn.jsonl.gz split: test - path: validation/eng_Latn-cwe_Latn.jsonl.gz split: validation - config_name: eng_Latn-kwj_Latn data_files: - path: train/eng_Latn-kwj_Latn.jsonl.gz split: train - path: test/eng_Latn-kwj_Latn.jsonl.gz split: test - path: validation/eng_Latn-kwj_Latn.jsonl.gz split: validation - config_name: eng_Latn-srp_Latn data_files: - path: train/eng_Latn-srp_Latn.jsonl.gz split: train - path: test/eng_Latn-srp_Latn.jsonl.gz split: test - path: validation/eng_Latn-srp_Latn.jsonl.gz split: validation - config_name: eng_Latn-qvn_Latn data_files: - path: train/eng_Latn-qvn_Latn.jsonl.gz split: train - path: test/eng_Latn-qvn_Latn.jsonl.gz split: test - path: validation/eng_Latn-qvn_Latn.jsonl.gz split: validation - config_name: eng_Latn-tsw_Latn data_files: - path: train/eng_Latn-tsw_Latn.jsonl.gz split: train - path: test/eng_Latn-tsw_Latn.jsonl.gz split: test - path: validation/eng_Latn-tsw_Latn.jsonl.gz split: validation - config_name: eng_Latn-wro_Latn data_files: - path: train/eng_Latn-wro_Latn.jsonl.gz split: train - path: test/eng_Latn-wro_Latn.jsonl.gz split: test - path: validation/eng_Latn-wro_Latn.jsonl.gz split: validation - config_name: eng_Latn-tod_Latn data_files: - path: train/eng_Latn-tod_Latn.jsonl.gz split: train - path: test/eng_Latn-tod_Latn.jsonl.gz split: test - path: validation/eng_Latn-tod_Latn.jsonl.gz split: validation - config_name: eng_Latn-bco_Latn data_files: - path: train/eng_Latn-bco_Latn.jsonl.gz split: train - path: test/eng_Latn-bco_Latn.jsonl.gz split: test - path: validation/eng_Latn-bco_Latn.jsonl.gz split: validation - config_name: eng_Latn-ikk_Latn data_files: - path: train/eng_Latn-ikk_Latn.jsonl.gz split: train - path: test/eng_Latn-ikk_Latn.jsonl.gz split: test - path: validation/eng_Latn-ikk_Latn.jsonl.gz split: validation - config_name: eng_Latn-tna_Latn data_files: - path: train/eng_Latn-tna_Latn.jsonl.gz split: train - path: test/eng_Latn-tna_Latn.jsonl.gz split: test - path: validation/eng_Latn-tna_Latn.jsonl.gz split: validation - config_name: eng_Latn-swp_Latn data_files: - path: train/eng_Latn-swp_Latn.jsonl.gz split: train - path: test/eng_Latn-swp_Latn.jsonl.gz split: test - path: validation/eng_Latn-swp_Latn.jsonl.gz split: validation - config_name: eng_Latn-agm_Latn data_files: - path: train/eng_Latn-agm_Latn.jsonl.gz split: train - path: test/eng_Latn-agm_Latn.jsonl.gz split: test - path: validation/eng_Latn-agm_Latn.jsonl.gz split: validation - config_name: eng_Latn-con_Latn data_files: - path: train/eng_Latn-con_Latn.jsonl.gz split: train - path: test/eng_Latn-con_Latn.jsonl.gz split: test - path: validation/eng_Latn-con_Latn.jsonl.gz split: validation - config_name: eng_Latn-sgz_Latn data_files: - path: train/eng_Latn-sgz_Latn.jsonl.gz split: train - path: test/eng_Latn-sgz_Latn.jsonl.gz split: test - path: validation/eng_Latn-sgz_Latn.jsonl.gz split: validation - config_name: eng_Latn-mwc_Latn data_files: - path: train/eng_Latn-mwc_Latn.jsonl.gz split: train - path: test/eng_Latn-mwc_Latn.jsonl.gz split: test - path: validation/eng_Latn-mwc_Latn.jsonl.gz split: validation - config_name: eng_Latn-azb_Arab data_files: - path: train/eng_Latn-azb_Arab.jsonl.gz split: train - path: test/eng_Latn-azb_Arab.jsonl.gz split: test - path: validation/eng_Latn-azb_Arab.jsonl.gz split: validation - config_name: eng_Latn-aon_Latn data_files: - path: train/eng_Latn-aon_Latn.jsonl.gz split: train - path: test/eng_Latn-aon_Latn.jsonl.gz split: test - path: validation/eng_Latn-aon_Latn.jsonl.gz split: validation - config_name: eng_Latn-mvn_Latn data_files: - path: train/eng_Latn-mvn_Latn.jsonl.gz split: train - path: test/eng_Latn-mvn_Latn.jsonl.gz split: test - path: validation/eng_Latn-mvn_Latn.jsonl.gz split: validation - config_name: eng_Latn-mpj_Latn data_files: - path: train/eng_Latn-mpj_Latn.jsonl.gz split: train - path: test/eng_Latn-mpj_Latn.jsonl.gz split: test - path: validation/eng_Latn-mpj_Latn.jsonl.gz split: validation - config_name: eng_Latn-cot_Latn data_files: - path: train/eng_Latn-cot_Latn.jsonl.gz split: train - path: test/eng_Latn-cot_Latn.jsonl.gz split: test - path: validation/eng_Latn-cot_Latn.jsonl.gz split: validation - config_name: eng_Latn-tuo_Latn data_files: - path: train/eng_Latn-tuo_Latn.jsonl.gz split: train - path: test/eng_Latn-tuo_Latn.jsonl.gz split: test - path: validation/eng_Latn-tuo_Latn.jsonl.gz split: validation - config_name: eng_Latn-iou_Latn data_files: - path: train/eng_Latn-iou_Latn.jsonl.gz split: train - path: test/eng_Latn-iou_Latn.jsonl.gz split: test - path: validation/eng_Latn-iou_Latn.jsonl.gz split: validation - config_name: eng_Latn-big_Latn data_files: - path: train/eng_Latn-big_Latn.jsonl.gz split: train - path: test/eng_Latn-big_Latn.jsonl.gz split: test - path: validation/eng_Latn-big_Latn.jsonl.gz split: validation - config_name: eng_Latn-apw_Latn data_files: - path: train/eng_Latn-apw_Latn.jsonl.gz split: train - path: test/eng_Latn-apw_Latn.jsonl.gz split: test - path: validation/eng_Latn-apw_Latn.jsonl.gz split: validation - config_name: eng_Latn-kpx_Latn data_files: - path: train/eng_Latn-kpx_Latn.jsonl.gz split: train - path: test/eng_Latn-kpx_Latn.jsonl.gz split: test - path: validation/eng_Latn-kpx_Latn.jsonl.gz split: validation - config_name: eng_Latn-cui_Latn data_files: - path: train/eng_Latn-cui_Latn.jsonl.gz split: train - path: test/eng_Latn-cui_Latn.jsonl.gz split: test - path: validation/eng_Latn-cui_Latn.jsonl.gz split: validation - config_name: eng_Latn-bnp_Latn data_files: - path: train/eng_Latn-bnp_Latn.jsonl.gz split: train - path: test/eng_Latn-bnp_Latn.jsonl.gz split: test - path: validation/eng_Latn-bnp_Latn.jsonl.gz split: validation - config_name: eng_Latn-ngp_Latn data_files: - path: train/eng_Latn-ngp_Latn.jsonl.gz split: train - path: test/eng_Latn-ngp_Latn.jsonl.gz split: test - path: validation/eng_Latn-ngp_Latn.jsonl.gz split: validation - config_name: eng_Latn-mkj_Latn data_files: - path: train/eng_Latn-mkj_Latn.jsonl.gz split: train - path: test/eng_Latn-mkj_Latn.jsonl.gz split: test - path: validation/eng_Latn-mkj_Latn.jsonl.gz split: validation - config_name: eng_Latn-chf_Latn data_files: - path: train/eng_Latn-chf_Latn.jsonl.gz split: train - path: test/eng_Latn-chf_Latn.jsonl.gz split: test - path: validation/eng_Latn-chf_Latn.jsonl.gz split: validation - config_name: eng_Latn-tca_Latn data_files: - path: train/eng_Latn-tca_Latn.jsonl.gz split: train - path: test/eng_Latn-tca_Latn.jsonl.gz split: test - path: validation/eng_Latn-tca_Latn.jsonl.gz split: validation - config_name: eng_Latn-poh_Latn data_files: - path: train/eng_Latn-poh_Latn.jsonl.gz split: train - path: test/eng_Latn-poh_Latn.jsonl.gz split: test - path: validation/eng_Latn-poh_Latn.jsonl.gz split: validation - config_name: eng_Latn-ese_Latn data_files: - path: train/eng_Latn-ese_Latn.jsonl.gz split: train - path: test/eng_Latn-ese_Latn.jsonl.gz split: test - path: validation/eng_Latn-ese_Latn.jsonl.gz split: validation - config_name: eng_Latn-plu_Latn data_files: - path: train/eng_Latn-plu_Latn.jsonl.gz split: train - path: test/eng_Latn-plu_Latn.jsonl.gz split: test - path: validation/eng_Latn-plu_Latn.jsonl.gz split: validation - config_name: eng_Latn-crn_Latn data_files: - path: train/eng_Latn-crn_Latn.jsonl.gz split: train - path: test/eng_Latn-crn_Latn.jsonl.gz split: test - path: validation/eng_Latn-crn_Latn.jsonl.gz split: validation - config_name: eng_Latn-mxt_Latn data_files: - path: train/eng_Latn-mxt_Latn.jsonl.gz split: train - path: test/eng_Latn-mxt_Latn.jsonl.gz split: test - path: validation/eng_Latn-mxt_Latn.jsonl.gz split: validation - config_name: eng_Latn-tnk_Latn data_files: - path: train/eng_Latn-tnk_Latn.jsonl.gz split: train - path: test/eng_Latn-tnk_Latn.jsonl.gz split: test - path: validation/eng_Latn-tnk_Latn.jsonl.gz split: validation - config_name: eng_Latn-zar_Latn data_files: - path: train/eng_Latn-zar_Latn.jsonl.gz split: train - path: test/eng_Latn-zar_Latn.jsonl.gz split: test - path: validation/eng_Latn-zar_Latn.jsonl.gz split: validation - config_name: eng_Latn-sri_Latn data_files: - path: train/eng_Latn-sri_Latn.jsonl.gz split: train - path: test/eng_Latn-sri_Latn.jsonl.gz split: test - path: validation/eng_Latn-sri_Latn.jsonl.gz split: validation - config_name: eng_Latn-pan_Guru data_files: - path: train/eng_Latn-pan_Guru.jsonl.gz split: train - path: test/eng_Latn-pan_Guru.jsonl.gz split: test - path: validation/eng_Latn-pan_Guru.jsonl.gz split: validation - config_name: eng_Latn-kik_Latn data_files: - path: train/eng_Latn-kik_Latn.jsonl.gz split: train - path: test/eng_Latn-kik_Latn.jsonl.gz split: test - path: validation/eng_Latn-kik_Latn.jsonl.gz split: validation - config_name: eng_Latn-yby_Latn data_files: - path: train/eng_Latn-yby_Latn.jsonl.gz split: train - path: test/eng_Latn-yby_Latn.jsonl.gz split: test - path: validation/eng_Latn-yby_Latn.jsonl.gz split: validation - config_name: eng_Latn-qup_Latn data_files: - path: train/eng_Latn-qup_Latn.jsonl.gz split: train - path: test/eng_Latn-qup_Latn.jsonl.gz split: test - path: validation/eng_Latn-qup_Latn.jsonl.gz split: validation - config_name: eng_Latn-mco_Latn data_files: - path: train/eng_Latn-mco_Latn.jsonl.gz split: train - path: test/eng_Latn-mco_Latn.jsonl.gz split: test - path: validation/eng_Latn-mco_Latn.jsonl.gz split: validation - config_name: eng_Latn-gux_Latn data_files: - path: train/eng_Latn-gux_Latn.jsonl.gz split: train - path: test/eng_Latn-gux_Latn.jsonl.gz split: test - path: validation/eng_Latn-gux_Latn.jsonl.gz split: validation - config_name: eng_Latn-spa_Latn data_files: - path: train/eng_Latn-spa_Latn.jsonl.gz split: train - path: test/eng_Latn-spa_Latn.jsonl.gz split: test - path: validation/eng_Latn-spa_Latn.jsonl.gz split: validation - config_name: eng_Latn-heg_Latn data_files: - path: train/eng_Latn-heg_Latn.jsonl.gz split: train - path: test/eng_Latn-heg_Latn.jsonl.gz split: test - path: validation/eng_Latn-heg_Latn.jsonl.gz split: validation - config_name: eng_Latn-gwi_Latn data_files: - path: train/eng_Latn-gwi_Latn.jsonl.gz split: train - path: test/eng_Latn-gwi_Latn.jsonl.gz split: test - path: validation/eng_Latn-gwi_Latn.jsonl.gz split: validation - config_name: eng_Latn-ttc_Latn data_files: - path: train/eng_Latn-ttc_Latn.jsonl.gz split: train - path: test/eng_Latn-ttc_Latn.jsonl.gz split: test - path: validation/eng_Latn-ttc_Latn.jsonl.gz split: validation - config_name: eng_Latn-mqj_Latn data_files: - path: train/eng_Latn-mqj_Latn.jsonl.gz split: train - path: test/eng_Latn-mqj_Latn.jsonl.gz split: test - path: validation/eng_Latn-mqj_Latn.jsonl.gz split: validation - config_name: eng_Latn-pjt_Latn data_files: - path: train/eng_Latn-pjt_Latn.jsonl.gz split: train - path: test/eng_Latn-pjt_Latn.jsonl.gz split: test - path: validation/eng_Latn-pjt_Latn.jsonl.gz split: validation - config_name: eng_Latn-gui_Latn data_files: - path: train/eng_Latn-gui_Latn.jsonl.gz split: train - path: test/eng_Latn-gui_Latn.jsonl.gz split: test - path: validation/eng_Latn-gui_Latn.jsonl.gz split: validation - config_name: eng_Latn-tel_Telu data_files: - path: train/eng_Latn-tel_Telu.jsonl.gz split: train - path: test/eng_Latn-tel_Telu.jsonl.gz split: test - path: validation/eng_Latn-tel_Telu.jsonl.gz split: validation - config_name: eng_Latn-lbb_Latn data_files: - path: train/eng_Latn-lbb_Latn.jsonl.gz split: train - path: test/eng_Latn-lbb_Latn.jsonl.gz split: test - path: validation/eng_Latn-lbb_Latn.jsonl.gz split: validation - config_name: eng_Latn-cbr_Latn data_files: - path: train/eng_Latn-cbr_Latn.jsonl.gz split: train - path: test/eng_Latn-cbr_Latn.jsonl.gz split: test - path: validation/eng_Latn-cbr_Latn.jsonl.gz split: validation - config_name: eng_Latn-jvn_Latn data_files: - path: train/eng_Latn-jvn_Latn.jsonl.gz split: train - path: test/eng_Latn-jvn_Latn.jsonl.gz split: test - path: validation/eng_Latn-jvn_Latn.jsonl.gz split: validation - config_name: eng_Latn-huu_Latn data_files: - path: train/eng_Latn-huu_Latn.jsonl.gz split: train - path: test/eng_Latn-huu_Latn.jsonl.gz split: test - path: validation/eng_Latn-huu_Latn.jsonl.gz split: validation - config_name: eng_Latn-kyq_Latn data_files: - path: train/eng_Latn-kyq_Latn.jsonl.gz split: train - path: test/eng_Latn-kyq_Latn.jsonl.gz split: test - path: validation/eng_Latn-kyq_Latn.jsonl.gz split: validation - config_name: eng_Latn-lex_Latn data_files: - path: train/eng_Latn-lex_Latn.jsonl.gz split: train - path: test/eng_Latn-lex_Latn.jsonl.gz split: test - path: validation/eng_Latn-lex_Latn.jsonl.gz split: validation - config_name: eng_Latn-lug_Latn data_files: - path: train/eng_Latn-lug_Latn.jsonl.gz split: train - path: test/eng_Latn-lug_Latn.jsonl.gz split: test - path: validation/eng_Latn-lug_Latn.jsonl.gz split: validation - config_name: eng_Latn-tbc_Latn data_files: - path: train/eng_Latn-tbc_Latn.jsonl.gz split: train - path: test/eng_Latn-tbc_Latn.jsonl.gz split: test - path: validation/eng_Latn-tbc_Latn.jsonl.gz split: validation - config_name: eng_Latn-srm_Latn data_files: - path: train/eng_Latn-srm_Latn.jsonl.gz split: train - path: test/eng_Latn-srm_Latn.jsonl.gz split: test - path: validation/eng_Latn-srm_Latn.jsonl.gz split: validation - config_name: eng_Latn-ztq_Latn data_files: - path: train/eng_Latn-ztq_Latn.jsonl.gz split: train - path: test/eng_Latn-ztq_Latn.jsonl.gz split: test - path: validation/eng_Latn-ztq_Latn.jsonl.gz split: validation - config_name: eng_Latn-clu_Latn data_files: - path: train/eng_Latn-clu_Latn.jsonl.gz split: train - path: test/eng_Latn-clu_Latn.jsonl.gz split: test - path: validation/eng_Latn-clu_Latn.jsonl.gz split: validation - config_name: eng_Latn-wol_Latn data_files: - path: train/eng_Latn-wol_Latn.jsonl.gz split: train - path: test/eng_Latn-wol_Latn.jsonl.gz split: test - path: validation/eng_Latn-wol_Latn.jsonl.gz split: validation - config_name: eng_Latn-wrk_Latn data_files: - path: train/eng_Latn-wrk_Latn.jsonl.gz split: train - path: test/eng_Latn-wrk_Latn.jsonl.gz split: test - path: validation/eng_Latn-wrk_Latn.jsonl.gz split: validation - config_name: eng_Latn-ssg_Latn data_files: - path: train/eng_Latn-ssg_Latn.jsonl.gz split: train - path: test/eng_Latn-ssg_Latn.jsonl.gz split: test - path: validation/eng_Latn-ssg_Latn.jsonl.gz split: validation - config_name: eng_Latn-tha_Thai data_files: - path: train/eng_Latn-tha_Thai.jsonl.gz split: train - path: test/eng_Latn-tha_Thai.jsonl.gz split: test - path: validation/eng_Latn-tha_Thai.jsonl.gz split: validation - config_name: eng_Latn-gub_Latn data_files: - path: train/eng_Latn-gub_Latn.jsonl.gz split: train - path: test/eng_Latn-gub_Latn.jsonl.gz split: test - path: validation/eng_Latn-gub_Latn.jsonl.gz split: validation - config_name: eng_Latn-rop_Latn data_files: - path: train/eng_Latn-rop_Latn.jsonl.gz split: train - path: test/eng_Latn-rop_Latn.jsonl.gz split: test - path: validation/eng_Latn-rop_Latn.jsonl.gz split: validation - config_name: eng_Latn-ind_Latn data_files: - path: train/eng_Latn-ind_Latn.jsonl.gz split: train - path: test/eng_Latn-ind_Latn.jsonl.gz split: test - path: validation/eng_Latn-ind_Latn.jsonl.gz split: validation - config_name: eng_Latn-urb_Latn data_files: - path: train/eng_Latn-urb_Latn.jsonl.gz split: train - path: test/eng_Latn-urb_Latn.jsonl.gz split: test - path: validation/eng_Latn-urb_Latn.jsonl.gz split: validation - config_name: eng_Latn-ziw_Latn data_files: - path: train/eng_Latn-ziw_Latn.jsonl.gz split: train - path: test/eng_Latn-ziw_Latn.jsonl.gz split: test - path: validation/eng_Latn-ziw_Latn.jsonl.gz split: validation - config_name: eng_Latn-waj_Latn data_files: - path: train/eng_Latn-waj_Latn.jsonl.gz split: train - path: test/eng_Latn-waj_Latn.jsonl.gz split: test - path: validation/eng_Latn-waj_Latn.jsonl.gz split: validation - config_name: eng_Latn-tku_Latn data_files: - path: train/eng_Latn-tku_Latn.jsonl.gz split: train - path: test/eng_Latn-tku_Latn.jsonl.gz split: test - path: validation/eng_Latn-tku_Latn.jsonl.gz split: validation - config_name: eng_Latn-pao_Latn data_files: - path: train/eng_Latn-pao_Latn.jsonl.gz split: train - path: test/eng_Latn-pao_Latn.jsonl.gz split: test - path: validation/eng_Latn-pao_Latn.jsonl.gz split: validation - config_name: eng_Latn-tet_Latn data_files: - path: train/eng_Latn-tet_Latn.jsonl.gz split: train - path: test/eng_Latn-tet_Latn.jsonl.gz split: test - path: validation/eng_Latn-tet_Latn.jsonl.gz split: validation - config_name: eng_Latn-msc_Latn data_files: - path: train/eng_Latn-msc_Latn.jsonl.gz split: train - path: test/eng_Latn-msc_Latn.jsonl.gz split: test - path: validation/eng_Latn-msc_Latn.jsonl.gz split: validation - config_name: eng_Latn-wal_Ethi data_files: - path: train/eng_Latn-wal_Ethi.jsonl.gz split: train - path: test/eng_Latn-wal_Ethi.jsonl.gz split: test - path: validation/eng_Latn-wal_Ethi.jsonl.gz split: validation - config_name: eng_Latn-bmu_Latn data_files: - path: train/eng_Latn-bmu_Latn.jsonl.gz split: train - path: test/eng_Latn-bmu_Latn.jsonl.gz split: test - path: validation/eng_Latn-bmu_Latn.jsonl.gz split: validation - config_name: eng_Latn-yaq_Latn data_files: - path: train/eng_Latn-yaq_Latn.jsonl.gz split: train - path: test/eng_Latn-yaq_Latn.jsonl.gz split: test - path: validation/eng_Latn-yaq_Latn.jsonl.gz split: validation - config_name: eng_Latn-bgt_Latn data_files: - path: train/eng_Latn-bgt_Latn.jsonl.gz split: train - path: test/eng_Latn-bgt_Latn.jsonl.gz split: test - path: validation/eng_Latn-bgt_Latn.jsonl.gz split: validation - config_name: eng_Latn-atb_Latn data_files: - path: train/eng_Latn-atb_Latn.jsonl.gz split: train - path: test/eng_Latn-atb_Latn.jsonl.gz split: test - path: validation/eng_Latn-atb_Latn.jsonl.gz split: validation - config_name: eng_Latn-apn_Latn data_files: - path: train/eng_Latn-apn_Latn.jsonl.gz split: train - path: test/eng_Latn-apn_Latn.jsonl.gz split: test - path: validation/eng_Latn-apn_Latn.jsonl.gz split: validation - config_name: eng_Latn-por_Latn data_files: - path: train/eng_Latn-por_Latn.jsonl.gz split: train - path: test/eng_Latn-por_Latn.jsonl.gz split: test - path: validation/eng_Latn-por_Latn.jsonl.gz split: validation - config_name: eng_Latn-quf_Latn data_files: - path: train/eng_Latn-quf_Latn.jsonl.gz split: train - path: test/eng_Latn-quf_Latn.jsonl.gz split: test - path: validation/eng_Latn-quf_Latn.jsonl.gz split: validation - config_name: eng_Latn-prf_Latn data_files: - path: train/eng_Latn-prf_Latn.jsonl.gz split: train - path: test/eng_Latn-prf_Latn.jsonl.gz split: test - path: validation/eng_Latn-prf_Latn.jsonl.gz split: validation - config_name: eng_Latn-ndj_Latn data_files: - path: train/eng_Latn-ndj_Latn.jsonl.gz split: train - path: test/eng_Latn-ndj_Latn.jsonl.gz split: test - path: validation/eng_Latn-ndj_Latn.jsonl.gz split: validation - config_name: eng_Latn-hub_Latn data_files: - path: train/eng_Latn-hub_Latn.jsonl.gz split: train - path: test/eng_Latn-hub_Latn.jsonl.gz split: test - path: validation/eng_Latn-hub_Latn.jsonl.gz split: validation - config_name: eng_Latn-kvn_Latn data_files: - path: train/eng_Latn-kvn_Latn.jsonl.gz split: train - path: test/eng_Latn-kvn_Latn.jsonl.gz split: test - path: validation/eng_Latn-kvn_Latn.jsonl.gz split: validation - config_name: eng_Latn-swe_Latn data_files: - path: train/eng_Latn-swe_Latn.jsonl.gz split: train - path: test/eng_Latn-swe_Latn.jsonl.gz split: test - path: validation/eng_Latn-swe_Latn.jsonl.gz split: validation - config_name: eng_Latn-xtd_Latn data_files: - path: train/eng_Latn-xtd_Latn.jsonl.gz split: train - path: test/eng_Latn-xtd_Latn.jsonl.gz split: test - path: validation/eng_Latn-xtd_Latn.jsonl.gz split: validation - config_name: eng_Latn-blz_Latn data_files: - path: train/eng_Latn-blz_Latn.jsonl.gz split: train - path: test/eng_Latn-blz_Latn.jsonl.gz split: test - path: validation/eng_Latn-blz_Latn.jsonl.gz split: validation - config_name: eng_Latn-arb_Arab data_files: - path: train/eng_Latn-arb_Arab.jsonl.gz split: train - path: test/eng_Latn-arb_Arab.jsonl.gz split: test - path: validation/eng_Latn-arb_Arab.jsonl.gz split: validation - config_name: eng_Latn-gdr_Latn data_files: - path: train/eng_Latn-gdr_Latn.jsonl.gz split: train - path: test/eng_Latn-gdr_Latn.jsonl.gz split: test - path: validation/eng_Latn-gdr_Latn.jsonl.gz split: validation - config_name: eng_Latn-ksd_Latn data_files: - path: train/eng_Latn-ksd_Latn.jsonl.gz split: train - path: test/eng_Latn-ksd_Latn.jsonl.gz split: test - path: validation/eng_Latn-ksd_Latn.jsonl.gz split: validation - config_name: eng_Latn-toj_Latn data_files: - path: train/eng_Latn-toj_Latn.jsonl.gz split: train - path: test/eng_Latn-toj_Latn.jsonl.gz split: test - path: validation/eng_Latn-toj_Latn.jsonl.gz split: validation - config_name: eng_Latn-arp_Latn data_files: - path: train/eng_Latn-arp_Latn.jsonl.gz split: train - path: test/eng_Latn-arp_Latn.jsonl.gz split: test - path: validation/eng_Latn-arp_Latn.jsonl.gz split: validation - config_name: eng_Latn-cnt_Latn data_files: - path: train/eng_Latn-cnt_Latn.jsonl.gz split: train - path: test/eng_Latn-cnt_Latn.jsonl.gz split: test - path: validation/eng_Latn-cnt_Latn.jsonl.gz split: validation - config_name: eng_Latn-aoj_Latn data_files: - path: train/eng_Latn-aoj_Latn.jsonl.gz split: train - path: test/eng_Latn-aoj_Latn.jsonl.gz split: test - path: validation/eng_Latn-aoj_Latn.jsonl.gz split: validation - config_name: eng_Latn-fai_Latn data_files: - path: train/eng_Latn-fai_Latn.jsonl.gz split: train - path: test/eng_Latn-fai_Latn.jsonl.gz split: test - path: validation/eng_Latn-fai_Latn.jsonl.gz split: validation - config_name: eng_Latn-far_Latn data_files: - path: train/eng_Latn-far_Latn.jsonl.gz split: train - path: test/eng_Latn-far_Latn.jsonl.gz split: test - path: validation/eng_Latn-far_Latn.jsonl.gz split: validation - config_name: eng_Latn-ons_Latn data_files: - path: train/eng_Latn-ons_Latn.jsonl.gz split: train - path: test/eng_Latn-ons_Latn.jsonl.gz split: test - path: validation/eng_Latn-ons_Latn.jsonl.gz split: validation - config_name: eng_Latn-emi_Latn data_files: - path: train/eng_Latn-emi_Latn.jsonl.gz split: train - path: test/eng_Latn-emi_Latn.jsonl.gz split: test - path: validation/eng_Latn-emi_Latn.jsonl.gz split: validation - config_name: eng_Latn-yre_Latn data_files: - path: train/eng_Latn-yre_Latn.jsonl.gz split: train - path: test/eng_Latn-yre_Latn.jsonl.gz split: test - path: validation/eng_Latn-yre_Latn.jsonl.gz split: validation - config_name: eng_Latn-zpz_Latn data_files: - path: train/eng_Latn-zpz_Latn.jsonl.gz split: train - path: test/eng_Latn-zpz_Latn.jsonl.gz split: test - path: validation/eng_Latn-zpz_Latn.jsonl.gz split: validation - config_name: eng_Latn-yss_Latn data_files: - path: train/eng_Latn-yss_Latn.jsonl.gz split: train - path: test/eng_Latn-yss_Latn.jsonl.gz split: test - path: validation/eng_Latn-yss_Latn.jsonl.gz split: validation - config_name: eng_Latn-kos_Latn data_files: - path: train/eng_Latn-kos_Latn.jsonl.gz split: train - path: test/eng_Latn-kos_Latn.jsonl.gz split: test - path: validation/eng_Latn-kos_Latn.jsonl.gz split: validation - config_name: eng_Latn-reg_Latn data_files: - path: train/eng_Latn-reg_Latn.jsonl.gz split: train - path: test/eng_Latn-reg_Latn.jsonl.gz split: test - path: validation/eng_Latn-reg_Latn.jsonl.gz split: validation - config_name: eng_Latn-rro_Latn data_files: - path: train/eng_Latn-rro_Latn.jsonl.gz split: train - path: test/eng_Latn-rro_Latn.jsonl.gz split: test - path: validation/eng_Latn-rro_Latn.jsonl.gz split: validation - config_name: eng_Latn-apz_Latn data_files: - path: train/eng_Latn-apz_Latn.jsonl.gz split: train - path: test/eng_Latn-apz_Latn.jsonl.gz split: test - path: validation/eng_Latn-apz_Latn.jsonl.gz split: validation - config_name: eng_Latn-boj_Latn data_files: - path: train/eng_Latn-boj_Latn.jsonl.gz split: train - path: test/eng_Latn-boj_Latn.jsonl.gz split: test - path: validation/eng_Latn-boj_Latn.jsonl.gz split: validation - config_name: eng_Latn-hla_Latn data_files: - path: train/eng_Latn-hla_Latn.jsonl.gz split: train - path: test/eng_Latn-hla_Latn.jsonl.gz split: test - path: validation/eng_Latn-hla_Latn.jsonl.gz split: validation - config_name: eng_Latn-gyr_Latn data_files: - path: train/eng_Latn-gyr_Latn.jsonl.gz split: train - path: test/eng_Latn-gyr_Latn.jsonl.gz split: test - path: validation/eng_Latn-gyr_Latn.jsonl.gz split: validation - config_name: eng_Latn-ukr_Cyrl data_files: - path: train/eng_Latn-ukr_Cyrl.jsonl.gz split: train - path: test/eng_Latn-ukr_Cyrl.jsonl.gz split: test - path: validation/eng_Latn-ukr_Cyrl.jsonl.gz split: validation - config_name: eng_Latn-gvs_Latn data_files: - path: train/eng_Latn-gvs_Latn.jsonl.gz split: train - path: test/eng_Latn-gvs_Latn.jsonl.gz split: test - path: validation/eng_Latn-gvs_Latn.jsonl.gz split: validation - config_name: eng_Latn-mil_Latn data_files: - path: train/eng_Latn-mil_Latn.jsonl.gz split: train - path: test/eng_Latn-mil_Latn.jsonl.gz split: test - path: validation/eng_Latn-mil_Latn.jsonl.gz split: validation - config_name: eng_Latn-gul_Latn data_files: - path: train/eng_Latn-gul_Latn.jsonl.gz split: train - path: test/eng_Latn-gul_Latn.jsonl.gz split: test - path: validation/eng_Latn-gul_Latn.jsonl.gz split: validation - config_name: eng_Latn-ood_Latn data_files: - path: train/eng_Latn-ood_Latn.jsonl.gz split: train - path: test/eng_Latn-ood_Latn.jsonl.gz split: test - path: validation/eng_Latn-ood_Latn.jsonl.gz split: validation - config_name: eng_Latn-ewe_Latn data_files: - path: train/eng_Latn-ewe_Latn.jsonl.gz split: train - path: test/eng_Latn-ewe_Latn.jsonl.gz split: test - path: validation/eng_Latn-ewe_Latn.jsonl.gz split: validation - config_name: eng_Latn-qul_Latn data_files: - path: train/eng_Latn-qul_Latn.jsonl.gz split: train - path: test/eng_Latn-qul_Latn.jsonl.gz split: test - path: validation/eng_Latn-qul_Latn.jsonl.gz split: validation - config_name: eng_Latn-kbm_Latn data_files: - path: train/eng_Latn-kbm_Latn.jsonl.gz split: train - path: test/eng_Latn-kbm_Latn.jsonl.gz split: test - path: validation/eng_Latn-kbm_Latn.jsonl.gz split: validation - config_name: eng_Latn-mih_Latn data_files: - path: train/eng_Latn-mih_Latn.jsonl.gz split: train - path: test/eng_Latn-mih_Latn.jsonl.gz split: test - path: validation/eng_Latn-mih_Latn.jsonl.gz split: validation - config_name: eng_Latn-maq_Latn data_files: - path: train/eng_Latn-maq_Latn.jsonl.gz split: train - path: test/eng_Latn-maq_Latn.jsonl.gz split: test - path: validation/eng_Latn-maq_Latn.jsonl.gz split: validation - config_name: eng_Latn-bbr_Latn data_files: - path: train/eng_Latn-bbr_Latn.jsonl.gz split: train - path: test/eng_Latn-bbr_Latn.jsonl.gz split: test - path: validation/eng_Latn-bbr_Latn.jsonl.gz split: validation - config_name: eng_Latn-cbu_Latn data_files: - path: train/eng_Latn-cbu_Latn.jsonl.gz split: train - path: test/eng_Latn-cbu_Latn.jsonl.gz split: test - path: validation/eng_Latn-cbu_Latn.jsonl.gz split: validation - config_name: eng_Latn-meq_Latn data_files: - path: train/eng_Latn-meq_Latn.jsonl.gz split: train - path: test/eng_Latn-meq_Latn.jsonl.gz split: test - path: validation/eng_Latn-meq_Latn.jsonl.gz split: validation - config_name: eng_Latn-bmk_Latn data_files: - path: train/eng_Latn-bmk_Latn.jsonl.gz split: train - path: test/eng_Latn-bmk_Latn.jsonl.gz split: test - path: validation/eng_Latn-bmk_Latn.jsonl.gz split: validation - config_name: eng_Latn-hui_Latn data_files: - path: train/eng_Latn-hui_Latn.jsonl.gz split: train - path: test/eng_Latn-hui_Latn.jsonl.gz split: test - path: validation/eng_Latn-hui_Latn.jsonl.gz split: validation - config_name: eng_Latn-tgl_Latn data_files: - path: train/eng_Latn-tgl_Latn.jsonl.gz split: train - path: test/eng_Latn-tgl_Latn.jsonl.gz split: test - path: validation/eng_Latn-tgl_Latn.jsonl.gz split: validation - config_name: eng_Latn-lgl_Latn data_files: - path: train/eng_Latn-lgl_Latn.jsonl.gz split: train - path: test/eng_Latn-lgl_Latn.jsonl.gz split: test - path: validation/eng_Latn-lgl_Latn.jsonl.gz split: validation - config_name: eng_Latn-zpq_Latn data_files: - path: train/eng_Latn-zpq_Latn.jsonl.gz split: train - path: test/eng_Latn-zpq_Latn.jsonl.gz split: test - path: validation/eng_Latn-zpq_Latn.jsonl.gz split: validation - config_name: eng_Latn-mti_Latn data_files: - path: train/eng_Latn-mti_Latn.jsonl.gz split: train - path: test/eng_Latn-mti_Latn.jsonl.gz split: test - path: validation/eng_Latn-mti_Latn.jsonl.gz split: validation - config_name: eng_Latn-pah_Latn data_files: - path: train/eng_Latn-pah_Latn.jsonl.gz split: train - path: test/eng_Latn-pah_Latn.jsonl.gz split: test - path: validation/eng_Latn-pah_Latn.jsonl.gz split: validation - config_name: eng_Latn-nch_Latn data_files: - path: train/eng_Latn-nch_Latn.jsonl.gz split: train - path: test/eng_Latn-nch_Latn.jsonl.gz split: test - path: validation/eng_Latn-nch_Latn.jsonl.gz split: validation - config_name: eng_Latn-mjc_Latn data_files: - path: train/eng_Latn-mjc_Latn.jsonl.gz split: train - path: test/eng_Latn-mjc_Latn.jsonl.gz split: test - path: validation/eng_Latn-mjc_Latn.jsonl.gz split: validation - config_name: eng_Latn-zty_Latn data_files: - path: train/eng_Latn-zty_Latn.jsonl.gz split: train - path: test/eng_Latn-zty_Latn.jsonl.gz split: test - path: validation/eng_Latn-zty_Latn.jsonl.gz split: validation - config_name: eng_Latn-ksj_Latn data_files: - path: train/eng_Latn-ksj_Latn.jsonl.gz split: train - path: test/eng_Latn-ksj_Latn.jsonl.gz split: test - path: validation/eng_Latn-ksj_Latn.jsonl.gz split: validation - config_name: eng_Latn-nvm_Latn data_files: - path: train/eng_Latn-nvm_Latn.jsonl.gz split: train - path: test/eng_Latn-nvm_Latn.jsonl.gz split: test - path: validation/eng_Latn-nvm_Latn.jsonl.gz split: validation - config_name: eng_Latn-kyc_Latn data_files: - path: train/eng_Latn-kyc_Latn.jsonl.gz split: train - path: test/eng_Latn-kyc_Latn.jsonl.gz split: test - path: validation/eng_Latn-kyc_Latn.jsonl.gz split: validation - config_name: eng_Latn-bao_Latn data_files: - path: train/eng_Latn-bao_Latn.jsonl.gz split: train - path: test/eng_Latn-bao_Latn.jsonl.gz split: test - path: validation/eng_Latn-bao_Latn.jsonl.gz split: validation - config_name: eng_Latn-zas_Latn data_files: - path: train/eng_Latn-zas_Latn.jsonl.gz split: train - path: test/eng_Latn-zas_Latn.jsonl.gz split: test - path: validation/eng_Latn-zas_Latn.jsonl.gz split: validation - config_name: eng_Latn-djr_Latn data_files: - path: train/eng_Latn-djr_Latn.jsonl.gz split: train - path: test/eng_Latn-djr_Latn.jsonl.gz split: test - path: validation/eng_Latn-djr_Latn.jsonl.gz split: validation - config_name: eng_Latn-bpr_Latn data_files: - path: train/eng_Latn-bpr_Latn.jsonl.gz split: train - path: test/eng_Latn-bpr_Latn.jsonl.gz split: test - path: validation/eng_Latn-bpr_Latn.jsonl.gz split: validation - config_name: eng_Latn-ndg_Latn data_files: - path: train/eng_Latn-ndg_Latn.jsonl.gz split: train - path: test/eng_Latn-ndg_Latn.jsonl.gz split: test - path: validation/eng_Latn-ndg_Latn.jsonl.gz split: validation - config_name: eng_Latn-ots_Latn data_files: - path: train/eng_Latn-ots_Latn.jsonl.gz split: train - path: test/eng_Latn-ots_Latn.jsonl.gz split: test - path: validation/eng_Latn-ots_Latn.jsonl.gz split: validation - config_name: eng_Latn-miz_Latn data_files: - path: train/eng_Latn-miz_Latn.jsonl.gz split: train - path: test/eng_Latn-miz_Latn.jsonl.gz split: test - path: validation/eng_Latn-miz_Latn.jsonl.gz split: validation - config_name: eng_Latn-cco_Latn data_files: - path: train/eng_Latn-cco_Latn.jsonl.gz split: train - path: test/eng_Latn-cco_Latn.jsonl.gz split: test - path: validation/eng_Latn-cco_Latn.jsonl.gz split: validation - config_name: eng_Latn-mbc_Latn data_files: - path: train/eng_Latn-mbc_Latn.jsonl.gz split: train - path: test/eng_Latn-mbc_Latn.jsonl.gz split: test - path: validation/eng_Latn-mbc_Latn.jsonl.gz split: validation - config_name: eng_Latn-myy_Latn data_files: - path: train/eng_Latn-myy_Latn.jsonl.gz split: train - path: test/eng_Latn-myy_Latn.jsonl.gz split: test - path: validation/eng_Latn-myy_Latn.jsonl.gz split: validation - config_name: eng_Latn-att_Latn data_files: - path: train/eng_Latn-att_Latn.jsonl.gz split: train - path: test/eng_Latn-att_Latn.jsonl.gz split: test - path: validation/eng_Latn-att_Latn.jsonl.gz split: validation - config_name: eng_Latn-aly_Latn data_files: - path: train/eng_Latn-aly_Latn.jsonl.gz split: train - path: test/eng_Latn-aly_Latn.jsonl.gz split: test - path: validation/eng_Latn-aly_Latn.jsonl.gz split: validation - config_name: eng_Latn-mgh_Latn data_files: - path: train/eng_Latn-mgh_Latn.jsonl.gz split: train - path: test/eng_Latn-mgh_Latn.jsonl.gz split: test - path: validation/eng_Latn-mgh_Latn.jsonl.gz split: validation - config_name: eng_Latn-mqb_Latn data_files: - path: train/eng_Latn-mqb_Latn.jsonl.gz split: train - path: test/eng_Latn-mqb_Latn.jsonl.gz split: test - path: validation/eng_Latn-mqb_Latn.jsonl.gz split: validation - config_name: eng_Latn-sps_Latn data_files: - path: train/eng_Latn-sps_Latn.jsonl.gz split: train - path: test/eng_Latn-sps_Latn.jsonl.gz split: test - path: validation/eng_Latn-sps_Latn.jsonl.gz split: validation - config_name: eng_Latn-wbi_Latn data_files: - path: train/eng_Latn-wbi_Latn.jsonl.gz split: train - path: test/eng_Latn-wbi_Latn.jsonl.gz split: test - path: validation/eng_Latn-wbi_Latn.jsonl.gz split: validation - config_name: eng_Latn-rai_Latn data_files: - path: train/eng_Latn-rai_Latn.jsonl.gz split: train - path: test/eng_Latn-rai_Latn.jsonl.gz split: test - path: validation/eng_Latn-rai_Latn.jsonl.gz split: validation - config_name: eng_Latn-knf_Latn data_files: - path: train/eng_Latn-knf_Latn.jsonl.gz split: train - path: test/eng_Latn-knf_Latn.jsonl.gz split: test - path: validation/eng_Latn-knf_Latn.jsonl.gz split: validation - config_name: eng_Latn-txq_Latn data_files: - path: train/eng_Latn-txq_Latn.jsonl.gz split: train - path: test/eng_Latn-txq_Latn.jsonl.gz split: test - path: validation/eng_Latn-txq_Latn.jsonl.gz split: validation - config_name: eng_Latn-cuk_Latn data_files: - path: train/eng_Latn-cuk_Latn.jsonl.gz split: train - path: test/eng_Latn-cuk_Latn.jsonl.gz split: test - path: validation/eng_Latn-cuk_Latn.jsonl.gz split: validation - config_name: eng_Latn-tew_Latn data_files: - path: train/eng_Latn-tew_Latn.jsonl.gz split: train - path: test/eng_Latn-tew_Latn.jsonl.gz split: test - path: validation/eng_Latn-tew_Latn.jsonl.gz split: validation - config_name: eng_Latn-aia_Latn data_files: - path: train/eng_Latn-aia_Latn.jsonl.gz split: train - path: test/eng_Latn-aia_Latn.jsonl.gz split: test - path: validation/eng_Latn-aia_Latn.jsonl.gz split: validation - config_name: eng_Latn-ghs_Latn data_files: - path: train/eng_Latn-ghs_Latn.jsonl.gz split: train - path: test/eng_Latn-ghs_Latn.jsonl.gz split: test - path: validation/eng_Latn-ghs_Latn.jsonl.gz split: validation - config_name: eng_Latn-kne_Latn data_files: - path: train/eng_Latn-kne_Latn.jsonl.gz split: train - path: test/eng_Latn-kne_Latn.jsonl.gz split: test - path: validation/eng_Latn-kne_Latn.jsonl.gz split: validation - config_name: eng_Latn-snp_Latn data_files: - path: train/eng_Latn-snp_Latn.jsonl.gz split: train - path: test/eng_Latn-snp_Latn.jsonl.gz split: test - path: validation/eng_Latn-snp_Latn.jsonl.gz split: validation - config_name: eng_Latn-yon_Latn data_files: - path: train/eng_Latn-yon_Latn.jsonl.gz split: train - path: test/eng_Latn-yon_Latn.jsonl.gz split: test - path: validation/eng_Latn-yon_Latn.jsonl.gz split: validation - config_name: eng_Latn-rkb_Latn data_files: - path: train/eng_Latn-rkb_Latn.jsonl.gz split: train - path: test/eng_Latn-rkb_Latn.jsonl.gz split: test - path: validation/eng_Latn-rkb_Latn.jsonl.gz split: validation - config_name: eng_Latn-mam_Latn data_files: - path: train/eng_Latn-mam_Latn.jsonl.gz split: train - path: test/eng_Latn-mam_Latn.jsonl.gz split: test - path: validation/eng_Latn-mam_Latn.jsonl.gz split: validation - config_name: eng_Latn-ffm_Latn data_files: - path: train/eng_Latn-ffm_Latn.jsonl.gz split: train - path: test/eng_Latn-ffm_Latn.jsonl.gz split: test - path: validation/eng_Latn-ffm_Latn.jsonl.gz split: validation - config_name: eng_Latn-tbo_Latn data_files: - path: train/eng_Latn-tbo_Latn.jsonl.gz split: train - path: test/eng_Latn-tbo_Latn.jsonl.gz split: test - path: validation/eng_Latn-tbo_Latn.jsonl.gz split: validation - config_name: eng_Latn-cta_Latn data_files: - path: train/eng_Latn-cta_Latn.jsonl.gz split: train - path: test/eng_Latn-cta_Latn.jsonl.gz split: test - path: validation/eng_Latn-cta_Latn.jsonl.gz split: validation - config_name: eng_Latn-mca_Latn data_files: - path: train/eng_Latn-mca_Latn.jsonl.gz split: train - path: test/eng_Latn-mca_Latn.jsonl.gz split: test - path: validation/eng_Latn-mca_Latn.jsonl.gz split: validation - config_name: eng_Latn-smk_Latn data_files: - path: train/eng_Latn-smk_Latn.jsonl.gz split: train - path: test/eng_Latn-smk_Latn.jsonl.gz split: test - path: validation/eng_Latn-smk_Latn.jsonl.gz split: validation - config_name: eng_Latn-bqc_Latn data_files: - path: train/eng_Latn-bqc_Latn.jsonl.gz split: train - path: test/eng_Latn-bqc_Latn.jsonl.gz split: test - path: validation/eng_Latn-bqc_Latn.jsonl.gz split: validation - config_name: eng_Latn-khz_Latn data_files: - path: train/eng_Latn-khz_Latn.jsonl.gz split: train - path: test/eng_Latn-khz_Latn.jsonl.gz split: test - path: validation/eng_Latn-khz_Latn.jsonl.gz split: validation - config_name: eng_Latn-ceb_Latn data_files: - path: train/eng_Latn-ceb_Latn.jsonl.gz split: train - path: test/eng_Latn-ceb_Latn.jsonl.gz split: test - path: validation/eng_Latn-ceb_Latn.jsonl.gz split: validation - config_name: eng_Latn-nyu_Latn data_files: - path: train/eng_Latn-nyu_Latn.jsonl.gz split: train - path: test/eng_Latn-nyu_Latn.jsonl.gz split: test - path: validation/eng_Latn-nyu_Latn.jsonl.gz split: validation - config_name: eng_Latn-hlt_Latn data_files: - path: train/eng_Latn-hlt_Latn.jsonl.gz split: train - path: test/eng_Latn-hlt_Latn.jsonl.gz split: test - path: validation/eng_Latn-hlt_Latn.jsonl.gz split: validation - config_name: eng_Latn-qvw_Latn data_files: - path: train/eng_Latn-qvw_Latn.jsonl.gz split: train - path: test/eng_Latn-qvw_Latn.jsonl.gz split: test - path: validation/eng_Latn-qvw_Latn.jsonl.gz split: validation - config_name: eng_Latn-poy_Latn data_files: - path: train/eng_Latn-poy_Latn.jsonl.gz split: train - path: test/eng_Latn-poy_Latn.jsonl.gz split: test - path: validation/eng_Latn-poy_Latn.jsonl.gz split: validation - config_name: eng_Latn-jiv_Latn data_files: - path: train/eng_Latn-jiv_Latn.jsonl.gz split: train - path: test/eng_Latn-jiv_Latn.jsonl.gz split: test - path: validation/eng_Latn-jiv_Latn.jsonl.gz split: validation - config_name: eng_Latn-mna_Latn data_files: - path: train/eng_Latn-mna_Latn.jsonl.gz split: train - path: test/eng_Latn-mna_Latn.jsonl.gz split: test - path: validation/eng_Latn-mna_Latn.jsonl.gz split: validation - config_name: eng_Latn-xsi_Latn data_files: - path: train/eng_Latn-xsi_Latn.jsonl.gz split: train - path: test/eng_Latn-xsi_Latn.jsonl.gz split: test - path: validation/eng_Latn-xsi_Latn.jsonl.gz split: validation - config_name: eng_Latn-crx_Latn data_files: - path: train/eng_Latn-crx_Latn.jsonl.gz split: train - path: test/eng_Latn-crx_Latn.jsonl.gz split: test - path: validation/eng_Latn-crx_Latn.jsonl.gz split: validation - config_name: eng_Latn-apb_Latn data_files: - path: train/eng_Latn-apb_Latn.jsonl.gz split: train - path: test/eng_Latn-apb_Latn.jsonl.gz split: test - path: validation/eng_Latn-apb_Latn.jsonl.gz split: validation - config_name: eng_Latn-imo_Latn data_files: - path: train/eng_Latn-imo_Latn.jsonl.gz split: train - path: test/eng_Latn-imo_Latn.jsonl.gz split: test - path: validation/eng_Latn-imo_Latn.jsonl.gz split: validation - config_name: eng_Latn-fue_Latn data_files: - path: train/eng_Latn-fue_Latn.jsonl.gz split: train - path: test/eng_Latn-fue_Latn.jsonl.gz split: test - path: validation/eng_Latn-fue_Latn.jsonl.gz split: validation - config_name: eng_Latn-bhl_Latn data_files: - path: train/eng_Latn-bhl_Latn.jsonl.gz split: train - path: test/eng_Latn-bhl_Latn.jsonl.gz split: test - path: validation/eng_Latn-bhl_Latn.jsonl.gz split: validation - config_name: eng_Latn-tim_Latn data_files: - path: train/eng_Latn-tim_Latn.jsonl.gz split: train - path: test/eng_Latn-tim_Latn.jsonl.gz split: test - path: validation/eng_Latn-tim_Latn.jsonl.gz split: validation - config_name: eng_Latn-mgw_Latn data_files: - path: train/eng_Latn-mgw_Latn.jsonl.gz split: train - path: test/eng_Latn-mgw_Latn.jsonl.gz split: test - path: validation/eng_Latn-mgw_Latn.jsonl.gz split: validation - config_name: eng_Latn-taj_Deva data_files: - path: train/eng_Latn-taj_Deva.jsonl.gz split: train - path: test/eng_Latn-taj_Deva.jsonl.gz split: test - path: validation/eng_Latn-taj_Deva.jsonl.gz split: validation - config_name: eng_Latn-djk_Latn data_files: - path: train/eng_Latn-djk_Latn.jsonl.gz split: train - path: test/eng_Latn-djk_Latn.jsonl.gz split: test - path: validation/eng_Latn-djk_Latn.jsonl.gz split: validation - config_name: eng_Latn-ruf_Latn data_files: - path: train/eng_Latn-ruf_Latn.jsonl.gz split: train - path: test/eng_Latn-ruf_Latn.jsonl.gz split: test - path: validation/eng_Latn-ruf_Latn.jsonl.gz split: validation - config_name: eng_Latn-bqp_Latn data_files: - path: train/eng_Latn-bqp_Latn.jsonl.gz split: train - path: test/eng_Latn-bqp_Latn.jsonl.gz split: test - path: validation/eng_Latn-bqp_Latn.jsonl.gz split: validation - config_name: eng_Latn-adz_Latn data_files: - path: train/eng_Latn-adz_Latn.jsonl.gz split: train - path: test/eng_Latn-adz_Latn.jsonl.gz split: test - path: validation/eng_Latn-adz_Latn.jsonl.gz split: validation - config_name: eng_Latn-bmr_Latn data_files: - path: train/eng_Latn-bmr_Latn.jsonl.gz split: train - path: test/eng_Latn-bmr_Latn.jsonl.gz split: test - path: validation/eng_Latn-bmr_Latn.jsonl.gz split: validation - config_name: eng_Latn-ata_Latn data_files: - path: train/eng_Latn-ata_Latn.jsonl.gz split: train - path: test/eng_Latn-ata_Latn.jsonl.gz split: test - path: validation/eng_Latn-ata_Latn.jsonl.gz split: validation - config_name: eng_Latn-mio_Latn data_files: - path: train/eng_Latn-mio_Latn.jsonl.gz split: train - path: test/eng_Latn-mio_Latn.jsonl.gz split: test - path: validation/eng_Latn-mio_Latn.jsonl.gz split: validation - config_name: eng_Latn-pad_Latn data_files: - path: train/eng_Latn-pad_Latn.jsonl.gz split: train - path: test/eng_Latn-pad_Latn.jsonl.gz split: test - path: validation/eng_Latn-pad_Latn.jsonl.gz split: validation - config_name: eng_Latn-qxh_Latn data_files: - path: train/eng_Latn-qxh_Latn.jsonl.gz split: train - path: test/eng_Latn-qxh_Latn.jsonl.gz split: test - path: validation/eng_Latn-qxh_Latn.jsonl.gz split: validation - config_name: eng_Latn-tfr_Latn data_files: - path: train/eng_Latn-tfr_Latn.jsonl.gz split: train - path: test/eng_Latn-tfr_Latn.jsonl.gz split: test - path: validation/eng_Latn-tfr_Latn.jsonl.gz split: validation - config_name: eng_Latn-mie_Latn data_files: - path: train/eng_Latn-mie_Latn.jsonl.gz split: train - path: test/eng_Latn-mie_Latn.jsonl.gz split: test - path: validation/eng_Latn-mie_Latn.jsonl.gz split: validation - config_name: eng_Latn-tpi_Latn data_files: - path: train/eng_Latn-tpi_Latn.jsonl.gz split: train - path: test/eng_Latn-tpi_Latn.jsonl.gz split: test - path: validation/eng_Latn-tpi_Latn.jsonl.gz split: validation - config_name: eng_Latn-fuh_Latn data_files: - path: train/eng_Latn-fuh_Latn.jsonl.gz split: train - path: test/eng_Latn-fuh_Latn.jsonl.gz split: test - path: validation/eng_Latn-fuh_Latn.jsonl.gz split: validation - config_name: eng_Latn-dgr_Latn data_files: - path: train/eng_Latn-dgr_Latn.jsonl.gz split: train - path: test/eng_Latn-dgr_Latn.jsonl.gz split: test - path: validation/eng_Latn-dgr_Latn.jsonl.gz split: validation - config_name: eng_Latn-bch_Latn data_files: - path: train/eng_Latn-bch_Latn.jsonl.gz split: train - path: test/eng_Latn-bch_Latn.jsonl.gz split: test - path: validation/eng_Latn-bch_Latn.jsonl.gz split: validation - config_name: eng_Latn-mcr_Latn data_files: - path: train/eng_Latn-mcr_Latn.jsonl.gz split: train - path: test/eng_Latn-mcr_Latn.jsonl.gz split: test - path: validation/eng_Latn-mcr_Latn.jsonl.gz split: validation - config_name: eng_Latn-bkx_Latn data_files: - path: train/eng_Latn-bkx_Latn.jsonl.gz split: train - path: test/eng_Latn-bkx_Latn.jsonl.gz split: test - path: validation/eng_Latn-bkx_Latn.jsonl.gz split: validation - config_name: eng_Latn-agr_Latn data_files: - path: train/eng_Latn-agr_Latn.jsonl.gz split: train - path: test/eng_Latn-agr_Latn.jsonl.gz split: test - path: validation/eng_Latn-agr_Latn.jsonl.gz split: validation - config_name: eng_Latn-chq_Latn data_files: - path: train/eng_Latn-chq_Latn.jsonl.gz split: train - path: test/eng_Latn-chq_Latn.jsonl.gz split: test - path: validation/eng_Latn-chq_Latn.jsonl.gz split: validation - config_name: eng_Latn-rwo_Latn data_files: - path: train/eng_Latn-rwo_Latn.jsonl.gz split: train - path: test/eng_Latn-rwo_Latn.jsonl.gz split: test - path: validation/eng_Latn-rwo_Latn.jsonl.gz split: validation - config_name: eng_Latn-esk_Latn data_files: - path: train/eng_Latn-esk_Latn.jsonl.gz split: train - path: test/eng_Latn-esk_Latn.jsonl.gz split: test - path: validation/eng_Latn-esk_Latn.jsonl.gz split: validation - config_name: eng_Latn-zpl_Latn data_files: - path: train/eng_Latn-zpl_Latn.jsonl.gz split: train - path: test/eng_Latn-zpl_Latn.jsonl.gz split: test - path: validation/eng_Latn-zpl_Latn.jsonl.gz split: validation - config_name: eng_Latn-bjr_Latn data_files: - path: train/eng_Latn-bjr_Latn.jsonl.gz split: train - path: test/eng_Latn-bjr_Latn.jsonl.gz split: test - path: validation/eng_Latn-bjr_Latn.jsonl.gz split: validation - config_name: eng_Latn-kiw_Latn data_files: - path: train/eng_Latn-kiw_Latn.jsonl.gz split: train - path: test/eng_Latn-kiw_Latn.jsonl.gz split: test - path: validation/eng_Latn-kiw_Latn.jsonl.gz split: validation - config_name: eng_Latn-azg_Latn data_files: - path: train/eng_Latn-azg_Latn.jsonl.gz split: train - path: test/eng_Latn-azg_Latn.jsonl.gz split: test - path: validation/eng_Latn-azg_Latn.jsonl.gz split: validation - config_name: eng_Latn-mbb_Latn data_files: - path: train/eng_Latn-mbb_Latn.jsonl.gz split: train - path: test/eng_Latn-mbb_Latn.jsonl.gz split: test - path: validation/eng_Latn-mbb_Latn.jsonl.gz split: validation - config_name: eng_Latn-knj_Latn data_files: - path: train/eng_Latn-knj_Latn.jsonl.gz split: train - path: test/eng_Latn-knj_Latn.jsonl.gz split: test - path: validation/eng_Latn-knj_Latn.jsonl.gz split: validation - config_name: eng_Latn-cao_Latn data_files: - path: train/eng_Latn-cao_Latn.jsonl.gz split: train - path: test/eng_Latn-cao_Latn.jsonl.gz split: test - path: validation/eng_Latn-cao_Latn.jsonl.gz split: validation - config_name: eng_Latn-dji_Latn data_files: - path: train/eng_Latn-dji_Latn.jsonl.gz split: train - path: test/eng_Latn-dji_Latn.jsonl.gz split: test - path: validation/eng_Latn-dji_Latn.jsonl.gz split: validation - config_name: eng_Latn-bss_Latn data_files: - path: train/eng_Latn-bss_Latn.jsonl.gz split: train - path: test/eng_Latn-bss_Latn.jsonl.gz split: test - path: validation/eng_Latn-bss_Latn.jsonl.gz split: validation - config_name: eng_Latn-bgs_Latn data_files: - path: train/eng_Latn-bgs_Latn.jsonl.gz split: train - path: test/eng_Latn-bgs_Latn.jsonl.gz split: test - path: validation/eng_Latn-bgs_Latn.jsonl.gz split: validation - config_name: eng_Latn-mek_Latn data_files: - path: train/eng_Latn-mek_Latn.jsonl.gz split: train - path: test/eng_Latn-mek_Latn.jsonl.gz split: test - path: validation/eng_Latn-mek_Latn.jsonl.gz split: validation - config_name: eng_Latn-yuj_Latn data_files: - path: train/eng_Latn-yuj_Latn.jsonl.gz split: train - path: test/eng_Latn-yuj_Latn.jsonl.gz split: test - path: validation/eng_Latn-yuj_Latn.jsonl.gz split: validation - config_name: eng_Latn-tpt_Latn data_files: - path: train/eng_Latn-tpt_Latn.jsonl.gz split: train - path: test/eng_Latn-tpt_Latn.jsonl.gz split: test - path: validation/eng_Latn-tpt_Latn.jsonl.gz split: validation - config_name: eng_Latn-zos_Latn data_files: - path: train/eng_Latn-zos_Latn.jsonl.gz split: train - path: test/eng_Latn-zos_Latn.jsonl.gz split: test - path: validation/eng_Latn-zos_Latn.jsonl.gz split: validation - config_name: eng_Latn-blw_Latn data_files: - path: train/eng_Latn-blw_Latn.jsonl.gz split: train - path: test/eng_Latn-blw_Latn.jsonl.gz split: test - path: validation/eng_Latn-blw_Latn.jsonl.gz split: validation - config_name: eng_Latn-viv_Latn data_files: - path: train/eng_Latn-viv_Latn.jsonl.gz split: train - path: test/eng_Latn-viv_Latn.jsonl.gz split: test - path: validation/eng_Latn-viv_Latn.jsonl.gz split: validation - config_name: eng_Latn-ikw_Latn data_files: - path: train/eng_Latn-ikw_Latn.jsonl.gz split: train - path: test/eng_Latn-ikw_Latn.jsonl.gz split: test - path: validation/eng_Latn-ikw_Latn.jsonl.gz split: validation - config_name: eng_Latn-tue_Latn data_files: - path: train/eng_Latn-tue_Latn.jsonl.gz split: train - path: test/eng_Latn-tue_Latn.jsonl.gz split: test - path: validation/eng_Latn-tue_Latn.jsonl.gz split: validation - config_name: eng_Latn-uvh_Latn data_files: - path: train/eng_Latn-uvh_Latn.jsonl.gz split: train - path: test/eng_Latn-uvh_Latn.jsonl.gz split: test - path: validation/eng_Latn-uvh_Latn.jsonl.gz split: validation - config_name: eng_Latn-yap_Latn data_files: - path: train/eng_Latn-yap_Latn.jsonl.gz split: train - path: test/eng_Latn-yap_Latn.jsonl.gz split: test - path: validation/eng_Latn-yap_Latn.jsonl.gz split: validation - config_name: eng_Latn-nca_Latn data_files: - path: train/eng_Latn-nca_Latn.jsonl.gz split: train - path: test/eng_Latn-nca_Latn.jsonl.gz split: test - path: validation/eng_Latn-nca_Latn.jsonl.gz split: validation - config_name: eng_Latn-luo_Latn data_files: - path: train/eng_Latn-luo_Latn.jsonl.gz split: train - path: test/eng_Latn-luo_Latn.jsonl.gz split: test - path: validation/eng_Latn-luo_Latn.jsonl.gz split: validation - config_name: eng_Latn-tmd_Latn data_files: - path: train/eng_Latn-tmd_Latn.jsonl.gz split: train - path: test/eng_Latn-tmd_Latn.jsonl.gz split: test - path: validation/eng_Latn-tmd_Latn.jsonl.gz split: validation - config_name: eng_Latn-txu_Latn data_files: - path: train/eng_Latn-txu_Latn.jsonl.gz split: train - path: test/eng_Latn-txu_Latn.jsonl.gz split: test - path: validation/eng_Latn-txu_Latn.jsonl.gz split: validation - config_name: eng_Latn-yor_Latn data_files: - path: train/eng_Latn-yor_Latn.jsonl.gz split: train - path: test/eng_Latn-yor_Latn.jsonl.gz split: test - path: validation/eng_Latn-yor_Latn.jsonl.gz split: validation - config_name: eng_Latn-amx_Latn data_files: - path: train/eng_Latn-amx_Latn.jsonl.gz split: train - path: test/eng_Latn-amx_Latn.jsonl.gz split: test - path: validation/eng_Latn-amx_Latn.jsonl.gz split: validation - config_name: eng_Latn-uli_Latn data_files: - path: train/eng_Latn-uli_Latn.jsonl.gz split: train - path: test/eng_Latn-uli_Latn.jsonl.gz split: test - path: validation/eng_Latn-uli_Latn.jsonl.gz split: validation - config_name: eng_Latn-dov_Latn data_files: - path: train/eng_Latn-dov_Latn.jsonl.gz split: train - path: test/eng_Latn-dov_Latn.jsonl.gz split: test - path: validation/eng_Latn-dov_Latn.jsonl.gz split: validation - config_name: eng_Latn-huv_Latn data_files: - path: train/eng_Latn-huv_Latn.jsonl.gz split: train - path: test/eng_Latn-huv_Latn.jsonl.gz split: test - path: validation/eng_Latn-huv_Latn.jsonl.gz split: validation - config_name: eng_Latn-msk_Latn data_files: - path: train/eng_Latn-msk_Latn.jsonl.gz split: train - path: test/eng_Latn-msk_Latn.jsonl.gz split: test - path: validation/eng_Latn-msk_Latn.jsonl.gz split: validation - config_name: eng_Latn-twi_Latn data_files: - path: train/eng_Latn-twi_Latn.jsonl.gz split: train - path: test/eng_Latn-twi_Latn.jsonl.gz split: test - path: validation/eng_Latn-twi_Latn.jsonl.gz split: validation - config_name: eng_Latn-aer_Latn data_files: - path: train/eng_Latn-aer_Latn.jsonl.gz split: train - path: test/eng_Latn-aer_Latn.jsonl.gz split: test - path: validation/eng_Latn-aer_Latn.jsonl.gz split: validation - config_name: eng_Latn-pib_Latn data_files: - path: train/eng_Latn-pib_Latn.jsonl.gz split: train - path: test/eng_Latn-pib_Latn.jsonl.gz split: test - path: validation/eng_Latn-pib_Latn.jsonl.gz split: validation - config_name: eng_Latn-ter_Latn data_files: - path: train/eng_Latn-ter_Latn.jsonl.gz split: train - path: test/eng_Latn-ter_Latn.jsonl.gz split: test - path: validation/eng_Latn-ter_Latn.jsonl.gz split: validation - config_name: eng_Latn-eri_Latn data_files: - path: train/eng_Latn-eri_Latn.jsonl.gz split: train - path: test/eng_Latn-eri_Latn.jsonl.gz split: test - path: validation/eng_Latn-eri_Latn.jsonl.gz split: validation - config_name: eng_Latn-cth_Latn data_files: - path: train/eng_Latn-cth_Latn.jsonl.gz split: train - path: test/eng_Latn-cth_Latn.jsonl.gz split: test - path: validation/eng_Latn-cth_Latn.jsonl.gz split: validation - config_name: eng_Latn-dwr_Latn data_files: - path: train/eng_Latn-dwr_Latn.jsonl.gz split: train - path: test/eng_Latn-dwr_Latn.jsonl.gz split: test - path: validation/eng_Latn-dwr_Latn.jsonl.gz split: validation - config_name: eng_Latn-srq_Latn data_files: - path: train/eng_Latn-srq_Latn.jsonl.gz split: train - path: test/eng_Latn-srq_Latn.jsonl.gz split: test - path: validation/eng_Latn-srq_Latn.jsonl.gz split: validation - config_name: eng_Latn-mmx_Latn data_files: - path: train/eng_Latn-mmx_Latn.jsonl.gz split: train - path: test/eng_Latn-mmx_Latn.jsonl.gz split: test - path: validation/eng_Latn-mmx_Latn.jsonl.gz split: validation - config_name: eng_Latn-cap_Latn data_files: - path: train/eng_Latn-cap_Latn.jsonl.gz split: train - path: test/eng_Latn-cap_Latn.jsonl.gz split: test - path: validation/eng_Latn-cap_Latn.jsonl.gz split: validation - config_name: eng_Latn-ces_Latn data_files: - path: train/eng_Latn-ces_Latn.jsonl.gz split: train - path: test/eng_Latn-ces_Latn.jsonl.gz split: test - path: validation/eng_Latn-ces_Latn.jsonl.gz split: validation - config_name: eng_Latn-cpu_Latn data_files: - path: train/eng_Latn-cpu_Latn.jsonl.gz split: train - path: test/eng_Latn-cpu_Latn.jsonl.gz split: test - path: validation/eng_Latn-cpu_Latn.jsonl.gz split: validation - config_name: eng_Latn-lww_Latn data_files: - path: train/eng_Latn-lww_Latn.jsonl.gz split: train - path: test/eng_Latn-lww_Latn.jsonl.gz split: test - path: validation/eng_Latn-lww_Latn.jsonl.gz split: validation - config_name: eng_Latn-hix_Latn data_files: - path: train/eng_Latn-hix_Latn.jsonl.gz split: train - path: test/eng_Latn-hix_Latn.jsonl.gz split: test - path: validation/eng_Latn-hix_Latn.jsonl.gz split: validation - config_name: eng_Latn-cab_Latn data_files: - path: train/eng_Latn-cab_Latn.jsonl.gz split: train - path: test/eng_Latn-cab_Latn.jsonl.gz split: test - path: validation/eng_Latn-cab_Latn.jsonl.gz split: validation - config_name: eng_Latn-fuf_Latn data_files: - path: train/eng_Latn-fuf_Latn.jsonl.gz split: train - path: test/eng_Latn-fuf_Latn.jsonl.gz split: test - path: validation/eng_Latn-fuf_Latn.jsonl.gz split: validation - config_name: eng_Latn-mcf_Latn data_files: - path: train/eng_Latn-mcf_Latn.jsonl.gz split: train - path: test/eng_Latn-mcf_Latn.jsonl.gz split: test - path: validation/eng_Latn-mcf_Latn.jsonl.gz split: validation - config_name: eng_Latn-shj_Latn data_files: - path: train/eng_Latn-shj_Latn.jsonl.gz split: train - path: test/eng_Latn-shj_Latn.jsonl.gz split: test - path: validation/eng_Latn-shj_Latn.jsonl.gz split: validation - config_name: eng_Latn-qwh_Latn data_files: - path: train/eng_Latn-qwh_Latn.jsonl.gz split: train - path: test/eng_Latn-qwh_Latn.jsonl.gz split: test - path: validation/eng_Latn-qwh_Latn.jsonl.gz split: validation - config_name: eng_Latn-zsr_Latn data_files: - path: train/eng_Latn-zsr_Latn.jsonl.gz split: train - path: test/eng_Latn-zsr_Latn.jsonl.gz split: test - path: validation/eng_Latn-zsr_Latn.jsonl.gz split: validation - config_name: eng_Latn-daa_Latn data_files: - path: train/eng_Latn-daa_Latn.jsonl.gz split: train - path: test/eng_Latn-daa_Latn.jsonl.gz split: test - path: validation/eng_Latn-daa_Latn.jsonl.gz split: validation - config_name: eng_Latn-sus_Arab data_files: - path: train/eng_Latn-sus_Arab.jsonl.gz split: train - path: test/eng_Latn-sus_Arab.jsonl.gz split: test - path: validation/eng_Latn-sus_Arab.jsonl.gz split: validation - config_name: eng_Latn-lbk_Latn data_files: - path: train/eng_Latn-lbk_Latn.jsonl.gz split: train - path: test/eng_Latn-lbk_Latn.jsonl.gz split: test - path: validation/eng_Latn-lbk_Latn.jsonl.gz split: validation - config_name: eng_Latn-nii_Latn data_files: - path: train/eng_Latn-nii_Latn.jsonl.gz split: train - path: test/eng_Latn-nii_Latn.jsonl.gz split: test - path: validation/eng_Latn-nii_Latn.jsonl.gz split: validation - config_name: eng_Latn-gvn_Latn data_files: - path: train/eng_Latn-gvn_Latn.jsonl.gz split: train - path: test/eng_Latn-gvn_Latn.jsonl.gz split: test - path: validation/eng_Latn-gvn_Latn.jsonl.gz split: validation - config_name: eng_Latn-yaa_Latn data_files: - path: train/eng_Latn-yaa_Latn.jsonl.gz split: train - path: test/eng_Latn-yaa_Latn.jsonl.gz split: test - path: validation/eng_Latn-yaa_Latn.jsonl.gz split: validation - config_name: eng_Latn-npi_Deva data_files: - path: train/eng_Latn-npi_Deva.jsonl.gz split: train - path: test/eng_Latn-npi_Deva.jsonl.gz split: test - path: validation/eng_Latn-npi_Deva.jsonl.gz split: validation - config_name: eng_Latn-uig_Latn data_files: - path: train/eng_Latn-uig_Latn.jsonl.gz split: train - path: test/eng_Latn-uig_Latn.jsonl.gz split: test - path: validation/eng_Latn-uig_Latn.jsonl.gz split: validation - config_name: eng_Latn-mmo_Latn data_files: - path: train/eng_Latn-mmo_Latn.jsonl.gz split: train - path: test/eng_Latn-mmo_Latn.jsonl.gz split: test - path: validation/eng_Latn-mmo_Latn.jsonl.gz split: validation - config_name: eng_Latn-ktm_Latn data_files: - path: train/eng_Latn-ktm_Latn.jsonl.gz split: train - path: test/eng_Latn-ktm_Latn.jsonl.gz split: test - path: validation/eng_Latn-ktm_Latn.jsonl.gz split: validation - config_name: eng_Latn-agu_Latn data_files: - path: train/eng_Latn-agu_Latn.jsonl.gz split: train - path: test/eng_Latn-agu_Latn.jsonl.gz split: test - path: validation/eng_Latn-agu_Latn.jsonl.gz split: validation - config_name: eng_Latn-agg_Latn data_files: - path: train/eng_Latn-agg_Latn.jsonl.gz split: train - path: test/eng_Latn-agg_Latn.jsonl.gz split: test - path: validation/eng_Latn-agg_Latn.jsonl.gz split: validation - config_name: eng_Latn-ken_Latn data_files: - path: train/eng_Latn-ken_Latn.jsonl.gz split: train - path: test/eng_Latn-ken_Latn.jsonl.gz split: test - path: validation/eng_Latn-ken_Latn.jsonl.gz split: validation - config_name: eng_Latn-beu_Latn data_files: - path: train/eng_Latn-beu_Latn.jsonl.gz split: train - path: test/eng_Latn-beu_Latn.jsonl.gz split: test - path: validation/eng_Latn-beu_Latn.jsonl.gz split: validation - config_name: eng_Latn-cac_Latn data_files: - path: train/eng_Latn-cac_Latn.jsonl.gz split: train - path: test/eng_Latn-cac_Latn.jsonl.gz split: test - path: validation/eng_Latn-cac_Latn.jsonl.gz split: validation - config_name: eng_Latn-uri_Latn data_files: - path: train/eng_Latn-uri_Latn.jsonl.gz split: train - path: test/eng_Latn-uri_Latn.jsonl.gz split: test - path: validation/eng_Latn-uri_Latn.jsonl.gz split: validation - config_name: eng_Latn-dah_Latn data_files: - path: train/eng_Latn-dah_Latn.jsonl.gz split: train - path: test/eng_Latn-dah_Latn.jsonl.gz split: test - path: validation/eng_Latn-dah_Latn.jsonl.gz split: validation - config_name: eng_Latn-otn_Latn data_files: - path: train/eng_Latn-otn_Latn.jsonl.gz split: train - path: test/eng_Latn-otn_Latn.jsonl.gz split: test - path: validation/eng_Latn-otn_Latn.jsonl.gz split: validation - config_name: eng_Latn-wos_Latn data_files: - path: train/eng_Latn-wos_Latn.jsonl.gz split: train - path: test/eng_Latn-wos_Latn.jsonl.gz split: test - path: validation/eng_Latn-wos_Latn.jsonl.gz split: validation - config_name: eng_Latn-hin_Deva data_files: - path: train/eng_Latn-hin_Deva.jsonl.gz split: train - path: test/eng_Latn-hin_Deva.jsonl.gz split: test - path: validation/eng_Latn-hin_Deva.jsonl.gz split: validation - config_name: eng_Latn-ctu_Latn data_files: - path: train/eng_Latn-ctu_Latn.jsonl.gz split: train - path: test/eng_Latn-ctu_Latn.jsonl.gz split: test - path: validation/eng_Latn-ctu_Latn.jsonl.gz split: validation - config_name: eng_Latn-pes_Arab data_files: - path: train/eng_Latn-pes_Arab.jsonl.gz split: train - path: test/eng_Latn-pes_Arab.jsonl.gz split: test - path: validation/eng_Latn-pes_Arab.jsonl.gz split: validation - config_name: eng_Latn-tbf_Latn data_files: - path: train/eng_Latn-tbf_Latn.jsonl.gz split: train - path: test/eng_Latn-tbf_Latn.jsonl.gz split: test - path: validation/eng_Latn-tbf_Latn.jsonl.gz split: validation - config_name: eng_Latn-bsj_Latn data_files: - path: train/eng_Latn-bsj_Latn.jsonl.gz split: train - path: test/eng_Latn-bsj_Latn.jsonl.gz split: test - path: validation/eng_Latn-bsj_Latn.jsonl.gz split: validation - config_name: eng_Latn-aey_Latn data_files: - path: train/eng_Latn-aey_Latn.jsonl.gz split: train - path: test/eng_Latn-aey_Latn.jsonl.gz split: test - path: validation/eng_Latn-aey_Latn.jsonl.gz split: validation - config_name: eng_Latn-qxn_Latn data_files: - path: train/eng_Latn-qxn_Latn.jsonl.gz split: train - path: test/eng_Latn-qxn_Latn.jsonl.gz split: test - path: validation/eng_Latn-qxn_Latn.jsonl.gz split: validation - config_name: eng_Latn-rug_Latn data_files: - path: train/eng_Latn-rug_Latn.jsonl.gz split: train - path: test/eng_Latn-rug_Latn.jsonl.gz split: test - path: validation/eng_Latn-rug_Latn.jsonl.gz split: validation - config_name: eng_Latn-nwi_Latn data_files: - path: train/eng_Latn-nwi_Latn.jsonl.gz split: train - path: test/eng_Latn-nwi_Latn.jsonl.gz split: test - path: validation/eng_Latn-nwi_Latn.jsonl.gz split: validation - config_name: eng_Latn-spl_Latn data_files: - path: train/eng_Latn-spl_Latn.jsonl.gz split: train - path: test/eng_Latn-spl_Latn.jsonl.gz split: test - path: validation/eng_Latn-spl_Latn.jsonl.gz split: validation - config_name: eng_Latn-kan_Knda data_files: - path: train/eng_Latn-kan_Knda.jsonl.gz split: train - path: test/eng_Latn-kan_Knda.jsonl.gz split: test - path: validation/eng_Latn-kan_Knda.jsonl.gz split: validation - config_name: eng_Latn-dif_Latn data_files: - path: train/eng_Latn-dif_Latn.jsonl.gz split: train - path: test/eng_Latn-dif_Latn.jsonl.gz split: test - path: validation/eng_Latn-dif_Latn.jsonl.gz split: validation - config_name: eng_Latn-cpa_Latn data_files: - path: train/eng_Latn-cpa_Latn.jsonl.gz split: train - path: test/eng_Latn-cpa_Latn.jsonl.gz split: test - path: validation/eng_Latn-cpa_Latn.jsonl.gz split: validation - config_name: eng_Latn-mau_Latn data_files: - path: train/eng_Latn-mau_Latn.jsonl.gz split: train - path: test/eng_Latn-mau_Latn.jsonl.gz split: test - path: validation/eng_Latn-mau_Latn.jsonl.gz split: validation - config_name: eng_Latn-ron_Latn data_files: - path: train/eng_Latn-ron_Latn.jsonl.gz split: train - path: test/eng_Latn-ron_Latn.jsonl.gz split: test - path: validation/eng_Latn-ron_Latn.jsonl.gz split: validation - config_name: eng_Latn-dop_Latn data_files: - path: train/eng_Latn-dop_Latn.jsonl.gz split: train - path: test/eng_Latn-dop_Latn.jsonl.gz split: test - path: validation/eng_Latn-dop_Latn.jsonl.gz split: validation - config_name: eng_Latn-hau_Latn data_files: - path: train/eng_Latn-hau_Latn.jsonl.gz split: train - path: test/eng_Latn-hau_Latn.jsonl.gz split: test - path: validation/eng_Latn-hau_Latn.jsonl.gz split: validation - config_name: eng_Latn-gnn_Latn data_files: - path: train/eng_Latn-gnn_Latn.jsonl.gz split: train - path: test/eng_Latn-gnn_Latn.jsonl.gz split: test - path: validation/eng_Latn-gnn_Latn.jsonl.gz split: validation - config_name: eng_Latn-bsn_Latn data_files: - path: train/eng_Latn-bsn_Latn.jsonl.gz split: train - path: test/eng_Latn-bsn_Latn.jsonl.gz split: test - path: validation/eng_Latn-bsn_Latn.jsonl.gz split: validation - config_name: eng_Latn-kpj_Latn data_files: - path: train/eng_Latn-kpj_Latn.jsonl.gz split: train - path: test/eng_Latn-kpj_Latn.jsonl.gz split: test - path: validation/eng_Latn-kpj_Latn.jsonl.gz split: validation - config_name: eng_Latn-wat_Latn data_files: - path: train/eng_Latn-wat_Latn.jsonl.gz split: train - path: test/eng_Latn-wat_Latn.jsonl.gz split: test - path: validation/eng_Latn-wat_Latn.jsonl.gz split: validation - config_name: eng_Latn-acr_Latn data_files: - path: train/eng_Latn-acr_Latn.jsonl.gz split: train - path: test/eng_Latn-acr_Latn.jsonl.gz split: test - path: validation/eng_Latn-acr_Latn.jsonl.gz split: validation - config_name: eng_Latn-caf_Latn data_files: - path: train/eng_Latn-caf_Latn.jsonl.gz split: train - path: test/eng_Latn-caf_Latn.jsonl.gz split: test - path: validation/eng_Latn-caf_Latn.jsonl.gz split: validation - config_name: eng_Latn-dhg_Latn data_files: - path: train/eng_Latn-dhg_Latn.jsonl.gz split: train - path: test/eng_Latn-dhg_Latn.jsonl.gz split: test - path: validation/eng_Latn-dhg_Latn.jsonl.gz split: validation - config_name: eng_Latn-yml_Latn data_files: - path: train/eng_Latn-yml_Latn.jsonl.gz split: train - path: test/eng_Latn-yml_Latn.jsonl.gz split: test - path: validation/eng_Latn-yml_Latn.jsonl.gz split: validation - config_name: eng_Latn-atd_Latn data_files: - path: train/eng_Latn-atd_Latn.jsonl.gz split: train - path: test/eng_Latn-atd_Latn.jsonl.gz split: test - path: validation/eng_Latn-atd_Latn.jsonl.gz split: validation - config_name: eng_Latn-bbb_Latn data_files: - path: train/eng_Latn-bbb_Latn.jsonl.gz split: train - path: test/eng_Latn-bbb_Latn.jsonl.gz split: test - path: validation/eng_Latn-bbb_Latn.jsonl.gz split: validation - config_name: eng_Latn-cle_Latn data_files: - path: train/eng_Latn-cle_Latn.jsonl.gz split: train - path: test/eng_Latn-cle_Latn.jsonl.gz split: test - path: validation/eng_Latn-cle_Latn.jsonl.gz split: validation - config_name: eng_Latn-myk_Latn data_files: - path: train/eng_Latn-myk_Latn.jsonl.gz split: train - path: test/eng_Latn-myk_Latn.jsonl.gz split: test - path: validation/eng_Latn-myk_Latn.jsonl.gz split: validation - config_name: eng_Latn-bxh_Latn data_files: - path: train/eng_Latn-bxh_Latn.jsonl.gz split: train - path: test/eng_Latn-bxh_Latn.jsonl.gz split: test - path: validation/eng_Latn-bxh_Latn.jsonl.gz split: validation - config_name: eng_Latn-tpa_Latn data_files: - path: train/eng_Latn-tpa_Latn.jsonl.gz split: train - path: test/eng_Latn-tpa_Latn.jsonl.gz split: test - path: validation/eng_Latn-tpa_Latn.jsonl.gz split: validation - config_name: eng_Latn-awk_Latn data_files: - path: train/eng_Latn-awk_Latn.jsonl.gz split: train - path: test/eng_Latn-awk_Latn.jsonl.gz split: test - path: validation/eng_Latn-awk_Latn.jsonl.gz split: validation - config_name: eng_Latn-gfk_Latn data_files: - path: train/eng_Latn-gfk_Latn.jsonl.gz split: train - path: test/eng_Latn-gfk_Latn.jsonl.gz split: test - path: validation/eng_Latn-gfk_Latn.jsonl.gz split: validation - config_name: eng_Latn-mph_Latn data_files: - path: train/eng_Latn-mph_Latn.jsonl.gz split: train - path: test/eng_Latn-mph_Latn.jsonl.gz split: test - path: validation/eng_Latn-mph_Latn.jsonl.gz split: validation - config_name: eng_Latn-csy_Latn data_files: - path: train/eng_Latn-csy_Latn.jsonl.gz split: train - path: test/eng_Latn-csy_Latn.jsonl.gz split: test - path: validation/eng_Latn-csy_Latn.jsonl.gz split: validation - config_name: eng_Latn-tgp_Latn data_files: - path: train/eng_Latn-tgp_Latn.jsonl.gz split: train - path: test/eng_Latn-tgp_Latn.jsonl.gz split: test - path: validation/eng_Latn-tgp_Latn.jsonl.gz split: validation - config_name: eng_Latn-zia_Latn data_files: - path: train/eng_Latn-zia_Latn.jsonl.gz split: train - path: test/eng_Latn-zia_Latn.jsonl.gz split: test - path: validation/eng_Latn-zia_Latn.jsonl.gz split: validation - config_name: eng_Latn-msm_Latn data_files: - path: train/eng_Latn-msm_Latn.jsonl.gz split: train - path: test/eng_Latn-msm_Latn.jsonl.gz split: test - path: validation/eng_Latn-msm_Latn.jsonl.gz split: validation - config_name: eng_Latn-kql_Latn data_files: - path: train/eng_Latn-kql_Latn.jsonl.gz split: train - path: test/eng_Latn-kql_Latn.jsonl.gz split: test - path: validation/eng_Latn-kql_Latn.jsonl.gz split: validation - config_name: eng_Latn-wnu_Latn data_files: - path: train/eng_Latn-wnu_Latn.jsonl.gz split: train - path: test/eng_Latn-wnu_Latn.jsonl.gz split: test - path: validation/eng_Latn-wnu_Latn.jsonl.gz split: validation - config_name: eng_Latn-nin_Latn data_files: - path: train/eng_Latn-nin_Latn.jsonl.gz split: train - path: test/eng_Latn-nin_Latn.jsonl.gz split: test - path: validation/eng_Latn-nin_Latn.jsonl.gz split: validation - config_name: eng_Latn-kmo_Latn data_files: - path: train/eng_Latn-kmo_Latn.jsonl.gz split: train - path: test/eng_Latn-kmo_Latn.jsonl.gz split: test - path: validation/eng_Latn-kmo_Latn.jsonl.gz split: validation - config_name: eng_Latn-mpx_Latn data_files: - path: train/eng_Latn-mpx_Latn.jsonl.gz split: train - path: test/eng_Latn-mpx_Latn.jsonl.gz split: test - path: validation/eng_Latn-mpx_Latn.jsonl.gz split: validation - config_name: eng_Latn-nas_Latn data_files: - path: train/eng_Latn-nas_Latn.jsonl.gz split: train - path: test/eng_Latn-nas_Latn.jsonl.gz split: test - path: validation/eng_Latn-nas_Latn.jsonl.gz split: validation - config_name: eng_Latn-ulk_Latn data_files: - path: train/eng_Latn-ulk_Latn.jsonl.gz split: train - path: test/eng_Latn-ulk_Latn.jsonl.gz split: test - path: validation/eng_Latn-ulk_Latn.jsonl.gz split: validation - config_name: eng_Latn-ipi_Latn data_files: - path: train/eng_Latn-ipi_Latn.jsonl.gz split: train - path: test/eng_Latn-ipi_Latn.jsonl.gz split: test - path: validation/eng_Latn-ipi_Latn.jsonl.gz split: validation - config_name: eng_Latn-mgc_Latn data_files: - path: train/eng_Latn-mgc_Latn.jsonl.gz split: train - path: test/eng_Latn-mgc_Latn.jsonl.gz split: test - path: validation/eng_Latn-mgc_Latn.jsonl.gz split: validation - config_name: eng_Latn-ape_Latn data_files: - path: train/eng_Latn-ape_Latn.jsonl.gz split: train - path: test/eng_Latn-ape_Latn.jsonl.gz split: test - path: validation/eng_Latn-ape_Latn.jsonl.gz split: validation - config_name: eng_Latn-tac_Latn data_files: - path: train/eng_Latn-tac_Latn.jsonl.gz split: train - path: test/eng_Latn-tac_Latn.jsonl.gz split: test - path: validation/eng_Latn-tac_Latn.jsonl.gz split: validation - config_name: eng_Latn-bzd_Latn data_files: - path: train/eng_Latn-bzd_Latn.jsonl.gz split: train - path: test/eng_Latn-bzd_Latn.jsonl.gz split: test - path: validation/eng_Latn-bzd_Latn.jsonl.gz split: validation - config_name: eng_Latn-amm_Latn data_files: - path: train/eng_Latn-amm_Latn.jsonl.gz split: train - path: test/eng_Latn-amm_Latn.jsonl.gz split: test - path: validation/eng_Latn-amm_Latn.jsonl.gz split: validation - config_name: eng_Latn-mic_Latn data_files: - path: train/eng_Latn-mic_Latn.jsonl.gz split: train - path: test/eng_Latn-mic_Latn.jsonl.gz split: test - path: validation/eng_Latn-mic_Latn.jsonl.gz split: validation - config_name: eng_Latn-sxb_Latn data_files: - path: train/eng_Latn-sxb_Latn.jsonl.gz split: train - path: test/eng_Latn-sxb_Latn.jsonl.gz split: test - path: validation/eng_Latn-sxb_Latn.jsonl.gz split: validation - config_name: eng_Latn-cux_Latn data_files: - path: train/eng_Latn-cux_Latn.jsonl.gz split: train - path: test/eng_Latn-cux_Latn.jsonl.gz split: test - path: validation/eng_Latn-cux_Latn.jsonl.gz split: validation - config_name: eng_Latn-ixl_Latn data_files: - path: train/eng_Latn-ixl_Latn.jsonl.gz split: train - path: test/eng_Latn-ixl_Latn.jsonl.gz split: test - path: validation/eng_Latn-ixl_Latn.jsonl.gz split: validation - config_name: eng_Latn-nif_Latn data_files: - path: train/eng_Latn-nif_Latn.jsonl.gz split: train - path: test/eng_Latn-nif_Latn.jsonl.gz split: test - path: validation/eng_Latn-nif_Latn.jsonl.gz split: validation - config_name: eng_Latn-isn_Latn data_files: - path: train/eng_Latn-isn_Latn.jsonl.gz split: train - path: test/eng_Latn-isn_Latn.jsonl.gz split: test - path: validation/eng_Latn-isn_Latn.jsonl.gz split: validation - config_name: eng_Latn-cmn_Hans data_files: - path: train/eng_Latn-cmn_Hans.jsonl.gz split: train - path: test/eng_Latn-cmn_Hans.jsonl.gz split: test - path: validation/eng_Latn-cmn_Hans.jsonl.gz split: validation - config_name: eng_Latn-kyf_Latn data_files: - path: train/eng_Latn-kyf_Latn.jsonl.gz split: train - path: test/eng_Latn-kyf_Latn.jsonl.gz split: test - path: validation/eng_Latn-kyf_Latn.jsonl.gz split: validation - config_name: eng_Latn-cut_Latn data_files: - path: train/eng_Latn-cut_Latn.jsonl.gz split: train - path: test/eng_Latn-cut_Latn.jsonl.gz split: test - path: validation/eng_Latn-cut_Latn.jsonl.gz split: validation - config_name: eng_Latn-lcm_Latn data_files: - path: train/eng_Latn-lcm_Latn.jsonl.gz split: train - path: test/eng_Latn-lcm_Latn.jsonl.gz split: test - path: validation/eng_Latn-lcm_Latn.jsonl.gz split: validation - config_name: eng_Latn-nya_Latn data_files: - path: train/eng_Latn-nya_Latn.jsonl.gz split: train - path: test/eng_Latn-nya_Latn.jsonl.gz split: test - path: validation/eng_Latn-nya_Latn.jsonl.gz split: validation - config_name: eng_Latn-kjs_Latn data_files: - path: train/eng_Latn-kjs_Latn.jsonl.gz split: train - path: test/eng_Latn-kjs_Latn.jsonl.gz split: test - path: validation/eng_Latn-kjs_Latn.jsonl.gz split: validation - config_name: eng_Latn-ton_Latn data_files: - path: train/eng_Latn-ton_Latn.jsonl.gz split: train - path: test/eng_Latn-ton_Latn.jsonl.gz split: test - path: validation/eng_Latn-ton_Latn.jsonl.gz split: validation - config_name: eng_Latn-qvs_Latn data_files: - path: train/eng_Latn-qvs_Latn.jsonl.gz split: train - path: test/eng_Latn-qvs_Latn.jsonl.gz split: test - path: validation/eng_Latn-qvs_Latn.jsonl.gz split: validation - config_name: eng_Latn-ino_Latn data_files: - path: train/eng_Latn-ino_Latn.jsonl.gz split: train - path: test/eng_Latn-ino_Latn.jsonl.gz split: test - path: validation/eng_Latn-ino_Latn.jsonl.gz split: validation - config_name: eng_Latn-zca_Latn data_files: - path: train/eng_Latn-zca_Latn.jsonl.gz split: train - path: test/eng_Latn-zca_Latn.jsonl.gz split: test - path: validation/eng_Latn-zca_Latn.jsonl.gz split: validation - config_name: eng_Latn-xav_Latn data_files: - path: train/eng_Latn-xav_Latn.jsonl.gz split: train - path: test/eng_Latn-xav_Latn.jsonl.gz split: test - path: validation/eng_Latn-xav_Latn.jsonl.gz split: validation - config_name: eng_Latn-jac_Latn data_files: - path: train/eng_Latn-jac_Latn.jsonl.gz split: train - path: test/eng_Latn-jac_Latn.jsonl.gz split: test - path: validation/eng_Latn-jac_Latn.jsonl.gz split: validation - config_name: eng_Latn-quc_Latn data_files: - path: train/eng_Latn-quc_Latn.jsonl.gz split: train - path: test/eng_Latn-quc_Latn.jsonl.gz split: test - path: validation/eng_Latn-quc_Latn.jsonl.gz split: validation - config_name: eng_Latn-npl_Latn data_files: - path: train/eng_Latn-npl_Latn.jsonl.gz split: train - path: test/eng_Latn-npl_Latn.jsonl.gz split: test - path: validation/eng_Latn-npl_Latn.jsonl.gz split: validation - config_name: eng_Latn-usa_Latn data_files: - path: train/eng_Latn-usa_Latn.jsonl.gz split: train - path: test/eng_Latn-usa_Latn.jsonl.gz split: test - path: validation/eng_Latn-usa_Latn.jsonl.gz split: validation - config_name: eng_Latn-kvg_Latn data_files: - path: train/eng_Latn-kvg_Latn.jsonl.gz split: train - path: test/eng_Latn-kvg_Latn.jsonl.gz split: test - path: validation/eng_Latn-kvg_Latn.jsonl.gz split: validation - config_name: eng_Latn-tee_Latn data_files: - path: train/eng_Latn-tee_Latn.jsonl.gz split: train - path: test/eng_Latn-tee_Latn.jsonl.gz split: test - path: validation/eng_Latn-tee_Latn.jsonl.gz split: validation - config_name: eng_Latn-hot_Latn data_files: - path: train/eng_Latn-hot_Latn.jsonl.gz split: train - path: test/eng_Latn-hot_Latn.jsonl.gz split: test - path: validation/eng_Latn-hot_Latn.jsonl.gz split: validation - config_name: eng_Latn-acf_Latn data_files: - path: train/eng_Latn-acf_Latn.jsonl.gz split: train - path: test/eng_Latn-acf_Latn.jsonl.gz split: test - path: validation/eng_Latn-acf_Latn.jsonl.gz split: validation - config_name: eng_Latn-wiu_Latn data_files: - path: train/eng_Latn-wiu_Latn.jsonl.gz split: train - path: test/eng_Latn-wiu_Latn.jsonl.gz split: test - path: validation/eng_Latn-wiu_Latn.jsonl.gz split: validation - config_name: eng_Latn-rmc_Latn data_files: - path: train/eng_Latn-rmc_Latn.jsonl.gz split: train - path: test/eng_Latn-rmc_Latn.jsonl.gz split: test - path: validation/eng_Latn-rmc_Latn.jsonl.gz split: validation - config_name: eng_Latn-snx_Latn data_files: - path: train/eng_Latn-snx_Latn.jsonl.gz split: train - path: test/eng_Latn-snx_Latn.jsonl.gz split: test - path: validation/eng_Latn-snx_Latn.jsonl.gz split: validation - config_name: eng_Latn-jpn_Jpan data_files: - path: train/eng_Latn-jpn_Jpan.jsonl.gz split: train - path: test/eng_Latn-jpn_Jpan.jsonl.gz split: test - path: validation/eng_Latn-jpn_Jpan.jsonl.gz split: validation - config_name: eng_Latn-tbg_Latn data_files: - path: train/eng_Latn-tbg_Latn.jsonl.gz split: train - path: test/eng_Latn-tbg_Latn.jsonl.gz split: test - path: validation/eng_Latn-tbg_Latn.jsonl.gz split: validation - config_name: eng_Latn-pwg_Latn data_files: - path: train/eng_Latn-pwg_Latn.jsonl.gz split: train - path: test/eng_Latn-pwg_Latn.jsonl.gz split: test - path: validation/eng_Latn-pwg_Latn.jsonl.gz split: validation - config_name: eng_Latn-nhr_Latn data_files: - path: train/eng_Latn-nhr_Latn.jsonl.gz split: train - path: test/eng_Latn-nhr_Latn.jsonl.gz split: test - path: validation/eng_Latn-nhr_Latn.jsonl.gz split: validation - config_name: eng_Latn-mwe_Latn data_files: - path: train/eng_Latn-mwe_Latn.jsonl.gz split: train - path: test/eng_Latn-mwe_Latn.jsonl.gz split: test - path: validation/eng_Latn-mwe_Latn.jsonl.gz split: validation - config_name: eng_Latn-kbq_Latn data_files: - path: train/eng_Latn-kbq_Latn.jsonl.gz split: train - path: test/eng_Latn-kbq_Latn.jsonl.gz split: test - path: validation/eng_Latn-kbq_Latn.jsonl.gz split: validation - config_name: eng_Latn-myw_Latn data_files: - path: train/eng_Latn-myw_Latn.jsonl.gz split: train - path: test/eng_Latn-myw_Latn.jsonl.gz split: test - path: validation/eng_Latn-myw_Latn.jsonl.gz split: validation - config_name: eng_Latn-jni_Latn data_files: - path: train/eng_Latn-jni_Latn.jsonl.gz split: train - path: test/eng_Latn-jni_Latn.jsonl.gz split: test - path: validation/eng_Latn-jni_Latn.jsonl.gz split: validation - config_name: eng_Latn-vmy_Latn data_files: - path: train/eng_Latn-vmy_Latn.jsonl.gz split: train - path: test/eng_Latn-vmy_Latn.jsonl.gz split: test - path: validation/eng_Latn-vmy_Latn.jsonl.gz split: validation - config_name: eng_Latn-zpv_Latn data_files: - path: train/eng_Latn-zpv_Latn.jsonl.gz split: train - path: test/eng_Latn-zpv_Latn.jsonl.gz split: test - path: validation/eng_Latn-zpv_Latn.jsonl.gz split: validation - config_name: eng_Latn-heb_Hebr data_files: - path: train/eng_Latn-heb_Hebr.jsonl.gz split: train - path: test/eng_Latn-heb_Hebr.jsonl.gz split: test - path: validation/eng_Latn-heb_Hebr.jsonl.gz split: validation - config_name: eng_Latn-bki_Latn data_files: - path: train/eng_Latn-bki_Latn.jsonl.gz split: train - path: test/eng_Latn-bki_Latn.jsonl.gz split: test - path: validation/eng_Latn-bki_Latn.jsonl.gz split: validation - config_name: eng_Latn-mee_Latn data_files: - path: train/eng_Latn-mee_Latn.jsonl.gz split: train - path: test/eng_Latn-mee_Latn.jsonl.gz split: test - path: validation/eng_Latn-mee_Latn.jsonl.gz split: validation - config_name: eng_Latn-aau_Latn data_files: - path: train/eng_Latn-aau_Latn.jsonl.gz split: train - path: test/eng_Latn-aau_Latn.jsonl.gz split: test - path: validation/eng_Latn-aau_Latn.jsonl.gz split: validation - config_name: eng_Latn-aaz_Latn data_files: - path: train/eng_Latn-aaz_Latn.jsonl.gz split: train - path: test/eng_Latn-aaz_Latn.jsonl.gz split: test - path: validation/eng_Latn-aaz_Latn.jsonl.gz split: validation - config_name: eng_Latn-aoi_Latn data_files: - path: train/eng_Latn-aoi_Latn.jsonl.gz split: train - path: test/eng_Latn-aoi_Latn.jsonl.gz split: test - path: validation/eng_Latn-aoi_Latn.jsonl.gz split: validation - config_name: eng_Latn-caa_Latn data_files: - path: train/eng_Latn-caa_Latn.jsonl.gz split: train - path: test/eng_Latn-caa_Latn.jsonl.gz split: test - path: validation/eng_Latn-caa_Latn.jsonl.gz split: validation - config_name: eng_Latn-zap_Latn data_files: - path: train/eng_Latn-zap_Latn.jsonl.gz split: train - path: test/eng_Latn-zap_Latn.jsonl.gz split: test - path: validation/eng_Latn-zap_Latn.jsonl.gz split: validation - config_name: eng_Latn-amk_Latn data_files: - path: train/eng_Latn-amk_Latn.jsonl.gz split: train - path: test/eng_Latn-amk_Latn.jsonl.gz split: test - path: validation/eng_Latn-amk_Latn.jsonl.gz split: validation - config_name: eng_Latn-zpo_Latn data_files: - path: train/eng_Latn-zpo_Latn.jsonl.gz split: train - path: test/eng_Latn-zpo_Latn.jsonl.gz split: test - path: validation/eng_Latn-zpo_Latn.jsonl.gz split: validation - config_name: eng_Latn-aom_Latn data_files: - path: train/eng_Latn-aom_Latn.jsonl.gz split: train - path: test/eng_Latn-aom_Latn.jsonl.gz split: test - path: validation/eng_Latn-aom_Latn.jsonl.gz split: validation - config_name: eng_Latn-zpu_Latn data_files: - path: train/eng_Latn-zpu_Latn.jsonl.gz split: train - path: test/eng_Latn-zpu_Latn.jsonl.gz split: test - path: validation/eng_Latn-zpu_Latn.jsonl.gz split: validation - config_name: eng_Latn-bdd_Latn data_files: - path: train/eng_Latn-bdd_Latn.jsonl.gz split: train - path: test/eng_Latn-bdd_Latn.jsonl.gz split: test - path: validation/eng_Latn-bdd_Latn.jsonl.gz split: validation - config_name: eng_Latn-acu_Latn data_files: - path: train/eng_Latn-acu_Latn.jsonl.gz split: train - path: test/eng_Latn-acu_Latn.jsonl.gz split: test - path: validation/eng_Latn-acu_Latn.jsonl.gz split: validation - config_name: eng_Latn-beo_Latn data_files: - path: train/eng_Latn-beo_Latn.jsonl.gz split: train - path: test/eng_Latn-beo_Latn.jsonl.gz split: test - path: validation/eng_Latn-beo_Latn.jsonl.gz split: validation - config_name: eng_Latn-cuc_Latn data_files: - path: train/eng_Latn-cuc_Latn.jsonl.gz split: train - path: test/eng_Latn-cuc_Latn.jsonl.gz split: test - path: validation/eng_Latn-cuc_Latn.jsonl.gz split: validation - config_name: eng_Latn-otm_Latn data_files: - path: train/eng_Latn-otm_Latn.jsonl.gz split: train - path: test/eng_Latn-otm_Latn.jsonl.gz split: test - path: validation/eng_Latn-otm_Latn.jsonl.gz split: validation - config_name: eng_Latn-tos_Latn data_files: - path: train/eng_Latn-tos_Latn.jsonl.gz split: train - path: test/eng_Latn-tos_Latn.jsonl.gz split: test - path: validation/eng_Latn-tos_Latn.jsonl.gz split: validation - config_name: eng_Latn-apu_Latn data_files: - path: train/eng_Latn-apu_Latn.jsonl.gz split: train - path: test/eng_Latn-apu_Latn.jsonl.gz split: test - path: validation/eng_Latn-apu_Latn.jsonl.gz split: validation - config_name: eng_Latn-jic_Latn data_files: - path: train/eng_Latn-jic_Latn.jsonl.gz split: train - path: test/eng_Latn-jic_Latn.jsonl.gz split: test - path: validation/eng_Latn-jic_Latn.jsonl.gz split: validation - config_name: eng_Latn-cek_Latn data_files: - path: train/eng_Latn-cek_Latn.jsonl.gz split: train - path: test/eng_Latn-cek_Latn.jsonl.gz split: test - path: validation/eng_Latn-cek_Latn.jsonl.gz split: validation - config_name: eng_Latn-tnp_Latn data_files: - path: train/eng_Latn-tnp_Latn.jsonl.gz split: train - path: test/eng_Latn-tnp_Latn.jsonl.gz split: test - path: validation/eng_Latn-tnp_Latn.jsonl.gz split: validation - config_name: eng_Latn-hns_Latn data_files: - path: train/eng_Latn-hns_Latn.jsonl.gz split: train - path: test/eng_Latn-hns_Latn.jsonl.gz split: test - path: validation/eng_Latn-hns_Latn.jsonl.gz split: validation - config_name: eng_Latn-mpt_Latn data_files: - path: train/eng_Latn-mpt_Latn.jsonl.gz split: train - path: test/eng_Latn-mpt_Latn.jsonl.gz split: test - path: validation/eng_Latn-mpt_Latn.jsonl.gz split: validation - config_name: eng_Latn-kmg_Latn data_files: - path: train/eng_Latn-kmg_Latn.jsonl.gz split: train - path: test/eng_Latn-kmg_Latn.jsonl.gz split: test - path: validation/eng_Latn-kmg_Latn.jsonl.gz split: validation - config_name: eng_Latn-nhg_Latn data_files: - path: train/eng_Latn-nhg_Latn.jsonl.gz split: train - path: test/eng_Latn-nhg_Latn.jsonl.gz split: test - path: validation/eng_Latn-nhg_Latn.jsonl.gz split: validation - config_name: eng_Latn-yle_Latn data_files: - path: train/eng_Latn-yle_Latn.jsonl.gz split: train - path: test/eng_Latn-yle_Latn.jsonl.gz split: test - path: validation/eng_Latn-yle_Latn.jsonl.gz split: validation - config_name: eng_Latn-yka_Latn data_files: - path: train/eng_Latn-yka_Latn.jsonl.gz split: train - path: test/eng_Latn-yka_Latn.jsonl.gz split: test - path: validation/eng_Latn-yka_Latn.jsonl.gz split: validation - config_name: eng_Latn-maj_Latn data_files: - path: train/eng_Latn-maj_Latn.jsonl.gz split: train - path: test/eng_Latn-maj_Latn.jsonl.gz split: test - path: validation/eng_Latn-maj_Latn.jsonl.gz split: validation - config_name: eng_Latn-agt_Latn data_files: - path: train/eng_Latn-agt_Latn.jsonl.gz split: train - path: test/eng_Latn-agt_Latn.jsonl.gz split: test - path: validation/eng_Latn-agt_Latn.jsonl.gz split: validation - config_name: eng_Latn-san_Latn data_files: - path: train/eng_Latn-san_Latn.jsonl.gz split: train - path: test/eng_Latn-san_Latn.jsonl.gz split: test - path: validation/eng_Latn-san_Latn.jsonl.gz split: validation - config_name: eng_Latn-kew_Latn data_files: - path: train/eng_Latn-kew_Latn.jsonl.gz split: train - path: test/eng_Latn-kew_Latn.jsonl.gz split: test - path: validation/eng_Latn-kew_Latn.jsonl.gz split: validation - config_name: eng_Latn-nop_Latn data_files: - path: train/eng_Latn-nop_Latn.jsonl.gz split: train - path: test/eng_Latn-nop_Latn.jsonl.gz split: test - path: validation/eng_Latn-nop_Latn.jsonl.gz split: validation - config_name: eng_Latn-zyp_Latn data_files: - path: train/eng_Latn-zyp_Latn.jsonl.gz split: train - path: test/eng_Latn-zyp_Latn.jsonl.gz split: test - path: validation/eng_Latn-zyp_Latn.jsonl.gz split: validation - config_name: eng_Latn-qvm_Latn data_files: - path: train/eng_Latn-qvm_Latn.jsonl.gz split: train - path: test/eng_Latn-qvm_Latn.jsonl.gz split: test - path: validation/eng_Latn-qvm_Latn.jsonl.gz split: validation - config_name: eng_Latn-mwp_Latn data_files: - path: train/eng_Latn-mwp_Latn.jsonl.gz split: train - path: test/eng_Latn-mwp_Latn.jsonl.gz split: test - path: validation/eng_Latn-mwp_Latn.jsonl.gz split: validation - config_name: eng_Latn-nhw_Latn data_files: - path: train/eng_Latn-nhw_Latn.jsonl.gz split: train - path: test/eng_Latn-nhw_Latn.jsonl.gz split: test - path: validation/eng_Latn-nhw_Latn.jsonl.gz split: validation - config_name: eng_Latn-als_Latn data_files: - path: train/eng_Latn-als_Latn.jsonl.gz split: train - path: test/eng_Latn-als_Latn.jsonl.gz split: test - path: validation/eng_Latn-als_Latn.jsonl.gz split: validation - config_name: eng_Latn-cof_Latn data_files: - path: train/eng_Latn-cof_Latn.jsonl.gz split: train - path: test/eng_Latn-cof_Latn.jsonl.gz split: test - path: validation/eng_Latn-cof_Latn.jsonl.gz split: validation - config_name: eng_Latn-auy_Latn data_files: - path: train/eng_Latn-auy_Latn.jsonl.gz split: train - path: test/eng_Latn-auy_Latn.jsonl.gz split: test - path: validation/eng_Latn-auy_Latn.jsonl.gz split: validation - config_name: eng_Latn-pol_Latn data_files: - path: train/eng_Latn-pol_Latn.jsonl.gz split: train - path: test/eng_Latn-pol_Latn.jsonl.gz split: test - path: validation/eng_Latn-pol_Latn.jsonl.gz split: validation - config_name: eng_Latn-klt_Latn data_files: - path: train/eng_Latn-klt_Latn.jsonl.gz split: train - path: test/eng_Latn-klt_Latn.jsonl.gz split: test - path: validation/eng_Latn-klt_Latn.jsonl.gz split: validation - config_name: eng_Latn-soy_Latn data_files: - path: train/eng_Latn-soy_Latn.jsonl.gz split: train - path: test/eng_Latn-soy_Latn.jsonl.gz split: test - path: validation/eng_Latn-soy_Latn.jsonl.gz split: validation - config_name: eng_Latn-ita_Latn data_files: - path: train/eng_Latn-ita_Latn.jsonl.gz split: train - path: test/eng_Latn-ita_Latn.jsonl.gz split: test - path: validation/eng_Latn-ita_Latn.jsonl.gz split: validation - config_name: eng_Latn-arn_Latn data_files: - path: train/eng_Latn-arn_Latn.jsonl.gz split: train - path: test/eng_Latn-arn_Latn.jsonl.gz split: test - path: validation/eng_Latn-arn_Latn.jsonl.gz split: validation - config_name: eng_Latn-tbz_Latn data_files: - path: train/eng_Latn-tbz_Latn.jsonl.gz split: train - path: test/eng_Latn-tbz_Latn.jsonl.gz split: test - path: validation/eng_Latn-tbz_Latn.jsonl.gz split: validation - config_name: eng_Latn-zaa_Latn data_files: - path: train/eng_Latn-zaa_Latn.jsonl.gz split: train - path: test/eng_Latn-zaa_Latn.jsonl.gz split: test - path: validation/eng_Latn-zaa_Latn.jsonl.gz split: validation - config_name: eng_Latn-meu_Latn data_files: - path: train/eng_Latn-meu_Latn.jsonl.gz split: train - path: test/eng_Latn-meu_Latn.jsonl.gz split: test - path: validation/eng_Latn-meu_Latn.jsonl.gz split: validation - config_name: eng_Latn-zao_Latn data_files: - path: train/eng_Latn-zao_Latn.jsonl.gz split: train - path: test/eng_Latn-zao_Latn.jsonl.gz split: test - path: validation/eng_Latn-zao_Latn.jsonl.gz split: validation - config_name: eng_Latn-mxp_Latn data_files: - path: train/eng_Latn-mxp_Latn.jsonl.gz split: train - path: test/eng_Latn-mxp_Latn.jsonl.gz split: test - path: validation/eng_Latn-mxp_Latn.jsonl.gz split: validation - config_name: eng_Latn-rgu_Latn data_files: - path: train/eng_Latn-rgu_Latn.jsonl.gz split: train - path: test/eng_Latn-rgu_Latn.jsonl.gz split: test - path: validation/eng_Latn-rgu_Latn.jsonl.gz split: validation - config_name: eng_Latn-tnn_Latn data_files: - path: train/eng_Latn-tnn_Latn.jsonl.gz split: train - path: test/eng_Latn-tnn_Latn.jsonl.gz split: test - path: validation/eng_Latn-tnn_Latn.jsonl.gz split: validation - config_name: eng_Latn-uvl_Latn data_files: - path: train/eng_Latn-uvl_Latn.jsonl.gz split: train - path: test/eng_Latn-uvl_Latn.jsonl.gz split: test - path: validation/eng_Latn-uvl_Latn.jsonl.gz split: validation - config_name: eng_Latn-eko_Latn data_files: - path: train/eng_Latn-eko_Latn.jsonl.gz split: train - path: test/eng_Latn-eko_Latn.jsonl.gz split: test - path: validation/eng_Latn-eko_Latn.jsonl.gz split: validation - config_name: eng_Latn-wmt_Latn data_files: - path: train/eng_Latn-wmt_Latn.jsonl.gz split: train - path: test/eng_Latn-wmt_Latn.jsonl.gz split: test - path: validation/eng_Latn-wmt_Latn.jsonl.gz split: validation - config_name: eng_Latn-kup_Latn data_files: - path: train/eng_Latn-kup_Latn.jsonl.gz split: train - path: test/eng_Latn-kup_Latn.jsonl.gz split: test - path: validation/eng_Latn-kup_Latn.jsonl.gz split: validation - config_name: eng_Latn-zai_Latn data_files: - path: train/eng_Latn-zai_Latn.jsonl.gz split: train - path: test/eng_Latn-zai_Latn.jsonl.gz split: test - path: validation/eng_Latn-zai_Latn.jsonl.gz split: validation - config_name: eng_Latn-ebk_Latn data_files: - path: train/eng_Latn-ebk_Latn.jsonl.gz split: train - path: test/eng_Latn-ebk_Latn.jsonl.gz split: test - path: validation/eng_Latn-ebk_Latn.jsonl.gz split: validation - config_name: eng_Latn-vie_Latn data_files: - path: train/eng_Latn-vie_Latn.jsonl.gz split: train - path: test/eng_Latn-vie_Latn.jsonl.gz split: test - path: validation/eng_Latn-vie_Latn.jsonl.gz split: validation - config_name: eng_Latn-azz_Latn data_files: - path: train/eng_Latn-azz_Latn.jsonl.gz split: train - path: test/eng_Latn-azz_Latn.jsonl.gz split: test - path: validation/eng_Latn-azz_Latn.jsonl.gz split: validation - config_name: eng_Latn-wbp_Latn data_files: - path: train/eng_Latn-wbp_Latn.jsonl.gz split: train - path: test/eng_Latn-wbp_Latn.jsonl.gz split: test - path: validation/eng_Latn-wbp_Latn.jsonl.gz split: validation - config_name: eng_Latn-tvk_Latn data_files: - path: train/eng_Latn-tvk_Latn.jsonl.gz split: train - path: test/eng_Latn-tvk_Latn.jsonl.gz split: test - path: validation/eng_Latn-tvk_Latn.jsonl.gz split: validation - config_name: eng_Latn-ote_Latn data_files: - path: train/eng_Latn-ote_Latn.jsonl.gz split: train - path: test/eng_Latn-ote_Latn.jsonl.gz split: test - path: validation/eng_Latn-ote_Latn.jsonl.gz split: validation - config_name: eng_Latn-ubu_Latn data_files: - path: train/eng_Latn-ubu_Latn.jsonl.gz split: train - path: test/eng_Latn-ubu_Latn.jsonl.gz split: test - path: validation/eng_Latn-ubu_Latn.jsonl.gz split: validation - config_name: eng_Latn-zga_Latn data_files: - path: train/eng_Latn-zga_Latn.jsonl.gz split: train - path: test/eng_Latn-zga_Latn.jsonl.gz split: test - path: validation/eng_Latn-zga_Latn.jsonl.gz split: validation - config_name: eng_Latn-bps_Latn data_files: - path: train/eng_Latn-bps_Latn.jsonl.gz split: train - path: test/eng_Latn-bps_Latn.jsonl.gz split: test - path: validation/eng_Latn-bps_Latn.jsonl.gz split: validation - config_name: eng_Latn-swh_Latn data_files: - path: train/eng_Latn-swh_Latn.jsonl.gz split: train - path: test/eng_Latn-swh_Latn.jsonl.gz split: test - path: validation/eng_Latn-swh_Latn.jsonl.gz split: validation - config_name: eng_Latn-ntp_Latn data_files: - path: train/eng_Latn-ntp_Latn.jsonl.gz split: train - path: test/eng_Latn-ntp_Latn.jsonl.gz split: test - path: validation/eng_Latn-ntp_Latn.jsonl.gz split: validation - config_name: eng_Latn-tav_Latn data_files: - path: train/eng_Latn-tav_Latn.jsonl.gz split: train - path: test/eng_Latn-tav_Latn.jsonl.gz split: test - path: validation/eng_Latn-tav_Latn.jsonl.gz split: validation - config_name: eng_Latn-kms_Latn data_files: - path: train/eng_Latn-kms_Latn.jsonl.gz split: train - path: test/eng_Latn-kms_Latn.jsonl.gz split: test - path: validation/eng_Latn-kms_Latn.jsonl.gz split: validation - config_name: eng_Latn-pio_Latn data_files: - path: train/eng_Latn-pio_Latn.jsonl.gz split: train - path: test/eng_Latn-pio_Latn.jsonl.gz split: test - path: validation/eng_Latn-pio_Latn.jsonl.gz split: validation - config_name: eng_Latn-guj_Gujr data_files: - path: train/eng_Latn-guj_Gujr.jsonl.gz split: train - path: test/eng_Latn-guj_Gujr.jsonl.gz split: test - path: validation/eng_Latn-guj_Gujr.jsonl.gz split: validation - config_name: eng_Latn-mbl_Latn data_files: - path: train/eng_Latn-mbl_Latn.jsonl.gz split: train - path: test/eng_Latn-mbl_Latn.jsonl.gz split: test - path: validation/eng_Latn-mbl_Latn.jsonl.gz split: validation - config_name: eng_Latn-aii_Syrc data_files: - path: train/eng_Latn-aii_Syrc.jsonl.gz split: train - path: test/eng_Latn-aii_Syrc.jsonl.gz split: test - path: validation/eng_Latn-aii_Syrc.jsonl.gz split: validation - config_name: eng_Latn-mle_Latn data_files: - path: train/eng_Latn-mle_Latn.jsonl.gz split: train - path: test/eng_Latn-mle_Latn.jsonl.gz split: test - path: validation/eng_Latn-mle_Latn.jsonl.gz split: validation - config_name: eng_Latn-zam_Latn data_files: - path: train/eng_Latn-zam_Latn.jsonl.gz split: train - path: test/eng_Latn-zam_Latn.jsonl.gz split: test - path: validation/eng_Latn-zam_Latn.jsonl.gz split: validation - config_name: eng_Latn-urt_Latn data_files: - path: train/eng_Latn-urt_Latn.jsonl.gz split: train - path: test/eng_Latn-urt_Latn.jsonl.gz split: test - path: validation/eng_Latn-urt_Latn.jsonl.gz split: validation - config_name: eng_Latn-guo_Latn data_files: - path: train/eng_Latn-guo_Latn.jsonl.gz split: train - path: test/eng_Latn-guo_Latn.jsonl.gz split: test - path: validation/eng_Latn-guo_Latn.jsonl.gz split: validation - config_name: eng_Latn-bkd_Latn data_files: - path: train/eng_Latn-bkd_Latn.jsonl.gz split: train - path: test/eng_Latn-bkd_Latn.jsonl.gz split: test - path: validation/eng_Latn-bkd_Latn.jsonl.gz split: validation - config_name: eng_Latn-rmy_Latn data_files: - path: train/eng_Latn-rmy_Latn.jsonl.gz split: train - path: test/eng_Latn-rmy_Latn.jsonl.gz split: test - path: validation/eng_Latn-rmy_Latn.jsonl.gz split: validation - config_name: eng_Latn-ong_Latn data_files: - path: train/eng_Latn-ong_Latn.jsonl.gz split: train - path: test/eng_Latn-ong_Latn.jsonl.gz split: test - path: validation/eng_Latn-ong_Latn.jsonl.gz split: validation - config_name: eng_Latn-mlp_Latn data_files: - path: train/eng_Latn-mlp_Latn.jsonl.gz split: train - path: test/eng_Latn-mlp_Latn.jsonl.gz split: test - path: validation/eng_Latn-mlp_Latn.jsonl.gz split: validation - config_name: eng_Latn-mir_Latn data_files: - path: train/eng_Latn-mir_Latn.jsonl.gz split: train - path: test/eng_Latn-mir_Latn.jsonl.gz split: test - path: validation/eng_Latn-mir_Latn.jsonl.gz split: validation - config_name: eng_Latn-med_Latn data_files: - path: train/eng_Latn-med_Latn.jsonl.gz split: train - path: test/eng_Latn-med_Latn.jsonl.gz split: test - path: validation/eng_Latn-med_Latn.jsonl.gz split: validation - config_name: eng_Latn-bef_Latn data_files: - path: train/eng_Latn-bef_Latn.jsonl.gz split: train - path: test/eng_Latn-bef_Latn.jsonl.gz split: test - path: validation/eng_Latn-bef_Latn.jsonl.gz split: validation - config_name: eng_Latn-yuw_Latn data_files: - path: train/eng_Latn-yuw_Latn.jsonl.gz split: train - path: test/eng_Latn-yuw_Latn.jsonl.gz split: test - path: validation/eng_Latn-yuw_Latn.jsonl.gz split: validation - config_name: eng_Latn-ded_Latn data_files: - path: train/eng_Latn-ded_Latn.jsonl.gz split: train - path: test/eng_Latn-ded_Latn.jsonl.gz split: test - path: validation/eng_Latn-ded_Latn.jsonl.gz split: validation - config_name: eng_Latn-ame_Latn data_files: - path: train/eng_Latn-ame_Latn.jsonl.gz split: train - path: test/eng_Latn-ame_Latn.jsonl.gz split: test - path: validation/eng_Latn-ame_Latn.jsonl.gz split: validation - config_name: eng_Latn-car_Latn data_files: - path: train/eng_Latn-car_Latn.jsonl.gz split: train - path: test/eng_Latn-car_Latn.jsonl.gz split: test - path: validation/eng_Latn-car_Latn.jsonl.gz split: validation - config_name: eng_Latn-chz_Latn data_files: - path: train/eng_Latn-chz_Latn.jsonl.gz split: train - path: test/eng_Latn-chz_Latn.jsonl.gz split: test - path: validation/eng_Latn-chz_Latn.jsonl.gz split: validation - config_name: eng_Latn-ubr_Latn data_files: - path: train/eng_Latn-ubr_Latn.jsonl.gz split: train - path: test/eng_Latn-ubr_Latn.jsonl.gz split: test - path: validation/eng_Latn-ubr_Latn.jsonl.gz split: validation - config_name: eng_Latn-mar_Deva data_files: - path: train/eng_Latn-mar_Deva.jsonl.gz split: train - path: test/eng_Latn-mar_Deva.jsonl.gz split: test - path: validation/eng_Latn-mar_Deva.jsonl.gz split: validation - config_name: eng_Latn-gun_Latn data_files: - path: train/eng_Latn-gun_Latn.jsonl.gz split: train - path: test/eng_Latn-gun_Latn.jsonl.gz split: test - path: validation/eng_Latn-gun_Latn.jsonl.gz split: validation - config_name: eng_Latn-pir_Latn data_files: - path: train/eng_Latn-pir_Latn.jsonl.gz split: train - path: test/eng_Latn-pir_Latn.jsonl.gz split: test - path: validation/eng_Latn-pir_Latn.jsonl.gz split: validation - config_name: eng_Latn-inb_Latn data_files: - path: train/eng_Latn-inb_Latn.jsonl.gz split: train - path: test/eng_Latn-inb_Latn.jsonl.gz split: test - path: validation/eng_Latn-inb_Latn.jsonl.gz split: validation - config_name: eng_Latn-gym_Latn data_files: - path: train/eng_Latn-gym_Latn.jsonl.gz split: train - path: test/eng_Latn-gym_Latn.jsonl.gz split: test - path: validation/eng_Latn-gym_Latn.jsonl.gz split: validation - config_name: eng_Latn-mit_Latn data_files: - path: train/eng_Latn-mit_Latn.jsonl.gz split: train - path: test/eng_Latn-mit_Latn.jsonl.gz split: test - path: validation/eng_Latn-mit_Latn.jsonl.gz split: validation - config_name: eng_Latn-enq_Latn data_files: - path: train/eng_Latn-enq_Latn.jsonl.gz split: train - path: test/eng_Latn-enq_Latn.jsonl.gz split: test - path: validation/eng_Latn-enq_Latn.jsonl.gz split: validation - config_name: eng_Latn-kqf_Latn data_files: - path: train/eng_Latn-kqf_Latn.jsonl.gz split: train - path: test/eng_Latn-kqf_Latn.jsonl.gz split: test - path: validation/eng_Latn-kqf_Latn.jsonl.gz split: validation - config_name: eng_Latn-mbh_Latn data_files: - path: train/eng_Latn-mbh_Latn.jsonl.gz split: train - path: test/eng_Latn-mbh_Latn.jsonl.gz split: test - path: validation/eng_Latn-mbh_Latn.jsonl.gz split: validation - config_name: eng_Latn-xbi_Latn data_files: - path: train/eng_Latn-xbi_Latn.jsonl.gz split: train - path: test/eng_Latn-xbi_Latn.jsonl.gz split: test - path: validation/eng_Latn-xbi_Latn.jsonl.gz split: validation - config_name: eng_Latn-gof_Latn data_files: - path: train/eng_Latn-gof_Latn.jsonl.gz split: train - path: test/eng_Latn-gof_Latn.jsonl.gz split: test - path: validation/eng_Latn-gof_Latn.jsonl.gz split: validation - config_name: eng_Latn-lat_Latn data_files: - path: train/eng_Latn-lat_Latn.jsonl.gz split: train - path: test/eng_Latn-lat_Latn.jsonl.gz split: test - path: validation/eng_Latn-lat_Latn.jsonl.gz split: validation - config_name: eng_Latn-gah_Latn data_files: - path: train/eng_Latn-gah_Latn.jsonl.gz split: train - path: test/eng_Latn-gah_Latn.jsonl.gz split: test - path: validation/eng_Latn-gah_Latn.jsonl.gz split: validation - config_name: eng_Latn-zav_Latn data_files: - path: train/eng_Latn-zav_Latn.jsonl.gz split: train - path: test/eng_Latn-zav_Latn.jsonl.gz split: test - path: validation/eng_Latn-zav_Latn.jsonl.gz split: validation - config_name: eng_Latn-tnc_Latn data_files: - path: train/eng_Latn-tnc_Latn.jsonl.gz split: train - path: test/eng_Latn-tnc_Latn.jsonl.gz split: test - path: validation/eng_Latn-tnc_Latn.jsonl.gz split: validation - config_name: eng_Latn-aso_Latn data_files: - path: train/eng_Latn-aso_Latn.jsonl.gz split: train - path: test/eng_Latn-aso_Latn.jsonl.gz split: test - path: validation/eng_Latn-aso_Latn.jsonl.gz split: validation - config_name: eng_Latn-cax_Latn data_files: - path: train/eng_Latn-cax_Latn.jsonl.gz split: train - path: test/eng_Latn-cax_Latn.jsonl.gz split: test - path: validation/eng_Latn-cax_Latn.jsonl.gz split: validation - config_name: eng_Latn-xtm_Latn data_files: - path: train/eng_Latn-xtm_Latn.jsonl.gz split: train - path: test/eng_Latn-xtm_Latn.jsonl.gz split: test - path: validation/eng_Latn-xtm_Latn.jsonl.gz split: validation - config_name: eng_Latn-llg_Latn data_files: - path: train/eng_Latn-llg_Latn.jsonl.gz split: train - path: test/eng_Latn-llg_Latn.jsonl.gz split: test - path: validation/eng_Latn-llg_Latn.jsonl.gz split: validation - config_name: eng_Latn-pls_Latn data_files: - path: train/eng_Latn-pls_Latn.jsonl.gz split: train - path: test/eng_Latn-pls_Latn.jsonl.gz split: test - path: validation/eng_Latn-pls_Latn.jsonl.gz split: validation - config_name: eng_Latn-nhi_Latn data_files: - path: train/eng_Latn-nhi_Latn.jsonl.gz split: train - path: test/eng_Latn-nhi_Latn.jsonl.gz split: test - path: validation/eng_Latn-nhi_Latn.jsonl.gz split: validation - config_name: eng_Latn-leu_Latn data_files: - path: train/eng_Latn-leu_Latn.jsonl.gz split: train - path: test/eng_Latn-leu_Latn.jsonl.gz split: test - path: validation/eng_Latn-leu_Latn.jsonl.gz split: validation - config_name: eng_Latn-agn_Latn data_files: - path: train/eng_Latn-agn_Latn.jsonl.gz split: train - path: test/eng_Latn-agn_Latn.jsonl.gz split: test - path: validation/eng_Latn-agn_Latn.jsonl.gz split: validation - config_name: eng_Latn-hus_Latn data_files: - path: train/eng_Latn-hus_Latn.jsonl.gz split: train - path: test/eng_Latn-hus_Latn.jsonl.gz split: test - path: validation/eng_Latn-hus_Latn.jsonl.gz split: validation - config_name: eng_Latn-hvn_Latn data_files: - path: train/eng_Latn-hvn_Latn.jsonl.gz split: train - path: test/eng_Latn-hvn_Latn.jsonl.gz split: test - path: validation/eng_Latn-hvn_Latn.jsonl.gz split: validation - config_name: eng_Latn-gup_Latn data_files: - path: train/eng_Latn-gup_Latn.jsonl.gz split: train - path: test/eng_Latn-gup_Latn.jsonl.gz split: test - path: validation/eng_Latn-gup_Latn.jsonl.gz split: validation - config_name: eng_Latn-ncu_Latn data_files: - path: train/eng_Latn-ncu_Latn.jsonl.gz split: train - path: test/eng_Latn-ncu_Latn.jsonl.gz split: test - path: validation/eng_Latn-ncu_Latn.jsonl.gz split: validation - config_name: eng_Latn-ilo_Latn data_files: - path: train/eng_Latn-ilo_Latn.jsonl.gz split: train - path: test/eng_Latn-ilo_Latn.jsonl.gz split: test - path: validation/eng_Latn-ilo_Latn.jsonl.gz split: validation - config_name: eng_Latn-cjv_Latn data_files: - path: train/eng_Latn-cjv_Latn.jsonl.gz split: train - path: test/eng_Latn-cjv_Latn.jsonl.gz split: test - path: validation/eng_Latn-cjv_Latn.jsonl.gz split: validation - config_name: eng_Latn-cbi_Latn data_files: - path: train/eng_Latn-cbi_Latn.jsonl.gz split: train - path: test/eng_Latn-cbi_Latn.jsonl.gz split: test - path: validation/eng_Latn-cbi_Latn.jsonl.gz split: validation - config_name: eng_Latn-sll_Latn data_files: - path: train/eng_Latn-sll_Latn.jsonl.gz split: train - path: test/eng_Latn-sll_Latn.jsonl.gz split: test - path: validation/eng_Latn-sll_Latn.jsonl.gz split: validation - config_name: eng_Latn-gvf_Latn data_files: - path: train/eng_Latn-gvf_Latn.jsonl.gz split: train - path: test/eng_Latn-gvf_Latn.jsonl.gz split: test - path: validation/eng_Latn-gvf_Latn.jsonl.gz split: validation - config_name: eng_Latn-cbk_Latn data_files: - path: train/eng_Latn-cbk_Latn.jsonl.gz split: train - path: test/eng_Latn-cbk_Latn.jsonl.gz split: test - path: validation/eng_Latn-cbk_Latn.jsonl.gz split: validation - config_name: eng_Latn-ctp_Latn data_files: - path: train/eng_Latn-ctp_Latn.jsonl.gz split: train - path: test/eng_Latn-ctp_Latn.jsonl.gz split: test - path: validation/eng_Latn-ctp_Latn.jsonl.gz split: validation - config_name: eng_Latn-rus_Cyrl data_files: - path: train/eng_Latn-rus_Cyrl.jsonl.gz split: train - path: test/eng_Latn-rus_Cyrl.jsonl.gz split: test - path: validation/eng_Latn-rus_Cyrl.jsonl.gz split: validation - config_name: eng_Latn-zpc_Latn data_files: - path: train/eng_Latn-zpc_Latn.jsonl.gz split: train - path: test/eng_Latn-zpc_Latn.jsonl.gz split: test - path: validation/eng_Latn-zpc_Latn.jsonl.gz split: validation - config_name: eng_Latn-dww_Latn data_files: - path: train/eng_Latn-dww_Latn.jsonl.gz split: train - path: test/eng_Latn-dww_Latn.jsonl.gz split: test - path: validation/eng_Latn-dww_Latn.jsonl.gz split: validation - config_name: eng_Latn-haw_Latn data_files: - path: train/eng_Latn-haw_Latn.jsonl.gz split: train - path: test/eng_Latn-haw_Latn.jsonl.gz split: test - path: validation/eng_Latn-haw_Latn.jsonl.gz split: validation - config_name: eng_Latn-hrv_Latn data_files: - path: train/eng_Latn-hrv_Latn.jsonl.gz split: train - path: test/eng_Latn-hrv_Latn.jsonl.gz split: test - path: validation/eng_Latn-hrv_Latn.jsonl.gz split: validation - config_name: eng_Latn-bhg_Latn data_files: - path: train/eng_Latn-bhg_Latn.jsonl.gz split: train - path: test/eng_Latn-bhg_Latn.jsonl.gz split: test - path: validation/eng_Latn-bhg_Latn.jsonl.gz split: validation - config_name: eng_Latn-kyg_Latn data_files: - path: train/eng_Latn-kyg_Latn.jsonl.gz split: train - path: test/eng_Latn-kyg_Latn.jsonl.gz split: test - path: validation/eng_Latn-kyg_Latn.jsonl.gz split: validation - config_name: eng_Latn-are_Latn data_files: - path: train/eng_Latn-are_Latn.jsonl.gz split: train - path: test/eng_Latn-are_Latn.jsonl.gz split: test - path: validation/eng_Latn-are_Latn.jsonl.gz split: validation - config_name: eng_Latn-pma_Latn data_files: - path: train/eng_Latn-pma_Latn.jsonl.gz split: train - path: test/eng_Latn-pma_Latn.jsonl.gz split: test - path: validation/eng_Latn-pma_Latn.jsonl.gz split: validation - config_name: eng_Latn-tcz_Latn data_files: - path: train/eng_Latn-tcz_Latn.jsonl.gz split: train - path: test/eng_Latn-tcz_Latn.jsonl.gz split: test - path: validation/eng_Latn-tcz_Latn.jsonl.gz split: validation - config_name: eng_Latn-mop_Latn data_files: - path: train/eng_Latn-mop_Latn.jsonl.gz split: train - path: test/eng_Latn-mop_Latn.jsonl.gz split: test - path: validation/eng_Latn-mop_Latn.jsonl.gz split: validation - config_name: eng_Latn-maa_Latn data_files: - path: train/eng_Latn-maa_Latn.jsonl.gz split: train - path: test/eng_Latn-maa_Latn.jsonl.gz split: test - path: validation/eng_Latn-maa_Latn.jsonl.gz split: validation - config_name: eng_Latn-row_Latn data_files: - path: train/eng_Latn-row_Latn.jsonl.gz split: train - path: test/eng_Latn-row_Latn.jsonl.gz split: test - path: validation/eng_Latn-row_Latn.jsonl.gz split: validation - config_name: eng_Latn-mcp_Latn data_files: - path: train/eng_Latn-mcp_Latn.jsonl.gz split: train - path: test/eng_Latn-mcp_Latn.jsonl.gz split: test - path: validation/eng_Latn-mcp_Latn.jsonl.gz split: validation - config_name: eng_Latn-bjv_Latn data_files: - path: train/eng_Latn-bjv_Latn.jsonl.gz split: train - path: test/eng_Latn-bjv_Latn.jsonl.gz split: test - path: validation/eng_Latn-bjv_Latn.jsonl.gz split: validation - config_name: eng_Latn-dan_Latn data_files: - path: train/eng_Latn-dan_Latn.jsonl.gz split: train - path: test/eng_Latn-dan_Latn.jsonl.gz split: test - path: validation/eng_Latn-dan_Latn.jsonl.gz split: validation - config_name: eng_Latn-kpw_Latn data_files: - path: train/eng_Latn-kpw_Latn.jsonl.gz split: train - path: test/eng_Latn-kpw_Latn.jsonl.gz split: test - path: validation/eng_Latn-kpw_Latn.jsonl.gz split: validation - config_name: eng_Latn-yal_Latn data_files: - path: train/eng_Latn-yal_Latn.jsonl.gz split: train - path: test/eng_Latn-yal_Latn.jsonl.gz split: test - path: validation/eng_Latn-yal_Latn.jsonl.gz split: validation - config_name: eng_Latn-yrb_Latn data_files: - path: train/eng_Latn-yrb_Latn.jsonl.gz split: train - path: test/eng_Latn-yrb_Latn.jsonl.gz split: test - path: validation/eng_Latn-yrb_Latn.jsonl.gz split: validation - config_name: eng_Latn-piu_Latn data_files: - path: train/eng_Latn-piu_Latn.jsonl.gz split: train - path: test/eng_Latn-piu_Latn.jsonl.gz split: test - path: validation/eng_Latn-piu_Latn.jsonl.gz split: validation - config_name: eng_Latn-kqa_Latn data_files: - path: train/eng_Latn-kqa_Latn.jsonl.gz split: train - path: test/eng_Latn-kqa_Latn.jsonl.gz split: test - path: validation/eng_Latn-kqa_Latn.jsonl.gz split: validation - config_name: eng_Latn-buk_Latn data_files: - path: train/eng_Latn-buk_Latn.jsonl.gz split: train - path: test/eng_Latn-buk_Latn.jsonl.gz split: test - path: validation/eng_Latn-buk_Latn.jsonl.gz split: validation - config_name: eng_Latn-taw_Latn data_files: - path: train/eng_Latn-taw_Latn.jsonl.gz split: train - path: test/eng_Latn-taw_Latn.jsonl.gz split: test - path: validation/eng_Latn-taw_Latn.jsonl.gz split: validation - config_name: eng_Latn-bzj_Latn data_files: - path: train/eng_Latn-bzj_Latn.jsonl.gz split: train - path: test/eng_Latn-bzj_Latn.jsonl.gz split: test - path: validation/eng_Latn-bzj_Latn.jsonl.gz split: validation - config_name: eng_Latn-boa_Latn data_files: - path: train/eng_Latn-boa_Latn.jsonl.gz split: train - path: test/eng_Latn-boa_Latn.jsonl.gz split: test - path: validation/eng_Latn-boa_Latn.jsonl.gz split: validation - config_name: eng_Latn-sua_Latn data_files: - path: train/eng_Latn-sua_Latn.jsonl.gz split: train - path: test/eng_Latn-sua_Latn.jsonl.gz split: test - path: validation/eng_Latn-sua_Latn.jsonl.gz split: validation - config_name: eng_Latn-mwf_Latn data_files: - path: train/eng_Latn-mwf_Latn.jsonl.gz split: train - path: test/eng_Latn-mwf_Latn.jsonl.gz split: test - path: validation/eng_Latn-mwf_Latn.jsonl.gz split: validation - config_name: eng_Latn-deu_Latn data_files: - path: train/eng_Latn-deu_Latn.jsonl.gz split: train - path: test/eng_Latn-deu_Latn.jsonl.gz split: test - path: validation/eng_Latn-deu_Latn.jsonl.gz split: validation - config_name: eng_Latn-ura_Latn data_files: - path: train/eng_Latn-ura_Latn.jsonl.gz split: train - path: test/eng_Latn-ura_Latn.jsonl.gz split: test - path: validation/eng_Latn-ura_Latn.jsonl.gz split: validation - config_name: eng_Latn-aui_Latn data_files: - path: train/eng_Latn-aui_Latn.jsonl.gz split: train - path: test/eng_Latn-aui_Latn.jsonl.gz split: test - path: validation/eng_Latn-aui_Latn.jsonl.gz split: validation - config_name: eng_Latn-wim_Latn data_files: - path: train/eng_Latn-wim_Latn.jsonl.gz split: train - path: test/eng_Latn-wim_Latn.jsonl.gz split: test - path: validation/eng_Latn-wim_Latn.jsonl.gz split: validation - config_name: eng_Latn-bzh_Latn data_files: - path: train/eng_Latn-bzh_Latn.jsonl.gz split: train - path: test/eng_Latn-bzh_Latn.jsonl.gz split: test - path: validation/eng_Latn-bzh_Latn.jsonl.gz split: validation - config_name: eng_Latn-nld_Latn data_files: - path: train/eng_Latn-nld_Latn.jsonl.gz split: train - path: test/eng_Latn-nld_Latn.jsonl.gz split: test - path: validation/eng_Latn-nld_Latn.jsonl.gz split: validation - config_name: eng_Latn-ory_Orya data_files: - path: train/eng_Latn-ory_Orya.jsonl.gz split: train - path: test/eng_Latn-ory_Orya.jsonl.gz split: test - path: validation/eng_Latn-ory_Orya.jsonl.gz split: validation - config_name: eng_Latn-ppo_Latn data_files: - path: train/eng_Latn-ppo_Latn.jsonl.gz split: train - path: test/eng_Latn-ppo_Latn.jsonl.gz split: test - path: validation/eng_Latn-ppo_Latn.jsonl.gz split: validation - config_name: eng_Latn-epo_Latn data_files: - path: train/eng_Latn-epo_Latn.jsonl.gz split: train - path: test/eng_Latn-epo_Latn.jsonl.gz split: test - path: validation/eng_Latn-epo_Latn.jsonl.gz split: validation - config_name: eng_Latn-hop_Latn data_files: - path: train/eng_Latn-hop_Latn.jsonl.gz split: train - path: test/eng_Latn-hop_Latn.jsonl.gz split: test - path: validation/eng_Latn-hop_Latn.jsonl.gz split: validation - config_name: eng_Latn-gdn_Latn data_files: - path: train/eng_Latn-gdn_Latn.jsonl.gz split: train - path: test/eng_Latn-gdn_Latn.jsonl.gz split: test - path: validation/eng_Latn-gdn_Latn.jsonl.gz split: validation - config_name: eng_Latn-tlf_Latn data_files: - path: train/eng_Latn-tlf_Latn.jsonl.gz split: train - path: test/eng_Latn-tlf_Latn.jsonl.gz split: test - path: validation/eng_Latn-tlf_Latn.jsonl.gz split: validation - config_name: eng_Latn-tiw_Latn data_files: - path: train/eng_Latn-tiw_Latn.jsonl.gz split: train - path: test/eng_Latn-tiw_Latn.jsonl.gz split: test - path: validation/eng_Latn-tiw_Latn.jsonl.gz split: validation - config_name: eng_Latn-sja_Latn data_files: - path: train/eng_Latn-sja_Latn.jsonl.gz split: train - path: test/eng_Latn-sja_Latn.jsonl.gz split: test - path: validation/eng_Latn-sja_Latn.jsonl.gz split: validation - config_name: eng_Latn-kdl_Latn data_files: - path: train/eng_Latn-kdl_Latn.jsonl.gz split: train - path: test/eng_Latn-kdl_Latn.jsonl.gz split: test - path: validation/eng_Latn-kdl_Latn.jsonl.gz split: validation - config_name: eng_Latn-chk_Latn data_files: - path: train/eng_Latn-chk_Latn.jsonl.gz split: train - path: test/eng_Latn-chk_Latn.jsonl.gz split: test - path: validation/eng_Latn-chk_Latn.jsonl.gz split: validation - config_name: eng_Latn-kdc_Latn data_files: - path: train/eng_Latn-kdc_Latn.jsonl.gz split: train - path: test/eng_Latn-kdc_Latn.jsonl.gz split: test - path: validation/eng_Latn-kdc_Latn.jsonl.gz split: validation - config_name: eng_Latn-gng_Latn data_files: - path: train/eng_Latn-gng_Latn.jsonl.gz split: train - path: test/eng_Latn-gng_Latn.jsonl.gz split: test - path: validation/eng_Latn-gng_Latn.jsonl.gz split: validation - config_name: eng_Latn-nko_Latn data_files: - path: train/eng_Latn-nko_Latn.jsonl.gz split: train - path: test/eng_Latn-nko_Latn.jsonl.gz split: test - path: validation/eng_Latn-nko_Latn.jsonl.gz split: validation - config_name: eng_Latn-wer_Latn data_files: - path: train/eng_Latn-wer_Latn.jsonl.gz split: train - path: test/eng_Latn-wer_Latn.jsonl.gz split: test - path: validation/eng_Latn-wer_Latn.jsonl.gz split: validation - config_name: eng_Latn-mhl_Latn data_files: - path: train/eng_Latn-mhl_Latn.jsonl.gz split: train - path: test/eng_Latn-mhl_Latn.jsonl.gz split: test - path: validation/eng_Latn-mhl_Latn.jsonl.gz split: validation - config_name: eng_Latn-toc_Latn data_files: - path: train/eng_Latn-toc_Latn.jsonl.gz split: train - path: test/eng_Latn-toc_Latn.jsonl.gz split: test - path: validation/eng_Latn-toc_Latn.jsonl.gz split: validation - config_name: eng_Latn-cbs_Latn data_files: - path: train/eng_Latn-cbs_Latn.jsonl.gz split: train - path: test/eng_Latn-cbs_Latn.jsonl.gz split: test - path: validation/eng_Latn-cbs_Latn.jsonl.gz split: validation - config_name: eng_Latn-qub_Latn data_files: - path: train/eng_Latn-qub_Latn.jsonl.gz split: train - path: test/eng_Latn-qub_Latn.jsonl.gz split: test - path: validation/eng_Latn-qub_Latn.jsonl.gz split: validation - config_name: eng_Latn-auc_Latn data_files: - path: train/eng_Latn-auc_Latn.jsonl.gz split: train - path: test/eng_Latn-auc_Latn.jsonl.gz split: test - path: validation/eng_Latn-auc_Latn.jsonl.gz split: validation - config_name: eng_Latn-kpr_Latn data_files: - path: train/eng_Latn-kpr_Latn.jsonl.gz split: train - path: test/eng_Latn-kpr_Latn.jsonl.gz split: test - path: validation/eng_Latn-kpr_Latn.jsonl.gz split: validation - config_name: eng_Latn-hat_Latn data_files: - path: train/eng_Latn-hat_Latn.jsonl.gz split: train - path: test/eng_Latn-hat_Latn.jsonl.gz split: test - path: validation/eng_Latn-hat_Latn.jsonl.gz split: validation - config_name: eng_Latn-sny_Latn data_files: - path: train/eng_Latn-sny_Latn.jsonl.gz split: train - path: test/eng_Latn-sny_Latn.jsonl.gz split: test - path: validation/eng_Latn-sny_Latn.jsonl.gz split: validation - config_name: eng_Latn-byr_Latn data_files: - path: train/eng_Latn-byr_Latn.jsonl.gz split: train - path: test/eng_Latn-byr_Latn.jsonl.gz split: test - path: validation/eng_Latn-byr_Latn.jsonl.gz split: validation - config_name: eng_Latn-emp_Latn data_files: - path: train/eng_Latn-emp_Latn.jsonl.gz split: train - path: test/eng_Latn-emp_Latn.jsonl.gz split: test - path: validation/eng_Latn-emp_Latn.jsonl.gz split: validation - config_name: eng_Latn-kwi_Latn data_files: - path: train/eng_Latn-kwi_Latn.jsonl.gz split: train - path: test/eng_Latn-kwi_Latn.jsonl.gz split: test - path: validation/eng_Latn-kwi_Latn.jsonl.gz split: validation - config_name: eng_Latn-gum_Latn data_files: - path: train/eng_Latn-gum_Latn.jsonl.gz split: train - path: test/eng_Latn-gum_Latn.jsonl.gz split: test - path: validation/eng_Latn-gum_Latn.jsonl.gz split: validation - config_name: eng_Latn-mbj_Latn data_files: - path: train/eng_Latn-mbj_Latn.jsonl.gz split: train - path: test/eng_Latn-mbj_Latn.jsonl.gz split: test - path: validation/eng_Latn-mbj_Latn.jsonl.gz split: validation - config_name: eng_Latn-sey_Latn data_files: - path: train/eng_Latn-sey_Latn.jsonl.gz split: train - path: test/eng_Latn-sey_Latn.jsonl.gz split: test - path: validation/eng_Latn-sey_Latn.jsonl.gz split: validation - config_name: eng_Latn-alp_Latn data_files: - path: train/eng_Latn-alp_Latn.jsonl.gz split: train - path: test/eng_Latn-alp_Latn.jsonl.gz split: test - path: validation/eng_Latn-alp_Latn.jsonl.gz split: validation - config_name: eng_Latn-gmv_Latn data_files: - path: train/eng_Latn-gmv_Latn.jsonl.gz split: train - path: test/eng_Latn-gmv_Latn.jsonl.gz split: test - path: validation/eng_Latn-gmv_Latn.jsonl.gz split: validation - config_name: eng_Latn-poe_Latn data_files: - path: train/eng_Latn-poe_Latn.jsonl.gz split: train - path: test/eng_Latn-poe_Latn.jsonl.gz split: test - path: validation/eng_Latn-poe_Latn.jsonl.gz split: validation - config_name: eng_Latn-etr_Latn data_files: - path: train/eng_Latn-etr_Latn.jsonl.gz split: train - path: test/eng_Latn-etr_Latn.jsonl.gz split: test - path: validation/eng_Latn-etr_Latn.jsonl.gz split: validation - config_name: eng_Latn-abt_Latn data_files: - path: train/eng_Latn-abt_Latn.jsonl.gz split: train - path: test/eng_Latn-abt_Latn.jsonl.gz split: test - path: validation/eng_Latn-abt_Latn.jsonl.gz split: validation - config_name: eng_Latn-tuf_Latn data_files: - path: train/eng_Latn-tuf_Latn.jsonl.gz split: train - path: test/eng_Latn-tuf_Latn.jsonl.gz split: test - path: validation/eng_Latn-tuf_Latn.jsonl.gz split: validation - config_name: eng_Latn-dob_Latn data_files: - path: train/eng_Latn-dob_Latn.jsonl.gz split: train - path: test/eng_Latn-dob_Latn.jsonl.gz split: test - path: validation/eng_Latn-dob_Latn.jsonl.gz split: validation - config_name: eng_Latn-nys_Latn data_files: - path: train/eng_Latn-nys_Latn.jsonl.gz split: train - path: test/eng_Latn-nys_Latn.jsonl.gz split: test - path: validation/eng_Latn-nys_Latn.jsonl.gz split: validation - config_name: eng_Latn-srn_Latn data_files: - path: train/eng_Latn-srn_Latn.jsonl.gz split: train - path: test/eng_Latn-srn_Latn.jsonl.gz split: test - path: validation/eng_Latn-srn_Latn.jsonl.gz split: validation - config_name: eng_Latn-kpf_Latn data_files: - path: train/eng_Latn-kpf_Latn.jsonl.gz split: train - path: test/eng_Latn-kpf_Latn.jsonl.gz split: test - path: validation/eng_Latn-kpf_Latn.jsonl.gz split: validation - config_name: eng_Latn-mbt_Latn data_files: - path: train/eng_Latn-mbt_Latn.jsonl.gz split: train - path: test/eng_Latn-mbt_Latn.jsonl.gz split: test - path: validation/eng_Latn-mbt_Latn.jsonl.gz split: validation - config_name: eng_Latn-stp_Latn data_files: - path: train/eng_Latn-stp_Latn.jsonl.gz split: train - path: test/eng_Latn-stp_Latn.jsonl.gz split: test - path: validation/eng_Latn-stp_Latn.jsonl.gz split: validation - config_name: eng_Latn-trc_Latn data_files: - path: train/eng_Latn-trc_Latn.jsonl.gz split: train - path: test/eng_Latn-trc_Latn.jsonl.gz split: test - path: validation/eng_Latn-trc_Latn.jsonl.gz split: validation - config_name: eng_Latn-for_Latn data_files: - path: train/eng_Latn-for_Latn.jsonl.gz split: train - path: test/eng_Latn-for_Latn.jsonl.gz split: test - path: validation/eng_Latn-for_Latn.jsonl.gz split: validation - config_name: eng_Latn-yad_Latn data_files: - path: train/eng_Latn-yad_Latn.jsonl.gz split: train - path: test/eng_Latn-yad_Latn.jsonl.gz split: test - path: validation/eng_Latn-yad_Latn.jsonl.gz split: validation - config_name: eng_Latn-cme_Latn data_files: - path: train/eng_Latn-cme_Latn.jsonl.gz split: train - path: test/eng_Latn-cme_Latn.jsonl.gz split: test - path: validation/eng_Latn-cme_Latn.jsonl.gz split: validation - config_name: eng_Latn-bba_Latn data_files: - path: train/eng_Latn-bba_Latn.jsonl.gz split: train - path: test/eng_Latn-bba_Latn.jsonl.gz split: test - path: validation/eng_Latn-bba_Latn.jsonl.gz split: validation - config_name: eng_Latn-mxq_Latn data_files: - path: train/eng_Latn-mxq_Latn.jsonl.gz split: train - path: test/eng_Latn-mxq_Latn.jsonl.gz split: test - path: validation/eng_Latn-mxq_Latn.jsonl.gz split: validation - config_name: eng_Latn-dwy_Latn data_files: - path: train/eng_Latn-dwy_Latn.jsonl.gz split: train - path: test/eng_Latn-dwy_Latn.jsonl.gz split: test - path: validation/eng_Latn-dwy_Latn.jsonl.gz split: validation - config_name: eng_Latn-atg_Latn data_files: - path: train/eng_Latn-atg_Latn.jsonl.gz split: train - path: test/eng_Latn-atg_Latn.jsonl.gz split: test - path: validation/eng_Latn-atg_Latn.jsonl.gz split: validation - config_name: eng_Latn-ncj_Latn data_files: - path: train/eng_Latn-ncj_Latn.jsonl.gz split: train - path: test/eng_Latn-ncj_Latn.jsonl.gz split: test - path: validation/eng_Latn-ncj_Latn.jsonl.gz split: validation - config_name: eng_Latn-mpm_Latn data_files: - path: train/eng_Latn-mpm_Latn.jsonl.gz split: train - path: test/eng_Latn-mpm_Latn.jsonl.gz split: test - path: validation/eng_Latn-mpm_Latn.jsonl.gz split: validation - config_name: eng_Latn-kqc_Latn data_files: - path: train/eng_Latn-kqc_Latn.jsonl.gz split: train - path: test/eng_Latn-kqc_Latn.jsonl.gz split: test - path: validation/eng_Latn-kqc_Latn.jsonl.gz split: validation - config_name: eng_Latn-knv_Latn data_files: - path: train/eng_Latn-knv_Latn.jsonl.gz split: train - path: test/eng_Latn-knv_Latn.jsonl.gz split: test - path: validation/eng_Latn-knv_Latn.jsonl.gz split: validation - config_name: eng_Latn-upv_Latn data_files: - path: train/eng_Latn-upv_Latn.jsonl.gz split: train - path: test/eng_Latn-upv_Latn.jsonl.gz split: test - path: validation/eng_Latn-upv_Latn.jsonl.gz split: validation - config_name: eng_Latn-yut_Latn data_files: - path: train/eng_Latn-yut_Latn.jsonl.gz split: train - path: test/eng_Latn-yut_Latn.jsonl.gz split: test - path: validation/eng_Latn-yut_Latn.jsonl.gz split: validation - config_name: eng_Latn-kje_Latn data_files: - path: train/eng_Latn-kje_Latn.jsonl.gz split: train - path: test/eng_Latn-kje_Latn.jsonl.gz split: test - path: validation/eng_Latn-kje_Latn.jsonl.gz split: validation - config_name: eng_Latn-okv_Latn data_files: - path: train/eng_Latn-okv_Latn.jsonl.gz split: train - path: test/eng_Latn-okv_Latn.jsonl.gz split: test - path: validation/eng_Latn-okv_Latn.jsonl.gz split: validation - config_name: eng_Latn-tof_Latn data_files: - path: train/eng_Latn-tof_Latn.jsonl.gz split: train - path: test/eng_Latn-tof_Latn.jsonl.gz split: test - path: validation/eng_Latn-tof_Latn.jsonl.gz split: validation - config_name: eng_Latn-faa_Latn data_files: - path: train/eng_Latn-faa_Latn.jsonl.gz split: train - path: test/eng_Latn-faa_Latn.jsonl.gz split: test - path: validation/eng_Latn-faa_Latn.jsonl.gz split: validation - config_name: eng_Latn-mya_Latn data_files: - path: train/eng_Latn-mya_Latn.jsonl.gz split: train - path: test/eng_Latn-mya_Latn.jsonl.gz split: test - path: validation/eng_Latn-mya_Latn.jsonl.gz split: validation - config_name: eng_Latn-hto_Latn data_files: - path: train/eng_Latn-hto_Latn.jsonl.gz split: train - path: test/eng_Latn-hto_Latn.jsonl.gz split: test - path: validation/eng_Latn-hto_Latn.jsonl.gz split: validation - config_name: eng_Latn-wiv_Latn data_files: - path: train/eng_Latn-wiv_Latn.jsonl.gz split: train - path: test/eng_Latn-wiv_Latn.jsonl.gz split: test - path: validation/eng_Latn-wiv_Latn.jsonl.gz split: validation - config_name: eng_Latn-vid_Latn data_files: - path: train/eng_Latn-vid_Latn.jsonl.gz split: train - path: test/eng_Latn-vid_Latn.jsonl.gz split: test - path: validation/eng_Latn-vid_Latn.jsonl.gz split: validation - config_name: eng_Latn-xla_Latn data_files: - path: train/eng_Latn-xla_Latn.jsonl.gz split: train - path: test/eng_Latn-xla_Latn.jsonl.gz split: test - path: validation/eng_Latn-xla_Latn.jsonl.gz split: validation - config_name: eng_Latn-snn_Latn data_files: - path: train/eng_Latn-snn_Latn.jsonl.gz split: train - path: test/eng_Latn-snn_Latn.jsonl.gz split: test - path: validation/eng_Latn-snn_Latn.jsonl.gz split: validation - config_name: eng_Latn-ycn_Latn data_files: - path: train/eng_Latn-ycn_Latn.jsonl.gz split: train - path: test/eng_Latn-ycn_Latn.jsonl.gz split: test - path: validation/eng_Latn-ycn_Latn.jsonl.gz split: validation - config_name: eng_Latn-mcb_Latn data_files: - path: train/eng_Latn-mcb_Latn.jsonl.gz split: train - path: test/eng_Latn-mcb_Latn.jsonl.gz split: test - path: validation/eng_Latn-mcb_Latn.jsonl.gz split: validation - config_name: eng_Latn-mal_Mlym data_files: - path: train/eng_Latn-mal_Mlym.jsonl.gz split: train - path: test/eng_Latn-mal_Mlym.jsonl.gz split: test - path: validation/eng_Latn-mal_Mlym.jsonl.gz split: validation - config_name: eng_Latn-sgb_Latn data_files: - path: train/eng_Latn-sgb_Latn.jsonl.gz split: train - path: test/eng_Latn-sgb_Latn.jsonl.gz split: test - path: validation/eng_Latn-sgb_Latn.jsonl.gz split: validation - config_name: eng_Latn-box_Latn data_files: - path: train/eng_Latn-box_Latn.jsonl.gz split: train - path: test/eng_Latn-box_Latn.jsonl.gz split: test - path: validation/eng_Latn-box_Latn.jsonl.gz split: validation - config_name: eng_Latn-amu_Latn data_files: - path: train/eng_Latn-amu_Latn.jsonl.gz split: train - path: test/eng_Latn-amu_Latn.jsonl.gz split: test - path: validation/eng_Latn-amu_Latn.jsonl.gz split: validation - config_name: eng_Latn-cni_Latn data_files: - path: train/eng_Latn-cni_Latn.jsonl.gz split: train - path: test/eng_Latn-cni_Latn.jsonl.gz split: test - path: validation/eng_Latn-cni_Latn.jsonl.gz split: validation - config_name: eng_Latn-byx_Latn data_files: - path: train/eng_Latn-byx_Latn.jsonl.gz split: train - path: test/eng_Latn-byx_Latn.jsonl.gz split: test - path: validation/eng_Latn-byx_Latn.jsonl.gz split: validation - config_name: eng_Latn-udu_Latn data_files: - path: train/eng_Latn-udu_Latn.jsonl.gz split: train - path: test/eng_Latn-udu_Latn.jsonl.gz split: test - path: validation/eng_Latn-udu_Latn.jsonl.gz split: validation - config_name: eng_Latn-jid_Latn data_files: - path: train/eng_Latn-jid_Latn.jsonl.gz split: train - path: test/eng_Latn-jid_Latn.jsonl.gz split: test - path: validation/eng_Latn-jid_Latn.jsonl.gz split: validation - config_name: eng_Latn-nlg_Latn data_files: - path: train/eng_Latn-nlg_Latn.jsonl.gz split: train - path: test/eng_Latn-nlg_Latn.jsonl.gz split: test - path: validation/eng_Latn-nlg_Latn.jsonl.gz split: validation - config_name: eng_Latn-wuv_Latn data_files: - path: train/eng_Latn-wuv_Latn.jsonl.gz split: train - path: test/eng_Latn-wuv_Latn.jsonl.gz split: test - path: validation/eng_Latn-wuv_Latn.jsonl.gz split: validation - config_name: eng_Latn-mto_Latn data_files: - path: train/eng_Latn-mto_Latn.jsonl.gz split: train - path: test/eng_Latn-mto_Latn.jsonl.gz split: test - path: validation/eng_Latn-mto_Latn.jsonl.gz split: validation - config_name: eng_Latn-mcd_Latn data_files: - path: train/eng_Latn-mcd_Latn.jsonl.gz split: train - path: test/eng_Latn-mcd_Latn.jsonl.gz split: test - path: validation/eng_Latn-mcd_Latn.jsonl.gz split: validation - config_name: eng_Latn-bus_Latn data_files: - path: train/eng_Latn-bus_Latn.jsonl.gz split: train - path: test/eng_Latn-bus_Latn.jsonl.gz split: test - path: validation/eng_Latn-bus_Latn.jsonl.gz split: validation - config_name: eng_Latn-glk_Arab data_files: - path: train/eng_Latn-glk_Arab.jsonl.gz split: train - path: test/eng_Latn-glk_Arab.jsonl.gz split: test - path: validation/eng_Latn-glk_Arab.jsonl.gz split: validation - config_name: eng_Latn-too_Latn data_files: - path: train/eng_Latn-too_Latn.jsonl.gz split: train - path: test/eng_Latn-too_Latn.jsonl.gz split: test - path: validation/eng_Latn-too_Latn.jsonl.gz split: validation - config_name: eng_Latn-mpp_Latn data_files: - path: train/eng_Latn-mpp_Latn.jsonl.gz split: train - path: test/eng_Latn-mpp_Latn.jsonl.gz split: test - path: validation/eng_Latn-mpp_Latn.jsonl.gz split: validation - config_name: eng_Latn-zaj_Latn data_files: - path: train/eng_Latn-zaj_Latn.jsonl.gz split: train - path: test/eng_Latn-zaj_Latn.jsonl.gz split: test - path: validation/eng_Latn-zaj_Latn.jsonl.gz split: validation - config_name: eng_Latn-yva_Latn data_files: - path: train/eng_Latn-yva_Latn.jsonl.gz split: train - path: test/eng_Latn-yva_Latn.jsonl.gz split: test - path: validation/eng_Latn-yva_Latn.jsonl.gz split: validation - config_name: eng_Latn-awx_Latn data_files: - path: train/eng_Latn-awx_Latn.jsonl.gz split: train - path: test/eng_Latn-awx_Latn.jsonl.gz split: test - path: validation/eng_Latn-awx_Latn.jsonl.gz split: validation - config_name: eng_Latn-ian_Latn data_files: - path: train/eng_Latn-ian_Latn.jsonl.gz split: train - path: test/eng_Latn-ian_Latn.jsonl.gz split: test - path: validation/eng_Latn-ian_Latn.jsonl.gz split: validation - config_name: eng_Latn-otq_Latn data_files: - path: train/eng_Latn-otq_Latn.jsonl.gz split: train - path: test/eng_Latn-otq_Latn.jsonl.gz split: test - path: validation/eng_Latn-otq_Latn.jsonl.gz split: validation - config_name: eng_Latn-fra_Latn data_files: - path: train/eng_Latn-fra_Latn.jsonl.gz split: train - path: test/eng_Latn-fra_Latn.jsonl.gz split: test - path: validation/eng_Latn-fra_Latn.jsonl.gz split: validation - config_name: eng_Latn-zlm_Latn data_files: - path: train/eng_Latn-zlm_Latn.jsonl.gz split: train - path: test/eng_Latn-zlm_Latn.jsonl.gz split: test - path: validation/eng_Latn-zlm_Latn.jsonl.gz split: validation - config_name: eng_Latn-ptu_Latn data_files: - path: train/eng_Latn-ptu_Latn.jsonl.gz split: train - path: test/eng_Latn-ptu_Latn.jsonl.gz split: test - path: validation/eng_Latn-ptu_Latn.jsonl.gz split: validation - config_name: eng_Latn-apr_Latn data_files: - path: train/eng_Latn-apr_Latn.jsonl.gz split: train - path: test/eng_Latn-apr_Latn.jsonl.gz split: test - path: validation/eng_Latn-apr_Latn.jsonl.gz split: validation - config_name: eng_Latn-zab_Latn data_files: - path: train/eng_Latn-zab_Latn.jsonl.gz split: train - path: test/eng_Latn-zab_Latn.jsonl.gz split: test - path: validation/eng_Latn-zab_Latn.jsonl.gz split: validation - config_name: eng_Latn-kwf_Latn data_files: - path: train/eng_Latn-kwf_Latn.jsonl.gz split: train - path: test/eng_Latn-kwf_Latn.jsonl.gz split: test - path: validation/eng_Latn-kwf_Latn.jsonl.gz split: validation - config_name: eng_Latn-cya_Latn data_files: - path: train/eng_Latn-cya_Latn.jsonl.gz split: train - path: test/eng_Latn-cya_Latn.jsonl.gz split: test - path: validation/eng_Latn-cya_Latn.jsonl.gz split: validation - config_name: eng_Latn-nna_Latn data_files: - path: train/eng_Latn-nna_Latn.jsonl.gz split: train - path: test/eng_Latn-nna_Latn.jsonl.gz split: test - path: validation/eng_Latn-nna_Latn.jsonl.gz split: validation - config_name: eng_Latn-wnc_Latn data_files: - path: train/eng_Latn-wnc_Latn.jsonl.gz split: train - path: test/eng_Latn-wnc_Latn.jsonl.gz split: test - path: validation/eng_Latn-wnc_Latn.jsonl.gz split: validation - config_name: eng_Latn-dad_Latn data_files: - path: train/eng_Latn-dad_Latn.jsonl.gz split: train - path: test/eng_Latn-dad_Latn.jsonl.gz split: test - path: validation/eng_Latn-dad_Latn.jsonl.gz split: validation - config_name: eng_Latn-opm_Latn data_files: - path: train/eng_Latn-opm_Latn.jsonl.gz split: train - path: test/eng_Latn-opm_Latn.jsonl.gz split: test - path: validation/eng_Latn-opm_Latn.jsonl.gz split: validation - config_name: eng_Latn-zaw_Latn data_files: - path: train/eng_Latn-zaw_Latn.jsonl.gz split: train - path: test/eng_Latn-zaw_Latn.jsonl.gz split: test - path: validation/eng_Latn-zaw_Latn.jsonl.gz split: validation - config_name: eng_Latn-agd_Latn data_files: - path: train/eng_Latn-agd_Latn.jsonl.gz split: train - path: test/eng_Latn-agd_Latn.jsonl.gz split: test - path: validation/eng_Latn-agd_Latn.jsonl.gz split: validation - config_name: eng_Latn-qxo_Latn data_files: - path: train/eng_Latn-qxo_Latn.jsonl.gz split: train - path: test/eng_Latn-qxo_Latn.jsonl.gz split: test - path: validation/eng_Latn-qxo_Latn.jsonl.gz split: validation - config_name: eng_Latn-ign_Latn data_files: - path: train/eng_Latn-ign_Latn.jsonl.gz split: train - path: test/eng_Latn-ign_Latn.jsonl.gz split: test - path: validation/eng_Latn-ign_Latn.jsonl.gz split: validation - config_name: eng_Latn-cak_Latn data_files: - path: train/eng_Latn-cak_Latn.jsonl.gz split: train - path: test/eng_Latn-cak_Latn.jsonl.gz split: test - path: validation/eng_Latn-cak_Latn.jsonl.gz split: validation - config_name: eng_Latn-top_Latn data_files: - path: train/eng_Latn-top_Latn.jsonl.gz split: train - path: test/eng_Latn-top_Latn.jsonl.gz split: test - path: validation/eng_Latn-top_Latn.jsonl.gz split: validation - config_name: eng_Latn-tgk_Cyrl data_files: - path: train/eng_Latn-tgk_Cyrl.jsonl.gz split: train - path: test/eng_Latn-tgk_Cyrl.jsonl.gz split: test - path: validation/eng_Latn-tgk_Cyrl.jsonl.gz split: validation - config_name: eng_Latn-awb_Latn data_files: - path: train/eng_Latn-awb_Latn.jsonl.gz split: train - path: test/eng_Latn-awb_Latn.jsonl.gz split: test - path: validation/eng_Latn-awb_Latn.jsonl.gz split: validation - config_name: eng_Latn-cnl_Latn data_files: - path: train/eng_Latn-cnl_Latn.jsonl.gz split: train - path: test/eng_Latn-cnl_Latn.jsonl.gz split: test - path: validation/eng_Latn-cnl_Latn.jsonl.gz split: validation - config_name: eng_Latn-kgp_Latn data_files: - path: train/eng_Latn-kgp_Latn.jsonl.gz split: train - path: test/eng_Latn-kgp_Latn.jsonl.gz split: test - path: validation/eng_Latn-kgp_Latn.jsonl.gz split: validation - config_name: eng_Latn-khs_Latn data_files: - path: train/eng_Latn-khs_Latn.jsonl.gz split: train - path: test/eng_Latn-khs_Latn.jsonl.gz split: test - path: validation/eng_Latn-khs_Latn.jsonl.gz split: validation - config_name: eng_Latn-abx_Latn data_files: - path: train/eng_Latn-abx_Latn.jsonl.gz split: train - path: test/eng_Latn-abx_Latn.jsonl.gz split: test - path: validation/eng_Latn-abx_Latn.jsonl.gz split: validation - config_name: eng_Latn-mcq_Latn data_files: - path: train/eng_Latn-mcq_Latn.jsonl.gz split: train - path: test/eng_Latn-mcq_Latn.jsonl.gz split: test - path: validation/eng_Latn-mcq_Latn.jsonl.gz split: validation - config_name: eng_Latn-chd_Latn data_files: - path: train/eng_Latn-chd_Latn.jsonl.gz split: train - path: test/eng_Latn-chd_Latn.jsonl.gz split: test - path: validation/eng_Latn-chd_Latn.jsonl.gz split: validation - config_name: eng_Latn-kud_Latn data_files: - path: train/eng_Latn-kud_Latn.jsonl.gz split: train - path: test/eng_Latn-kud_Latn.jsonl.gz split: test - path: validation/eng_Latn-kud_Latn.jsonl.gz split: validation - config_name: eng_Latn-nak_Latn data_files: - path: train/eng_Latn-nak_Latn.jsonl.gz split: train - path: test/eng_Latn-nak_Latn.jsonl.gz split: test - path: validation/eng_Latn-nak_Latn.jsonl.gz split: validation - config_name: eng_Latn-mux_Latn data_files: - path: train/eng_Latn-mux_Latn.jsonl.gz split: train - path: test/eng_Latn-mux_Latn.jsonl.gz split: test - path: validation/eng_Latn-mux_Latn.jsonl.gz split: validation - config_name: eng_Latn-tzo_Latn data_files: - path: train/eng_Latn-tzo_Latn.jsonl.gz split: train - path: test/eng_Latn-tzo_Latn.jsonl.gz split: test - path: validation/eng_Latn-tzo_Latn.jsonl.gz split: validation - config_name: eng_Latn-mav_Latn data_files: - path: train/eng_Latn-mav_Latn.jsonl.gz split: train - path: test/eng_Latn-mav_Latn.jsonl.gz split: test - path: validation/eng_Latn-mav_Latn.jsonl.gz split: validation - config_name: eng_Latn-avt_Latn data_files: - path: train/eng_Latn-avt_Latn.jsonl.gz split: train - path: test/eng_Latn-avt_Latn.jsonl.gz split: test - path: validation/eng_Latn-avt_Latn.jsonl.gz split: validation - config_name: eng_Latn-bjz_Latn data_files: - path: train/eng_Latn-bjz_Latn.jsonl.gz split: train - path: test/eng_Latn-bjz_Latn.jsonl.gz split: test - path: validation/eng_Latn-bjz_Latn.jsonl.gz split: validation - config_name: eng_Latn-ptp_Latn data_files: - path: train/eng_Latn-ptp_Latn.jsonl.gz split: train - path: test/eng_Latn-ptp_Latn.jsonl.gz split: test - path: validation/eng_Latn-ptp_Latn.jsonl.gz split: validation - config_name: eng_Latn-gnw_Latn data_files: - path: train/eng_Latn-gnw_Latn.jsonl.gz split: train - path: test/eng_Latn-gnw_Latn.jsonl.gz split: test - path: validation/eng_Latn-gnw_Latn.jsonl.gz split: validation - config_name: eng_Latn-cub_Latn data_files: - path: train/eng_Latn-cub_Latn.jsonl.gz split: train - path: test/eng_Latn-cub_Latn.jsonl.gz split: test - path: validation/eng_Latn-cub_Latn.jsonl.gz split: validation - config_name: eng_Latn-hmo_Latn data_files: - path: train/eng_Latn-hmo_Latn.jsonl.gz split: train - path: test/eng_Latn-hmo_Latn.jsonl.gz split: test - path: validation/eng_Latn-hmo_Latn.jsonl.gz split: validation - config_name: eng_Latn-kkl_Latn data_files: - path: train/eng_Latn-kkl_Latn.jsonl.gz split: train - path: test/eng_Latn-kkl_Latn.jsonl.gz split: test - path: validation/eng_Latn-kkl_Latn.jsonl.gz split: validation - config_name: eng_Latn-nou_Latn data_files: - path: train/eng_Latn-nou_Latn.jsonl.gz split: train - path: test/eng_Latn-nou_Latn.jsonl.gz split: test - path: validation/eng_Latn-nou_Latn.jsonl.gz split: validation - config_name: eng_Latn-bre_Latn data_files: - path: train/eng_Latn-bre_Latn.jsonl.gz split: train - path: test/eng_Latn-bre_Latn.jsonl.gz split: test - path: validation/eng_Latn-bre_Latn.jsonl.gz split: validation - config_name: eng_Latn-sim_Latn data_files: - path: train/eng_Latn-sim_Latn.jsonl.gz split: train - path: test/eng_Latn-sim_Latn.jsonl.gz split: test - path: validation/eng_Latn-sim_Latn.jsonl.gz split: validation - config_name: eng_Latn-sbk_Latn data_files: - path: train/eng_Latn-sbk_Latn.jsonl.gz split: train - path: test/eng_Latn-sbk_Latn.jsonl.gz split: test - path: validation/eng_Latn-sbk_Latn.jsonl.gz split: validation - config_name: eng_Latn-nsn_Latn data_files: - path: train/eng_Latn-nsn_Latn.jsonl.gz split: train - path: test/eng_Latn-nsn_Latn.jsonl.gz split: test - path: validation/eng_Latn-nsn_Latn.jsonl.gz split: validation - config_name: eng_Latn-mva_Latn data_files: - path: train/eng_Latn-mva_Latn.jsonl.gz split: train - path: test/eng_Latn-mva_Latn.jsonl.gz split: test - path: validation/eng_Latn-mva_Latn.jsonl.gz split: validation - config_name: eng_Latn-kkc_Latn data_files: - path: train/eng_Latn-kkc_Latn.jsonl.gz split: train - path: test/eng_Latn-kkc_Latn.jsonl.gz split: test - path: validation/eng_Latn-kkc_Latn.jsonl.gz split: validation - config_name: eng_Latn-gvc_Latn data_files: - path: train/eng_Latn-gvc_Latn.jsonl.gz split: train - path: test/eng_Latn-gvc_Latn.jsonl.gz split: test - path: validation/eng_Latn-gvc_Latn.jsonl.gz split: validation - config_name: eng_Latn-jao_Latn data_files: - path: train/eng_Latn-jao_Latn.jsonl.gz split: train - path: test/eng_Latn-jao_Latn.jsonl.gz split: test - path: validation/eng_Latn-jao_Latn.jsonl.gz split: validation - config_name: eng_Latn-kek_Latn data_files: - path: train/eng_Latn-kek_Latn.jsonl.gz split: train - path: test/eng_Latn-kek_Latn.jsonl.gz split: test - path: validation/eng_Latn-kek_Latn.jsonl.gz split: validation - config_name: eng_Latn-nfa_Latn data_files: - path: train/eng_Latn-nfa_Latn.jsonl.gz split: train - path: test/eng_Latn-nfa_Latn.jsonl.gz split: test - path: validation/eng_Latn-nfa_Latn.jsonl.gz split: validation - config_name: eng_Latn-lid_Latn data_files: - path: train/eng_Latn-lid_Latn.jsonl.gz split: train - path: test/eng_Latn-lid_Latn.jsonl.gz split: test - path: validation/eng_Latn-lid_Latn.jsonl.gz split: validation - config_name: eng_Latn-kmu_Latn data_files: - path: train/eng_Latn-kmu_Latn.jsonl.gz split: train - path: test/eng_Latn-kmu_Latn.jsonl.gz split: test - path: validation/eng_Latn-kmu_Latn.jsonl.gz split: validation - config_name: eng_Latn-hbo_Hebr data_files: - path: train/eng_Latn-hbo_Hebr.jsonl.gz split: train - path: test/eng_Latn-hbo_Hebr.jsonl.gz split: test - path: validation/eng_Latn-hbo_Hebr.jsonl.gz split: validation - config_name: eng_Latn-bkq_Latn data_files: - path: train/eng_Latn-bkq_Latn.jsonl.gz split: train - path: test/eng_Latn-bkq_Latn.jsonl.gz split: test - path: validation/eng_Latn-bkq_Latn.jsonl.gz split: validation - config_name: eng_Latn-mig_Latn data_files: - path: train/eng_Latn-mig_Latn.jsonl.gz split: train - path: test/eng_Latn-mig_Latn.jsonl.gz split: test - path: validation/eng_Latn-mig_Latn.jsonl.gz split: validation - config_name: eng_Latn-jae_Latn data_files: - path: train/eng_Latn-jae_Latn.jsonl.gz split: train - path: test/eng_Latn-jae_Latn.jsonl.gz split: test - path: validation/eng_Latn-jae_Latn.jsonl.gz split: validation - config_name: eng_Latn-ben_Beng data_files: - path: train/eng_Latn-ben_Beng.jsonl.gz split: train - path: test/eng_Latn-ben_Beng.jsonl.gz split: test - path: validation/eng_Latn-ben_Beng.jsonl.gz split: validation - config_name: eng_Latn-spy_Latn data_files: - path: train/eng_Latn-spy_Latn.jsonl.gz split: train - path: test/eng_Latn-spy_Latn.jsonl.gz split: test - path: validation/eng_Latn-spy_Latn.jsonl.gz split: validation - config_name: eng_Latn-bvd_Latn data_files: - path: train/eng_Latn-bvd_Latn.jsonl.gz split: train - path: test/eng_Latn-bvd_Latn.jsonl.gz split: test - path: validation/eng_Latn-bvd_Latn.jsonl.gz split: validation - config_name: eng_Latn-bvr_Latn data_files: - path: train/eng_Latn-bvr_Latn.jsonl.gz split: train - path: test/eng_Latn-bvr_Latn.jsonl.gz split: test - path: validation/eng_Latn-bvr_Latn.jsonl.gz split: validation - config_name: eng_Latn-kto_Latn data_files: - path: train/eng_Latn-kto_Latn.jsonl.gz split: train - path: test/eng_Latn-kto_Latn.jsonl.gz split: test - path: validation/eng_Latn-kto_Latn.jsonl.gz split: validation - config_name: eng_Latn-amn_Latn data_files: - path: train/eng_Latn-amn_Latn.jsonl.gz split: train - path: test/eng_Latn-amn_Latn.jsonl.gz split: test - path: validation/eng_Latn-amn_Latn.jsonl.gz split: validation - config_name: eng_Latn-spp_Latn data_files: - path: train/eng_Latn-spp_Latn.jsonl.gz split: train - path: test/eng_Latn-spp_Latn.jsonl.gz split: test - path: validation/eng_Latn-spp_Latn.jsonl.gz split: validation - config_name: eng_Latn-ncl_Latn data_files: - path: train/eng_Latn-ncl_Latn.jsonl.gz split: train - path: test/eng_Latn-ncl_Latn.jsonl.gz split: test - path: validation/eng_Latn-ncl_Latn.jsonl.gz split: validation - config_name: eng_Latn-tdt_Latn data_files: - path: train/eng_Latn-tdt_Latn.jsonl.gz split: train - path: test/eng_Latn-tdt_Latn.jsonl.gz split: test - path: validation/eng_Latn-tdt_Latn.jsonl.gz split: validation - config_name: eng_Latn-urw_Latn data_files: - path: train/eng_Latn-urw_Latn.jsonl.gz split: train - path: test/eng_Latn-urw_Latn.jsonl.gz split: test - path: validation/eng_Latn-urw_Latn.jsonl.gz split: validation - config_name: eng_Latn-shp_Latn data_files: - path: train/eng_Latn-shp_Latn.jsonl.gz split: train - path: test/eng_Latn-shp_Latn.jsonl.gz split: test - path: validation/eng_Latn-shp_Latn.jsonl.gz split: validation - config_name: eng_Latn-met_Latn data_files: - path: train/eng_Latn-met_Latn.jsonl.gz split: train - path: test/eng_Latn-met_Latn.jsonl.gz split: test - path: validation/eng_Latn-met_Latn.jsonl.gz split: validation - config_name: eng_Latn-pon_Latn data_files: - path: train/eng_Latn-pon_Latn.jsonl.gz split: train - path: test/eng_Latn-pon_Latn.jsonl.gz split: test - path: validation/eng_Latn-pon_Latn.jsonl.gz split: validation - config_name: eng_Latn-tiy_Latn data_files: - path: train/eng_Latn-tiy_Latn.jsonl.gz split: train - path: test/eng_Latn-tiy_Latn.jsonl.gz split: test - path: validation/eng_Latn-tiy_Latn.jsonl.gz split: validation - config_name: eng_Latn-nhy_Latn data_files: - path: train/eng_Latn-nhy_Latn.jsonl.gz split: train - path: test/eng_Latn-nhy_Latn.jsonl.gz split: test - path: validation/eng_Latn-nhy_Latn.jsonl.gz split: validation - config_name: eng_Latn-cpc_Latn data_files: - path: train/eng_Latn-cpc_Latn.jsonl.gz split: train - path: test/eng_Latn-cpc_Latn.jsonl.gz split: test - path: validation/eng_Latn-cpc_Latn.jsonl.gz split: validation - config_name: eng_Latn-bel_Cyrl data_files: - path: train/eng_Latn-bel_Cyrl.jsonl.gz split: train - path: test/eng_Latn-bel_Cyrl.jsonl.gz split: test - path: validation/eng_Latn-bel_Cyrl.jsonl.gz split: validation - config_name: eng_Latn-cbv_Latn data_files: - path: train/eng_Latn-cbv_Latn.jsonl.gz split: train - path: test/eng_Latn-cbv_Latn.jsonl.gz split: test - path: validation/eng_Latn-cbv_Latn.jsonl.gz split: validation - config_name: eng_Latn-pab_Latn data_files: - path: train/eng_Latn-pab_Latn.jsonl.gz split: train - path: test/eng_Latn-pab_Latn.jsonl.gz split: test - path: validation/eng_Latn-pab_Latn.jsonl.gz split: validation - config_name: eng_Latn-dgz_Latn data_files: - path: train/eng_Latn-dgz_Latn.jsonl.gz split: train - path: test/eng_Latn-dgz_Latn.jsonl.gz split: test - path: validation/eng_Latn-dgz_Latn.jsonl.gz split: validation - config_name: eng_Latn-pri_Latn data_files: - path: train/eng_Latn-pri_Latn.jsonl.gz split: train - path: test/eng_Latn-pri_Latn.jsonl.gz split: test - path: validation/eng_Latn-pri_Latn.jsonl.gz split: validation - config_name: eng_Latn-hch_Latn data_files: - path: train/eng_Latn-hch_Latn.jsonl.gz split: train - path: test/eng_Latn-hch_Latn.jsonl.gz split: test - path: validation/eng_Latn-hch_Latn.jsonl.gz split: validation - config_name: eng_Latn-wed_Latn data_files: - path: train/eng_Latn-wed_Latn.jsonl.gz split: train - path: test/eng_Latn-wed_Latn.jsonl.gz split: test - path: validation/eng_Latn-wed_Latn.jsonl.gz split: validation - config_name: eng_Latn-suz_Latn data_files: - path: train/eng_Latn-suz_Latn.jsonl.gz split: train - path: test/eng_Latn-suz_Latn.jsonl.gz split: test - path: validation/eng_Latn-suz_Latn.jsonl.gz split: validation - config_name: eng_Latn-usp_Latn data_files: - path: train/eng_Latn-usp_Latn.jsonl.gz split: train - path: test/eng_Latn-usp_Latn.jsonl.gz split: test - path: validation/eng_Latn-usp_Latn.jsonl.gz split: validation - config_name: eng_Latn-mkl_Latn data_files: - path: train/eng_Latn-mkl_Latn.jsonl.gz split: train - path: test/eng_Latn-mkl_Latn.jsonl.gz split: test - path: validation/eng_Latn-mkl_Latn.jsonl.gz split: validation - config_name: eng_Latn-cbt_Latn data_files: - path: train/eng_Latn-cbt_Latn.jsonl.gz split: train - path: test/eng_Latn-cbt_Latn.jsonl.gz split: test - path: validation/eng_Latn-cbt_Latn.jsonl.gz split: validation - config_name: eng_Latn-kpg_Latn data_files: - path: train/eng_Latn-kpg_Latn.jsonl.gz split: train - path: test/eng_Latn-kpg_Latn.jsonl.gz split: test - path: validation/eng_Latn-kpg_Latn.jsonl.gz split: validation - config_name: eng_Latn-kue_Latn data_files: - path: train/eng_Latn-kue_Latn.jsonl.gz split: train - path: test/eng_Latn-kue_Latn.jsonl.gz split: test - path: validation/eng_Latn-kue_Latn.jsonl.gz split: validation - config_name: eng_Latn-sbs_Latn data_files: - path: train/eng_Latn-sbs_Latn.jsonl.gz split: train - path: test/eng_Latn-sbs_Latn.jsonl.gz split: test - path: validation/eng_Latn-sbs_Latn.jsonl.gz split: validation - config_name: eng_Latn-qvz_Latn data_files: - path: train/eng_Latn-qvz_Latn.jsonl.gz split: train - path: test/eng_Latn-qvz_Latn.jsonl.gz split: test - path: validation/eng_Latn-qvz_Latn.jsonl.gz split: validation - config_name: eng_Latn-seh_Latn data_files: - path: train/eng_Latn-seh_Latn.jsonl.gz split: train - path: test/eng_Latn-seh_Latn.jsonl.gz split: test - path: validation/eng_Latn-seh_Latn.jsonl.gz split: validation - config_name: eng_Latn-wrs_Latn data_files: - path: train/eng_Latn-wrs_Latn.jsonl.gz split: train - path: test/eng_Latn-wrs_Latn.jsonl.gz split: test - path: validation/eng_Latn-wrs_Latn.jsonl.gz split: validation - config_name: eng_Latn-snc_Latn data_files: - path: train/eng_Latn-snc_Latn.jsonl.gz split: train - path: test/eng_Latn-snc_Latn.jsonl.gz split: test - path: validation/eng_Latn-snc_Latn.jsonl.gz split: validation - config_name: eng_Latn-bjp_Latn data_files: - path: train/eng_Latn-bjp_Latn.jsonl.gz split: train - path: test/eng_Latn-bjp_Latn.jsonl.gz split: test - path: validation/eng_Latn-bjp_Latn.jsonl.gz split: validation - config_name: eng_Latn-kyz_Latn data_files: - path: train/eng_Latn-kyz_Latn.jsonl.gz split: train - path: test/eng_Latn-kyz_Latn.jsonl.gz split: test - path: validation/eng_Latn-kyz_Latn.jsonl.gz split: validation - config_name: eng_Latn-noa_Latn data_files: - path: train/eng_Latn-noa_Latn.jsonl.gz split: train - path: test/eng_Latn-noa_Latn.jsonl.gz split: test - path: validation/eng_Latn-noa_Latn.jsonl.gz split: validation - config_name: eng_Latn-ssx_Latn data_files: - path: train/eng_Latn-ssx_Latn.jsonl.gz split: train - path: test/eng_Latn-ssx_Latn.jsonl.gz split: test - path: validation/eng_Latn-ssx_Latn.jsonl.gz split: validation - config_name: eng_Latn-nbq_Latn data_files: - path: train/eng_Latn-nbq_Latn.jsonl.gz split: train - path: test/eng_Latn-nbq_Latn.jsonl.gz split: test - path: validation/eng_Latn-nbq_Latn.jsonl.gz split: validation - config_name: eng_Latn-msb_Latn data_files: - path: train/eng_Latn-msb_Latn.jsonl.gz split: train - path: test/eng_Latn-msb_Latn.jsonl.gz split: test - path: validation/eng_Latn-msb_Latn.jsonl.gz split: validation - config_name: eng_Latn-sue_Latn data_files: - path: train/eng_Latn-sue_Latn.jsonl.gz split: train - path: test/eng_Latn-sue_Latn.jsonl.gz split: test - path: validation/eng_Latn-sue_Latn.jsonl.gz split: validation - config_name: eng_Latn-asm_Beng data_files: - path: train/eng_Latn-asm_Beng.jsonl.gz split: train - path: test/eng_Latn-asm_Beng.jsonl.gz split: test - path: validation/eng_Latn-asm_Beng.jsonl.gz split: validation - config_name: eng_Latn-som_Latn data_files: - path: train/eng_Latn-som_Latn.jsonl.gz split: train - path: test/eng_Latn-som_Latn.jsonl.gz split: test - path: validation/eng_Latn-som_Latn.jsonl.gz split: validation - config_name: eng_Latn-xon_Latn data_files: - path: train/eng_Latn-xon_Latn.jsonl.gz split: train - path: test/eng_Latn-xon_Latn.jsonl.gz split: test - path: validation/eng_Latn-xon_Latn.jsonl.gz split: validation - config_name: eng_Latn-qvh_Latn data_files: - path: train/eng_Latn-qvh_Latn.jsonl.gz split: train - path: test/eng_Latn-qvh_Latn.jsonl.gz split: test - path: validation/eng_Latn-qvh_Latn.jsonl.gz split: validation - config_name: eng_Latn-mib_Latn data_files: - path: train/eng_Latn-mib_Latn.jsonl.gz split: train - path: test/eng_Latn-mib_Latn.jsonl.gz split: test - path: validation/eng_Latn-mib_Latn.jsonl.gz split: validation - config_name: eng_Latn-wap_Latn data_files: - path: train/eng_Latn-wap_Latn.jsonl.gz split: train - path: test/eng_Latn-wap_Latn.jsonl.gz split: test - path: validation/eng_Latn-wap_Latn.jsonl.gz split: validation - config_name: eng_Latn-gai_Latn data_files: - path: train/eng_Latn-gai_Latn.jsonl.gz split: train - path: test/eng_Latn-gai_Latn.jsonl.gz split: test - path: validation/eng_Latn-gai_Latn.jsonl.gz split: validation - config_name: eng_Latn-mkn_Latn data_files: - path: train/eng_Latn-mkn_Latn.jsonl.gz split: train - path: test/eng_Latn-mkn_Latn.jsonl.gz split: test - path: validation/eng_Latn-mkn_Latn.jsonl.gz split: validation - config_name: eng_Latn-xnn_Latn data_files: - path: train/eng_Latn-xnn_Latn.jsonl.gz split: train - path: test/eng_Latn-xnn_Latn.jsonl.gz split: test - path: validation/eng_Latn-xnn_Latn.jsonl.gz split: validation - config_name: eng_Latn-amf_Latn data_files: - path: train/eng_Latn-amf_Latn.jsonl.gz split: train - path: test/eng_Latn-amf_Latn.jsonl.gz split: test - path: validation/eng_Latn-amf_Latn.jsonl.gz split: validation - config_name: eng_Latn-nhe_Latn data_files: - path: train/eng_Latn-nhe_Latn.jsonl.gz split: train - path: test/eng_Latn-nhe_Latn.jsonl.gz split: test - path: validation/eng_Latn-nhe_Latn.jsonl.gz split: validation - config_name: eng_Latn-kmk_Latn data_files: - path: train/eng_Latn-kmk_Latn.jsonl.gz split: train - path: test/eng_Latn-kmk_Latn.jsonl.gz split: test - path: validation/eng_Latn-kmk_Latn.jsonl.gz split: validation - config_name: eng_Latn-tam_Taml data_files: - path: train/eng_Latn-tam_Taml.jsonl.gz split: train - path: test/eng_Latn-tam_Taml.jsonl.gz split: test - path: validation/eng_Latn-tam_Taml.jsonl.gz split: validation - config_name: eng_Latn-nab_Latn data_files: - path: train/eng_Latn-nab_Latn.jsonl.gz split: train - path: test/eng_Latn-nab_Latn.jsonl.gz split: test - path: validation/eng_Latn-nab_Latn.jsonl.gz split: validation - config_name: eng_Latn-dik_Latn data_files: - path: train/eng_Latn-dik_Latn.jsonl.gz split: train - path: test/eng_Latn-dik_Latn.jsonl.gz split: test - path: validation/eng_Latn-dik_Latn.jsonl.gz split: validation - config_name: eng_Latn-cpy_Latn data_files: - path: train/eng_Latn-cpy_Latn.jsonl.gz split: train - path: test/eng_Latn-cpy_Latn.jsonl.gz split: test - path: validation/eng_Latn-cpy_Latn.jsonl.gz split: validation - config_name: eng_Latn-arl_Latn data_files: - path: train/eng_Latn-arl_Latn.jsonl.gz split: train - path: test/eng_Latn-arl_Latn.jsonl.gz split: test - path: validation/eng_Latn-arl_Latn.jsonl.gz split: validation - config_name: eng_Latn-tuc_Latn data_files: - path: train/eng_Latn-tuc_Latn.jsonl.gz split: train - path: test/eng_Latn-tuc_Latn.jsonl.gz split: test - path: validation/eng_Latn-tuc_Latn.jsonl.gz split: validation - config_name: eng_Latn-ngu_Latn data_files: - path: train/eng_Latn-ngu_Latn.jsonl.gz split: train - path: test/eng_Latn-ngu_Latn.jsonl.gz split: test - path: validation/eng_Latn-ngu_Latn.jsonl.gz split: validation - config_name: eng_Latn-zad_Latn data_files: - path: train/eng_Latn-zad_Latn.jsonl.gz split: train - path: test/eng_Latn-zad_Latn.jsonl.gz split: test - path: validation/eng_Latn-zad_Latn.jsonl.gz split: validation - config_name: eng_Latn-kmh_Latn data_files: - path: train/eng_Latn-kmh_Latn.jsonl.gz split: train - path: test/eng_Latn-kmh_Latn.jsonl.gz split: test - path: validation/eng_Latn-kmh_Latn.jsonl.gz split: validation - config_name: eng_Latn-quh_Latn data_files: - path: train/eng_Latn-quh_Latn.jsonl.gz split: train - path: test/eng_Latn-quh_Latn.jsonl.gz split: test - path: validation/eng_Latn-quh_Latn.jsonl.gz split: validation - config_name: eng_Latn-alq_Latn data_files: - path: train/eng_Latn-alq_Latn.jsonl.gz split: train - path: test/eng_Latn-alq_Latn.jsonl.gz split: test - path: validation/eng_Latn-alq_Latn.jsonl.gz split: validation - config_name: eng_Latn-grc_Grek data_files: - path: train/eng_Latn-grc_Grek.jsonl.gz split: train - path: test/eng_Latn-grc_Grek.jsonl.gz split: test - path: validation/eng_Latn-grc_Grek.jsonl.gz split: validation - config_name: eng_Latn-kaq_Latn data_files: - path: train/eng_Latn-kaq_Latn.jsonl.gz split: train - path: test/eng_Latn-kaq_Latn.jsonl.gz split: test - path: validation/eng_Latn-kaq_Latn.jsonl.gz split: validation - config_name: eng_Latn-zpm_Latn data_files: - path: train/eng_Latn-zpm_Latn.jsonl.gz split: train - path: test/eng_Latn-zpm_Latn.jsonl.gz split: test - path: validation/eng_Latn-zpm_Latn.jsonl.gz split: validation - config_name: eng_Latn-obo_Latn data_files: - path: train/eng_Latn-obo_Latn.jsonl.gz split: train - path: test/eng_Latn-obo_Latn.jsonl.gz split: test - path: validation/eng_Latn-obo_Latn.jsonl.gz split: validation - config_name: eng_Latn-cha_Latn data_files: - path: train/eng_Latn-cha_Latn.jsonl.gz split: train - path: test/eng_Latn-cha_Latn.jsonl.gz split: test - path: validation/eng_Latn-cha_Latn.jsonl.gz split: validation - config_name: eng_Latn-mbs_Latn data_files: - path: train/eng_Latn-mbs_Latn.jsonl.gz split: train - path: test/eng_Latn-mbs_Latn.jsonl.gz split: test - path: validation/eng_Latn-mbs_Latn.jsonl.gz split: validation - config_name: eng_Latn-poi_Latn data_files: - path: train/eng_Latn-poi_Latn.jsonl.gz split: train - path: test/eng_Latn-poi_Latn.jsonl.gz split: test - path: validation/eng_Latn-poi_Latn.jsonl.gz split: validation - config_name: eng_Latn-spm_Latn data_files: - path: train/eng_Latn-spm_Latn.jsonl.gz split: train - path: test/eng_Latn-spm_Latn.jsonl.gz split: test - path: validation/eng_Latn-spm_Latn.jsonl.gz split: validation - config_name: eng_Latn-cpb_Latn data_files: - path: train/eng_Latn-cpb_Latn.jsonl.gz split: train - path: test/eng_Latn-cpb_Latn.jsonl.gz split: test - path: validation/eng_Latn-cpb_Latn.jsonl.gz split: validation - config_name: eng_Latn-omw_Latn data_files: - path: train/eng_Latn-omw_Latn.jsonl.gz split: train - path: test/eng_Latn-omw_Latn.jsonl.gz split: test - path: validation/eng_Latn-omw_Latn.jsonl.gz split: validation - config_name: eng_Latn-klv_Latn data_files: - path: train/eng_Latn-klv_Latn.jsonl.gz split: train - path: test/eng_Latn-klv_Latn.jsonl.gz split: test - path: validation/eng_Latn-klv_Latn.jsonl.gz split: validation - config_name: eng_Latn-sbe_Latn data_files: - path: train/eng_Latn-sbe_Latn.jsonl.gz split: train - path: test/eng_Latn-sbe_Latn.jsonl.gz split: test - path: validation/eng_Latn-sbe_Latn.jsonl.gz split: validation - config_name: eng_Latn-ntu_Latn data_files: - path: train/eng_Latn-ntu_Latn.jsonl.gz split: train - path: test/eng_Latn-ntu_Latn.jsonl.gz split: test - path: validation/eng_Latn-ntu_Latn.jsonl.gz split: validation - config_name: eng_Latn-zat_Latn data_files: - path: train/eng_Latn-zat_Latn.jsonl.gz split: train - path: test/eng_Latn-zat_Latn.jsonl.gz split: test - path: validation/eng_Latn-zat_Latn.jsonl.gz split: validation - config_name: eng_Latn-bsp_Latn data_files: - path: train/eng_Latn-bsp_Latn.jsonl.gz split: train - path: test/eng_Latn-bsp_Latn.jsonl.gz split: test - path: validation/eng_Latn-bsp_Latn.jsonl.gz split: validation - config_name: eng_Latn-mps_Latn data_files: - path: train/eng_Latn-mps_Latn.jsonl.gz split: train - path: test/eng_Latn-mps_Latn.jsonl.gz split: test - path: validation/eng_Latn-mps_Latn.jsonl.gz split: validation - config_name: eng_Latn-mks_Latn data_files: - path: train/eng_Latn-mks_Latn.jsonl.gz split: train - path: test/eng_Latn-mks_Latn.jsonl.gz split: test - path: validation/eng_Latn-mks_Latn.jsonl.gz split: validation - config_name: eng_Latn-bmh_Latn data_files: - path: train/eng_Latn-bmh_Latn.jsonl.gz split: train - path: test/eng_Latn-bmh_Latn.jsonl.gz split: test - path: validation/eng_Latn-bmh_Latn.jsonl.gz split: validation - config_name: eng_Latn-tpz_Latn data_files: - path: train/eng_Latn-tpz_Latn.jsonl.gz split: train - path: test/eng_Latn-tpz_Latn.jsonl.gz split: test - path: validation/eng_Latn-tpz_Latn.jsonl.gz split: validation - config_name: eng_Latn-amr_Latn data_files: - path: train/eng_Latn-amr_Latn.jsonl.gz split: train - path: test/eng_Latn-amr_Latn.jsonl.gz split: test - path: validation/eng_Latn-amr_Latn.jsonl.gz split: validation - config_name: eng_Latn-cjo_Latn data_files: - path: train/eng_Latn-cjo_Latn.jsonl.gz split: train - path: test/eng_Latn-cjo_Latn.jsonl.gz split: test - path: validation/eng_Latn-cjo_Latn.jsonl.gz split: validation - config_name: eng_Latn-ksr_Latn data_files: - path: train/eng_Latn-ksr_Latn.jsonl.gz split: train - path: test/eng_Latn-ksr_Latn.jsonl.gz split: test - path: validation/eng_Latn-ksr_Latn.jsonl.gz split: validation - config_name: eng_Latn-tgo_Latn data_files: - path: train/eng_Latn-tgo_Latn.jsonl.gz split: train - path: test/eng_Latn-tgo_Latn.jsonl.gz split: test - path: validation/eng_Latn-tgo_Latn.jsonl.gz split: validation - config_name: eng_Latn-tke_Latn data_files: - path: train/eng_Latn-tke_Latn.jsonl.gz split: train - path: test/eng_Latn-tke_Latn.jsonl.gz split: test - path: validation/eng_Latn-tke_Latn.jsonl.gz split: validation - config_name: eng_Latn-lac_Latn data_files: - path: train/eng_Latn-lac_Latn.jsonl.gz split: train - path: test/eng_Latn-lac_Latn.jsonl.gz split: test - path: validation/eng_Latn-lac_Latn.jsonl.gz split: validation - config_name: eng_Latn-nhu_Latn data_files: - path: train/eng_Latn-nhu_Latn.jsonl.gz split: train - path: test/eng_Latn-nhu_Latn.jsonl.gz split: test - path: validation/eng_Latn-nhu_Latn.jsonl.gz split: validation - config_name: eng_Latn-ssd_Latn data_files: - path: train/eng_Latn-ssd_Latn.jsonl.gz split: train - path: test/eng_Latn-ssd_Latn.jsonl.gz split: test - path: validation/eng_Latn-ssd_Latn.jsonl.gz split: validation - config_name: eng_Latn-bon_Latn data_files: - path: train/eng_Latn-bon_Latn.jsonl.gz split: train - path: test/eng_Latn-bon_Latn.jsonl.gz split: test - path: validation/eng_Latn-bon_Latn.jsonl.gz split: validation - config_name: eng_Latn-cso_Latn data_files: - path: train/eng_Latn-cso_Latn.jsonl.gz split: train - path: test/eng_Latn-cso_Latn.jsonl.gz split: test - path: validation/eng_Latn-cso_Latn.jsonl.gz split: validation - config_name: eng_Latn-naf_Latn data_files: - path: train/eng_Latn-naf_Latn.jsonl.gz split: train - path: test/eng_Latn-naf_Latn.jsonl.gz split: test - path: validation/eng_Latn-naf_Latn.jsonl.gz split: validation - config_name: eng_Latn-kbh_Latn data_files: - path: train/eng_Latn-kbh_Latn.jsonl.gz split: train - path: test/eng_Latn-kbh_Latn.jsonl.gz split: test - path: validation/eng_Latn-kbh_Latn.jsonl.gz split: validation - config_name: eng_Latn-hun_Latn data_files: - path: train/eng_Latn-hun_Latn.jsonl.gz split: train - path: test/eng_Latn-hun_Latn.jsonl.gz split: test - path: validation/eng_Latn-hun_Latn.jsonl.gz split: validation - config_name: eng_Latn-tte_Latn data_files: - path: train/eng_Latn-tte_Latn.jsonl.gz split: train - path: test/eng_Latn-tte_Latn.jsonl.gz split: test - path: validation/eng_Latn-tte_Latn.jsonl.gz split: validation - config_name: eng_Latn-amo_Latn data_files: - path: train/eng_Latn-amo_Latn.jsonl.gz split: train - path: test/eng_Latn-amo_Latn.jsonl.gz split: test - path: validation/eng_Latn-amo_Latn.jsonl.gz split: validation - config_name: eng_Latn-kiz_Latn data_files: - path: train/eng_Latn-kiz_Latn.jsonl.gz split: train - path: test/eng_Latn-kiz_Latn.jsonl.gz split: test - path: validation/eng_Latn-kiz_Latn.jsonl.gz split: validation - config_name: eng_Latn-wsk_Latn data_files: - path: train/eng_Latn-wsk_Latn.jsonl.gz split: train - path: test/eng_Latn-wsk_Latn.jsonl.gz split: test - path: validation/eng_Latn-wsk_Latn.jsonl.gz split: validation - config_name: eng_Latn-kwd_Latn data_files: - path: train/eng_Latn-kwd_Latn.jsonl.gz split: train - path: test/eng_Latn-kwd_Latn.jsonl.gz split: test - path: validation/eng_Latn-kwd_Latn.jsonl.gz split: validation - config_name: eng_Latn-geb_Latn data_files: - path: train/eng_Latn-geb_Latn.jsonl.gz split: train - path: test/eng_Latn-geb_Latn.jsonl.gz split: test - path: validation/eng_Latn-geb_Latn.jsonl.gz split: validation - config_name: eng_Latn-mdy_Latn data_files: - path: train/eng_Latn-mdy_Latn.jsonl.gz split: train - path: test/eng_Latn-mdy_Latn.jsonl.gz split: test - path: validation/eng_Latn-mdy_Latn.jsonl.gz split: validation - config_name: eng_Latn-kgk_Latn data_files: - path: train/eng_Latn-kgk_Latn.jsonl.gz split: train - path: test/eng_Latn-kgk_Latn.jsonl.gz split: test - path: validation/eng_Latn-kgk_Latn.jsonl.gz split: validation - config_name: eng_Latn-kqw_Latn data_files: - path: train/eng_Latn-kqw_Latn.jsonl.gz split: train - path: test/eng_Latn-kqw_Latn.jsonl.gz split: test - path: validation/eng_Latn-kqw_Latn.jsonl.gz split: validation - config_name: eng_Latn-gaw_Latn data_files: - path: train/eng_Latn-gaw_Latn.jsonl.gz split: train - path: test/eng_Latn-gaw_Latn.jsonl.gz split: test - path: validation/eng_Latn-gaw_Latn.jsonl.gz split: validation - config_name: eng_Latn-mox_Latn data_files: - path: train/eng_Latn-mox_Latn.jsonl.gz split: train - path: test/eng_Latn-mox_Latn.jsonl.gz split: test - path: validation/eng_Latn-mox_Latn.jsonl.gz split: validation - config_name: eng_Latn-cav_Latn data_files: - path: train/eng_Latn-cav_Latn.jsonl.gz split: train - path: test/eng_Latn-cav_Latn.jsonl.gz split: test - path: validation/eng_Latn-cav_Latn.jsonl.gz split: validation - config_name: eng_Latn-tzj_Latn data_files: - path: train/eng_Latn-tzj_Latn.jsonl.gz split: train - path: test/eng_Latn-tzj_Latn.jsonl.gz split: test - path: validation/eng_Latn-tzj_Latn.jsonl.gz split: validation - config_name: eng_Latn-kze_Latn data_files: - path: train/eng_Latn-kze_Latn.jsonl.gz split: train - path: test/eng_Latn-kze_Latn.jsonl.gz split: test - path: validation/eng_Latn-kze_Latn.jsonl.gz split: validation - config_name: eng_Latn-not_Latn data_files: - path: train/eng_Latn-not_Latn.jsonl.gz split: train - path: test/eng_Latn-not_Latn.jsonl.gz split: test - path: validation/eng_Latn-not_Latn.jsonl.gz split: validation - config_name: eng_Latn-lin_Latn data_files: - path: train/eng_Latn-lin_Latn.jsonl.gz split: train - path: test/eng_Latn-lin_Latn.jsonl.gz split: test - path: validation/eng_Latn-lin_Latn.jsonl.gz split: validation - config_name: eng_Latn-urd_Arab data_files: - path: train/eng_Latn-urd_Arab.jsonl.gz split: train - path: test/eng_Latn-urd_Arab.jsonl.gz split: test - path: validation/eng_Latn-urd_Arab.jsonl.gz split: validation - config_name: eng_Latn-mlh_Latn data_files: - path: train/eng_Latn-mlh_Latn.jsonl.gz split: train - path: test/eng_Latn-mlh_Latn.jsonl.gz split: test - path: validation/eng_Latn-mlh_Latn.jsonl.gz split: validation - config_name: eng_Latn-muy_Latn data_files: - path: train/eng_Latn-muy_Latn.jsonl.gz split: train - path: test/eng_Latn-muy_Latn.jsonl.gz split: test - path: validation/eng_Latn-muy_Latn.jsonl.gz split: validation - config_name: eng_Latn-iws_Latn data_files: - path: train/eng_Latn-iws_Latn.jsonl.gz split: train - path: test/eng_Latn-iws_Latn.jsonl.gz split: test - path: validation/eng_Latn-iws_Latn.jsonl.gz split: validation - config_name: eng_Latn-tur_Latn data_files: - path: train/eng_Latn-tur_Latn.jsonl.gz split: train - path: test/eng_Latn-tur_Latn.jsonl.gz split: test - path: validation/eng_Latn-tur_Latn.jsonl.gz split: validation - config_name: eng_Latn-gam_Latn data_files: - path: train/eng_Latn-gam_Latn.jsonl.gz split: train - path: test/eng_Latn-gam_Latn.jsonl.gz split: test - path: validation/eng_Latn-gam_Latn.jsonl.gz split: validation - config_name: eng_Latn-kbc_Latn data_files: - path: train/eng_Latn-kbc_Latn.jsonl.gz split: train - path: test/eng_Latn-kbc_Latn.jsonl.gz split: test - path: validation/eng_Latn-kbc_Latn.jsonl.gz split: validation - config_name: eng_Latn-kgf_Latn data_files: - path: train/eng_Latn-kgf_Latn.jsonl.gz split: train - path: test/eng_Latn-kgf_Latn.jsonl.gz split: test - path: validation/eng_Latn-kgf_Latn.jsonl.gz split: validation - config_name: eng_Latn-maz_Latn data_files: - path: train/eng_Latn-maz_Latn.jsonl.gz split: train - path: test/eng_Latn-maz_Latn.jsonl.gz split: test - path: validation/eng_Latn-maz_Latn.jsonl.gz split: validation - config_name: eng_Latn-nss_Latn data_files: - path: train/eng_Latn-nss_Latn.jsonl.gz split: train - path: test/eng_Latn-nss_Latn.jsonl.gz split: test - path: validation/eng_Latn-nss_Latn.jsonl.gz split: validation - config_name: eng_Latn-ake_Latn data_files: - path: train/eng_Latn-ake_Latn.jsonl.gz split: train - path: test/eng_Latn-ake_Latn.jsonl.gz split: test - path: validation/eng_Latn-ake_Latn.jsonl.gz split: validation - config_name: eng_Latn-nuy_Latn data_files: - path: train/eng_Latn-nuy_Latn.jsonl.gz split: train - path: test/eng_Latn-nuy_Latn.jsonl.gz split: test - path: validation/eng_Latn-nuy_Latn.jsonl.gz split: validation - config_name: eng_Latn-bjk_Latn data_files: - path: train/eng_Latn-bjk_Latn.jsonl.gz split: train - path: test/eng_Latn-bjk_Latn.jsonl.gz split: test - path: validation/eng_Latn-bjk_Latn.jsonl.gz split: validation - config_name: eng_Latn-mzz_Latn data_files: - path: train/eng_Latn-mzz_Latn.jsonl.gz split: train - path: test/eng_Latn-mzz_Latn.jsonl.gz split: test - path: validation/eng_Latn-mzz_Latn.jsonl.gz split: validation - config_name: eng_Latn-msy_Latn data_files: - path: train/eng_Latn-msy_Latn.jsonl.gz split: train - path: test/eng_Latn-msy_Latn.jsonl.gz split: test - path: validation/eng_Latn-msy_Latn.jsonl.gz split: validation - config_name: eng_Latn-anh_Latn data_files: - path: train/eng_Latn-anh_Latn.jsonl.gz split: train - path: test/eng_Latn-anh_Latn.jsonl.gz split: test - path: validation/eng_Latn-anh_Latn.jsonl.gz split: validation - config_name: eng_Latn-bea_Latn data_files: - path: train/eng_Latn-bea_Latn.jsonl.gz split: train - path: test/eng_Latn-bea_Latn.jsonl.gz split: test - path: validation/eng_Latn-bea_Latn.jsonl.gz split: validation - config_name: eng_Latn-ntj_Latn data_files: - path: train/eng_Latn-ntj_Latn.jsonl.gz split: train - path: test/eng_Latn-ntj_Latn.jsonl.gz split: test - path: validation/eng_Latn-ntj_Latn.jsonl.gz split: validation - config_name: eng_Latn-anv_Latn data_files: - path: train/eng_Latn-anv_Latn.jsonl.gz split: train - path: test/eng_Latn-anv_Latn.jsonl.gz split: test - path: validation/eng_Latn-anv_Latn.jsonl.gz split: validation - config_name: eng_Latn-xed_Latn data_files: - path: train/eng_Latn-xed_Latn.jsonl.gz split: train - path: test/eng_Latn-xed_Latn.jsonl.gz split: test - path: validation/eng_Latn-xed_Latn.jsonl.gz split: validation - config_name: eng_Latn-nho_Latn data_files: - path: train/eng_Latn-nho_Latn.jsonl.gz split: train - path: test/eng_Latn-nho_Latn.jsonl.gz split: test - path: validation/eng_Latn-nho_Latn.jsonl.gz split: validation - config_name: eng_Latn-cbc_Latn data_files: - path: train/eng_Latn-cbc_Latn.jsonl.gz split: train - path: test/eng_Latn-cbc_Latn.jsonl.gz split: test - path: validation/eng_Latn-cbc_Latn.jsonl.gz split: validation - config_name: eng_Latn-qve_Latn data_files: - path: train/eng_Latn-qve_Latn.jsonl.gz split: train - path: test/eng_Latn-qve_Latn.jsonl.gz split: test - path: validation/eng_Latn-qve_Latn.jsonl.gz split: validation - config_name: eng_Latn-amp_Latn data_files: - path: train/eng_Latn-amp_Latn.jsonl.gz split: train - path: test/eng_Latn-amp_Latn.jsonl.gz split: test - path: validation/eng_Latn-amp_Latn.jsonl.gz split: validation - config_name: eng_Latn-qvc_Latn data_files: - path: train/eng_Latn-qvc_Latn.jsonl.gz split: train - path: test/eng_Latn-qvc_Latn.jsonl.gz split: test - path: validation/eng_Latn-qvc_Latn.jsonl.gz split: validation - config_name: eng_Latn-aka_Latn data_files: - path: train/eng_Latn-aka_Latn.jsonl.gz split: train - path: test/eng_Latn-aka_Latn.jsonl.gz split: test - path: validation/eng_Latn-aka_Latn.jsonl.gz split: validation - config_name: eng_Latn-aby_Latn data_files: - path: train/eng_Latn-aby_Latn.jsonl.gz split: train - path: test/eng_Latn-aby_Latn.jsonl.gz split: test - path: validation/eng_Latn-aby_Latn.jsonl.gz split: validation - config_name: eng_Latn-myu_Latn data_files: - path: train/eng_Latn-myu_Latn.jsonl.gz split: train - path: test/eng_Latn-myu_Latn.jsonl.gz split: test - path: validation/eng_Latn-myu_Latn.jsonl.gz split: validation - config_name: eng_Latn-aak_Arab data_files: - path: train/eng_Latn-aak_Arab.jsonl.gz split: train - path: test/eng_Latn-aak_Arab.jsonl.gz split: test - path: validation/eng_Latn-aak_Arab.jsonl.gz split: validation - config_name: eng_Latn-soq_Latn data_files: - path: train/eng_Latn-soq_Latn.jsonl.gz split: train - path: test/eng_Latn-soq_Latn.jsonl.gz split: test - path: validation/eng_Latn-soq_Latn.jsonl.gz split: validation - config_name: eng_Latn-tif_Latn data_files: - path: train/eng_Latn-tif_Latn.jsonl.gz split: train - path: test/eng_Latn-tif_Latn.jsonl.gz split: test - path: validation/eng_Latn-tif_Latn.jsonl.gz split: validation - config_name: eng_Latn-aai_Latn data_files: - path: train/eng_Latn-aai_Latn.jsonl.gz split: train - path: test/eng_Latn-aai_Latn.jsonl.gz split: test - path: validation/eng_Latn-aai_Latn.jsonl.gz split: validation - config_name: eng_Latn-nnq_Latn data_files: - path: train/eng_Latn-nnq_Latn.jsonl.gz split: train - path: test/eng_Latn-nnq_Latn.jsonl.gz split: test - path: validation/eng_Latn-nnq_Latn.jsonl.gz split: validation - config_name: eng_Latn-sab_Latn data_files: - path: train/eng_Latn-sab_Latn.jsonl.gz split: train - path: test/eng_Latn-sab_Latn.jsonl.gz split: test - path: validation/eng_Latn-sab_Latn.jsonl.gz split: validation - config_name: eng_Latn-wmw_Latn data_files: - path: train/eng_Latn-wmw_Latn.jsonl.gz split: train - path: test/eng_Latn-wmw_Latn.jsonl.gz split: test - path: validation/eng_Latn-wmw_Latn.jsonl.gz split: validation - config_name: eng_Latn-dgc_Latn data_files: - path: train/eng_Latn-dgc_Latn.jsonl.gz split: train - path: test/eng_Latn-dgc_Latn.jsonl.gz split: test - path: validation/eng_Latn-dgc_Latn.jsonl.gz split: validation - config_name: eng_Latn-roo_Latn data_files: - path: train/eng_Latn-roo_Latn.jsonl.gz split: train - path: test/eng_Latn-roo_Latn.jsonl.gz split: test - path: validation/eng_Latn-roo_Latn.jsonl.gz split: validation - config_name: eng_Latn-tcs_Latn data_files: - path: train/eng_Latn-tcs_Latn.jsonl.gz split: train - path: test/eng_Latn-tcs_Latn.jsonl.gz split: test - path: validation/eng_Latn-tcs_Latn.jsonl.gz split: validation - config_name: eng_Latn-mxb_Latn data_files: - path: train/eng_Latn-mxb_Latn.jsonl.gz split: train - path: test/eng_Latn-mxb_Latn.jsonl.gz split: test - path: validation/eng_Latn-mxb_Latn.jsonl.gz split: validation - config_name: eng_Latn-kde_Latn data_files: - path: train/eng_Latn-kde_Latn.jsonl.gz split: train - path: test/eng_Latn-kde_Latn.jsonl.gz split: test - path: validation/eng_Latn-kde_Latn.jsonl.gz split: validation --- This dataset pre-computes all English-centric directions from [bible-nlp/biblenlp-corpus](https://huggingface.co/datasets/bible-nlp/biblenlp-corpus), and as a result loading is significantly faster. Loading example: ```python >>> from datasets import load_dataset >>> dataset = load_dataset("davidstap/biblenlp-corpus-mmteb", "eng-arb", trust_remote_code=True) >>> dataset DatasetDict({ train: Dataset({ features: ['eng', 'arb'], num_rows: 28723 }) validation: Dataset({ features: ['eng', 'arb'], num_rows: 1578 }) test: Dataset({ features: ['eng', 'arb'], num_rows: 1551 }) }) >>> ``` Note that in all possible configurations, `eng` comes before the other language.
open-web-math/open-web-math	open-web-math	"2023-10-17T20:14:00Z"	18,540	312	[ "size_categories:1M<n<10M", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "arxiv:2310.06786", "region:us" ]	null	"2023-09-06T00:25:12Z"	--- dataset_info: features: - name: url dtype: string - name: text dtype: string - name: date dtype: string - name: metadata dtype: string splits: - name: train num_bytes: 56651995057 num_examples: 6315233 download_size: 16370689925 dataset_size: 56651995057 license: odc-by task_categories: - text-generation language: - en pretty_name: OpenWebMath size_categories: - 10B<n<100B --- <img src="imgs/OpenWebMath-left.png" width="300"> [Keiran Paster](https://keirp.com)\, [Marco Dos Santos](https://marco-dossantos.github.io/)\, [Zhangir Azerbayev](https://zhangir-azerbayev.github.io/), [Jimmy Ba](https://jimmylba.github.io/) [GitHub ](https://github.com/keirp/OpenWebMath) \| [ArXiv](https://arxiv.org/abs/2310.06786) \| [PDF](https://arxiv.org/pdf/2310.06786.pdf) OpenWebMath is a dataset containing the majority of the high-quality, mathematical text from the internet. It is filtered and extracted from over 200B HTML files on Common Crawl down to a set of 6.3 million documents containing a total of 14.7B tokens. OpenWebMath is intended for use in _pretraining_ and _finetuning_ large language models. You can download the dataset using Hugging Face: ```python from datasets import load_dataset ds = load_dataset("open-web-math/open-web-math") ``` # OpenWebMath Contents The dataset is structured as follows: ```python { "text": ..., # document text. "url": ..., # document url. "date": ..., # date the page was crawled. "metadata": ..., # JSON containing information from the extraction process. } ``` OpenWebMath contains documents from over 130k different domains, including data from forums, educational pages, and blogs. The dataset contains documents covering mathematics, physics, statistics, computer science, and more. The following table shows the most common domains in OpenWebMath by character count. \| Domain \| # Characters \| % Characters \| \| ----------------- \| ------------- \| ------------ \| \| stackexchange.com \| 4,655,132,784 \| 9.55% \| \| nature.com \| 1,529,935,838 \| 3.14% \| \| wordpress.com \| 1,294,166,938 \| 2.66% \| \| physicsforums.com \| 1,160,137,919 \| 2.38% \| \| github.io \| 725,689,722 \| 1.49% \| \| zbmath.org \| 620,019,503 \| 1.27% \| \| wikipedia.org \| 618,024,754 \| 1.27% \| \| groundai.com \| 545,214,990 \| 1.12% \| \| blogspot.com \| 520,392,333 \| 1.07% \| \| mathoverflow.net \| 499,102,560 \| 1.02% \| # OpenWebMath Pipeline <img src="imgs/pipeline.png" alt="Overview of the OpenWebMath Pipeline"> OpenWebMath builds on the massive [Common Crawl](https://commoncrawl.org/) dataset, which contains over 200B HTML documents. We filtered the data to only include documents that are: (1) in English, (2) contain mathematical content, and (3) are of high quality. We also put a strong emphasis on extracting LaTeX content from the HTML documents as well as reducing boilerplate in comparison to other web datasets. The OpenWebMath pipeline consists of five steps: 1. Prefiltering HTML Documents: - We apply a simple prefilter to all HTML documents in Common Crawl in order to skip documents without mathematical content to unnecessary processing time. 2. Text Extraction: - Extract text, including LaTeX content, from the HTML documents while removing boilerplate. 3. Content Classification and Filtering: - Apply a [FastText language identification model](https://fasttext.cc/docs/en/language-identification.html) to keep only English documents. - Filter high perplexity documents using a [KenLM](https://github.com/kpu/kenlm) model trained on [Proof-Pile](https://huggingface.co/datasets/hoskinson-center/proof-pile). - Filter non-mathematical documents using our own _MathScore_ model. 4. Deduplication: - Deduplicate the dataset using SimHash in [text-dedup](https://github.com/ChenghaoMou/text-dedup). 5. Manual Inspection: - Inspect the documents gathered from previous steps and remove low quality pages. For a detailed discussion on the processing pipeline, please refer to our paper. # License OpenWebMath is made available under an ODC-By 1.0 license; users should also abide by the CommonCrawl ToU: [https://commoncrawl.org/terms-of-use/](https://commoncrawl.org/terms-of-use/). We do not alter the license of any of the underlying data. # Citation Information ``` @misc{paster2023openwebmath, title={OpenWebMath: An Open Dataset of High-Quality Mathematical Web Text}, author={Keiran Paster and Marco Dos Santos and Zhangir Azerbayev and Jimmy Ba}, year={2023}, eprint={2310.06786}, archivePrefix={arXiv}, primaryClass={cs.AI} } ```
hails/bigbench	hails	"2023-11-17T16:05:10Z"	18,449	4	[ "size_categories:1M<n<10M", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]	null	"2023-10-03T19:55:51Z"	--- dataset_info: - config_name: abstract_narrative_understanding_zero_shot 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: 0 dataset_size: 13120138 - config_name: anachronisms_zero_shot 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: 0 dataset_size: 97652 - config_name: analogical_similarity_zero_shot 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: 0 dataset_size: 2747630 - config_name: analytic_entailment_zero_shot 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: 0 dataset_size: 34632 - config_name: arithmetic_zero_shot 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: 0 dataset_size: 7666544 - config_name: ascii_word_recognition_zero_shot 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: 0 dataset_size: 9969324 - config_name: authorship_verification_zero_shot 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: 0 dataset_size: 28237184 - config_name: auto_categorization_zero_shot 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: 0 dataset_size: 81098 - config_name: auto_debugging_zero_shot 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: 5112 num_examples: 34 - name: train num_bytes: 2651 num_examples: 18 - name: validation num_bytes: 2461 num_examples: 16 download_size: 0 dataset_size: 10224 - config_name: bbq_lite_json_zero_shot 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: 0 dataset_size: 13780986 - config_name: bridging_anaphora_resolution_barqa_zero_shot 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: 0 dataset_size: 3942030 - config_name: causal_judgment_zero_shot 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: 0 dataset_size: 409756 - config_name: cause_and_effect_zero_shot 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: 0 dataset_size: 98628 - config_name: checkmate_in_one_zero_shot 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: 0 dataset_size: 6246512 - config_name: chess_state_tracking_zero_shot 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: 0 dataset_size: 6539864 - config_name: chinese_remainder_theorem_zero_shot 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: 0 dataset_size: 306444 - config_name: cifar10_classification_zero_shot 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: 0 dataset_size: 222044400 - config_name: code_line_description_zero_shot 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: 0 dataset_size: 67340 - config_name: codenames_zero_shot 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: 0 dataset_size: 50390 - config_name: color_zero_shot 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: 0 dataset_size: 3266526 - config_name: common_morpheme_zero_shot 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: 0 dataset_size: 24776 - config_name: conceptual_combinations_zero_shot 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: 0 dataset_size: 117718 - config_name: conlang_translation_zero_shot 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: 0 dataset_size: 430380 - config_name: contextual_parametric_knowledge_conflicts_zero_shot 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: 0 dataset_size: 29175108 - config_name: crash_blossom_zero_shot 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: 0 dataset_size: 24388 - config_name: crass_ai_zero_shot 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: 0 dataset_size: 45740 - config_name: cryobiology_spanish_zero_shot 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: 0 dataset_size: 77348 - config_name: cryptonite_zero_shot 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: 0 dataset_size: 5688804 - config_name: cs_algorithms_zero_shot 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: 0 dataset_size: 544870 - config_name: dark_humor_detection_zero_shot 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: 0 dataset_size: 53112 - config_name: date_understanding_zero_shot 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: 0 dataset_size: 189816 - config_name: disambiguation_qa_zero_shot 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: 0 dataset_size: 244942 - config_name: discourse_marker_prediction_zero_shot 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: 0 dataset_size: 4181368 - config_name: disfl_qa_zero_shot 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: 0 dataset_size: 15929550 - config_name: dyck_languages_zero_shot 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: 0 dataset_size: 2455832 - config_name: elementary_math_qa_zero_shot 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: 0 dataset_size: 26885100 - config_name: emoji_movie_zero_shot 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: 0 dataset_size: 67334 - config_name: emojis_emotion_prediction_zero_shot 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: 0 dataset_size: 95966 - config_name: empirical_judgments_zero_shot 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: 0 dataset_size: 94998 - config_name: english_proverbs_zero_shot 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: 0 dataset_size: 45060 - config_name: english_russian_proverbs_zero_shot 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: 0 dataset_size: 119800 - config_name: entailed_polarity_hindi_zero_shot 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: 0 dataset_size: 114104 - config_name: entailed_polarity_zero_shot 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: 0 dataset_size: 50842 - config_name: epistemic_reasoning_zero_shot 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: 0 dataset_size: 1774316 - config_name: evaluating_information_essentiality_zero_shot 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: 0 dataset_size: 154976 - config_name: fact_checker_zero_shot 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: 0 dataset_size: 2674768 - config_name: fantasy_reasoning_zero_shot 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: 0 dataset_size: 151772 - config_name: few_shot_nlg_zero_shot 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: 0 dataset_size: 151874 - config_name: figure_of_speech_detection_zero_shot 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: 0 dataset_size: 43434 - config_name: formal_fallacies_syllogisms_negation_zero_shot 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: 0 dataset_size: 16629306 - config_name: gem_zero_shot 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: 0 dataset_size: 72130562 - config_name: gender_inclusive_sentences_german_zero_shot 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: 0 dataset_size: 253762 - config_name: general_knowledge_zero_shot 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: 0 dataset_size: 43656 - config_name: geometric_shapes_zero_shot 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: 0 dataset_size: 360188 - config_name: goal_step_wikihow_zero_shot 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: 0 dataset_size: 7135230 - config_name: gre_reading_comprehension_zero_shot 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: 0 dataset_size: 188546 - config_name: hhh_alignment_zero_shot 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: 0 dataset_size: 545796 - config_name: hindi_question_answering_zero_shot 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: 0 dataset_size: 30309908 - config_name: hindu_knowledge_zero_shot 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: 0 dataset_size: 88184 - config_name: hinglish_toxicity_zero_shot 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: 0 dataset_size: 121226 - config_name: human_organs_senses_zero_shot 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: 0 dataset_size: 15888 - config_name: hyperbaton_zero_shot 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: 0 dataset_size: 18767972 - config_name: identify_math_theorems_zero_shot 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: 0 dataset_size: 209682 - config_name: identify_odd_metaphor_zero_shot 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: 0 dataset_size: 55204 - config_name: implicatures_zero_shot 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: 0 dataset_size: 183366 - config_name: implicit_relations_zero_shot 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: 0 dataset_size: 159420 - config_name: intent_recognition_zero_shot 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: 0 dataset_size: 644742 - config_name: international_phonetic_alphabet_nli_zero_shot 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: 0 dataset_size: 158640 - config_name: international_phonetic_alphabet_transliterate_zero_shot 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: 0 dataset_size: 551876 - config_name: intersect_geometry_zero_shot 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: 0 dataset_size: 423349504 - config_name: irony_identification_zero_shot 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: 0 dataset_size: 56356 - config_name: kanji_ascii_zero_shot 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: 0 dataset_size: 733892 - config_name: kannada_zero_shot 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: 0 dataset_size: 281276 - config_name: key_value_maps_zero_shot 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: 0 dataset_size: 210272 - config_name: known_unknowns_zero_shot 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: 0 dataset_size: 15920 - config_name: language_games_zero_shot 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: 0 dataset_size: 1959238 - config_name: language_identification_zero_shot 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: 0 dataset_size: 14752446 - config_name: linguistic_mappings_zero_shot 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: 0 dataset_size: 2650372 - config_name: linguistics_puzzles_zero_shot 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: 0 dataset_size: 3492048 - config_name: list_functions_zero_shot 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: 2678136 num_examples: 10750 - name: train num_bytes: 2161065 num_examples: 8700 - name: validation num_bytes: 517071 num_examples: 2050 download_size: 0 dataset_size: 5356272 - config_name: logic_grid_puzzle_zero_shot 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: 0 dataset_size: 2912436 - config_name: logical_args_zero_shot 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: 0 dataset_size: 87164 - config_name: logical_deduction_zero_shot 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: 0 dataset_size: 2113432 - config_name: logical_fallacy_detection_zero_shot 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: 0 dataset_size: 1440572 - config_name: logical_sequence_zero_shot 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: 0 dataset_size: 45444 - config_name: mathematical_induction_zero_shot 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: 0 dataset_size: 38036 - config_name: matrixshapes_zero_shot 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: 0 dataset_size: 2261148 - config_name: metaphor_boolean_zero_shot 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: 0 dataset_size: 427696 - config_name: metaphor_understanding_zero_shot 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: 0 dataset_size: 401724 - config_name: minute_mysteries_qa_zero_shot 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: 0 dataset_size: 6490380 - config_name: misconceptions_russian_zero_shot 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: 0 dataset_size: 33982 - config_name: misconceptions_zero_shot 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: 0 dataset_size: 91632 - config_name: mnist_ascii_zero_shot 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: 0 dataset_size: 123479616 - config_name: modified_arithmetic_zero_shot 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: 0 dataset_size: 2441986 - config_name: moral_permissibility_zero_shot 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: 0 dataset_size: 324136 - config_name: movie_dialog_same_or_different_zero_shot 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: 0 dataset_size: 57291994 - config_name: movie_recommendation_zero_shot 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: 0 dataset_size: 347114 - config_name: mult_data_wrangling_zero_shot 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: 0 dataset_size: 1250844 - config_name: multiemo_zero_shot 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: 650173925 num_examples: 1437281 - name: train num_bytes: 520172185 num_examples: 1149873 - name: validation num_bytes: 130001740 num_examples: 287408 download_size: 0 dataset_size: 1300347850 - config_name: natural_instructions_zero_shot 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: 355938370 num_examples: 193250 - name: train num_bytes: 284920096 num_examples: 154615 - name: validation num_bytes: 71018274 num_examples: 38635 download_size: 0 dataset_size: 711876740 - config_name: navigate_zero_shot 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: 225813 num_examples: 1000 - name: train num_bytes: 180958 num_examples: 800 - name: validation num_bytes: 44855 num_examples: 200 download_size: 83744 dataset_size: 451626 - config_name: nonsense_words_grammar_zero_shot 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: 11102 num_examples: 50 - name: train num_bytes: 7582 num_examples: 34 - name: validation num_bytes: 3520 num_examples: 16 download_size: 24107 dataset_size: 22204 - config_name: novel_concepts_zero_shot 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: 16065 num_examples: 32 - name: train num_bytes: 8128 num_examples: 16 - name: validation num_bytes: 7937 num_examples: 16 download_size: 25919 dataset_size: 32130 - config_name: object_counting_zero_shot 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: 149555 num_examples: 1000 - name: train num_bytes: 119609 num_examples: 800 - name: validation num_bytes: 29946 num_examples: 200 download_size: 91852 dataset_size: 299110 - config_name: odd_one_out_zero_shot 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: 13843 num_examples: 86 - name: train num_bytes: 11217 num_examples: 69 - name: validation num_bytes: 2626 num_examples: 17 download_size: 25796 dataset_size: 27686 - config_name: operators_zero_shot 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: 32435 num_examples: 210 - name: train num_bytes: 25937 num_examples: 168 - name: validation num_bytes: 6498 num_examples: 42 download_size: 24728 dataset_size: 64870 - config_name: paragraph_segmentation_zero_shot 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: 56846507 num_examples: 9000 - name: train num_bytes: 45674320 num_examples: 7200 - name: validation num_bytes: 11172187 num_examples: 1800 download_size: 61123049 dataset_size: 113693014 - config_name: parsinlu_qa_zero_shot 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: 456189 num_examples: 1050 - name: train num_bytes: 366577 num_examples: 840 - name: validation num_bytes: 89612 num_examples: 210 download_size: 465963 dataset_size: 912378 - config_name: parsinlu_reading_comprehension_zero_shot 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: 573798 num_examples: 518 - name: train num_bytes: 455828 num_examples: 415 - name: validation num_bytes: 117970 num_examples: 103 download_size: 572992 dataset_size: 1147596 - config_name: penguins_in_a_table_zero_shot 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: 75985 num_examples: 149 - name: train num_bytes: 61321 num_examples: 120 - name: validation num_bytes: 14664 num_examples: 29 download_size: 32039 dataset_size: 151970 - config_name: periodic_elements_zero_shot 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: 285204 num_examples: 654 - name: train num_bytes: 229481 num_examples: 524 - name: validation num_bytes: 55723 num_examples: 130 download_size: 41084 dataset_size: 570408 - config_name: persian_idioms_zero_shot 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: 28592 num_examples: 66 - name: train num_bytes: 21684 num_examples: 50 - name: validation num_bytes: 6908 num_examples: 16 download_size: 34341 dataset_size: 57184 - config_name: phrase_relatedness_zero_shot 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: 30190 num_examples: 100 - name: train num_bytes: 23773 num_examples: 80 - name: validation num_bytes: 6417 num_examples: 20 download_size: 40334 dataset_size: 60380 - config_name: physical_intuition_zero_shot 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: 23734 num_examples: 81 - name: train num_bytes: 19307 num_examples: 65 - name: validation num_bytes: 4427 num_examples: 16 download_size: 28462 dataset_size: 47468 - config_name: physics_questions_zero_shot 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: 18372 num_examples: 54 - name: train num_bytes: 13402 num_examples: 38 - name: validation num_bytes: 4970 num_examples: 16 download_size: 35187 dataset_size: 36744 - config_name: physics_zero_shot 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: 120239 num_examples: 229 - name: train num_bytes: 96122 num_examples: 184 - name: validation num_bytes: 24117 num_examples: 45 download_size: 69885 dataset_size: 240478 - config_name: play_dialog_same_or_different_zero_shot 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: 3142468 num_examples: 3264 - name: train num_bytes: 2516052 num_examples: 2612 - name: validation num_bytes: 626416 num_examples: 652 download_size: 1710264 dataset_size: 6284936 - config_name: polish_sequence_labeling_zero_shot 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: 18081112 num_examples: 12812 - name: train num_bytes: 14470720 num_examples: 10250 - name: validation num_bytes: 3610392 num_examples: 2562 download_size: 5242934 dataset_size: 36162224 - config_name: presuppositions_as_nli_zero_shot 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: 502522 num_examples: 735 - name: train num_bytes: 400761 num_examples: 588 - name: validation num_bytes: 101761 num_examples: 147 download_size: 240065 dataset_size: 1005044 - config_name: qa_wikidata_zero_shot 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: 1419042 num_examples: 20321 - name: train num_bytes: 1134918 num_examples: 16257 - name: validation num_bytes: 284124 num_examples: 4064 download_size: 1181835 dataset_size: 2838084 - config_name: question_selection_zero_shot 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: 2487181 num_examples: 1582 - name: train num_bytes: 1990094 num_examples: 1266 - name: validation num_bytes: 497087 num_examples: 316 download_size: 1804283 dataset_size: 4974362 - config_name: real_or_fake_text_zero_shot 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: 53663318 num_examples: 15088 - name: train num_bytes: 42879846 num_examples: 12072 - name: validation num_bytes: 10783472 num_examples: 3016 download_size: 47399045 dataset_size: 107326636 - config_name: reasoning_about_colored_objects_zero_shot 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: 907474 num_examples: 2000 - name: train num_bytes: 729609 num_examples: 1600 - name: validation num_bytes: 177865 num_examples: 400 download_size: 273263 dataset_size: 1814948 - config_name: repeat_copy_logic_zero_shot 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: 6678 num_examples: 32 - name: train num_bytes: 3327 num_examples: 16 - name: validation num_bytes: 3351 num_examples: 16 download_size: 18315 dataset_size: 13356 - config_name: rephrase_zero_shot 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: 34222 num_examples: 78 - name: train num_bytes: 27360 num_examples: 62 - name: validation num_bytes: 6862 num_examples: 16 download_size: 41102 dataset_size: 68444 - config_name: riddle_sense_zero_shot 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: 15507 num_examples: 49 - name: train num_bytes: 10741 num_examples: 33 - name: validation num_bytes: 4766 num_examples: 16 download_size: 32496 dataset_size: 31014 - config_name: ruin_names_zero_shot 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: 144087 num_examples: 448 - name: train num_bytes: 115171 num_examples: 359 - name: validation num_bytes: 28916 num_examples: 89 download_size: 118193 dataset_size: 288174 - config_name: salient_translation_error_detection_zero_shot 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: 1141626 num_examples: 998 - name: train num_bytes: 912819 num_examples: 799 - name: validation num_bytes: 228807 num_examples: 199 download_size: 413634 dataset_size: 2283252 - config_name: scientific_press_release_zero_shot 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: 13690 num_examples: 50 - name: train num_bytes: 9254 num_examples: 34 - name: validation num_bytes: 4436 num_examples: 16 download_size: 27293 dataset_size: 27380 - config_name: semantic_parsing_in_context_sparc_zero_shot 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: 1524852 num_examples: 1155 - name: train num_bytes: 1248391 num_examples: 924 - name: validation num_bytes: 276461 num_examples: 231 download_size: 440326 dataset_size: 3049704 - config_name: semantic_parsing_spider_zero_shot 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: 1265744 num_examples: 1034 - name: train num_bytes: 973864 num_examples: 828 - name: validation num_bytes: 291880 num_examples: 206 download_size: 358276 dataset_size: 2531488 - config_name: sentence_ambiguity_zero_shot 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: 8168 num_examples: 60 - name: train num_bytes: 5976 num_examples: 44 - name: validation num_bytes: 2192 num_examples: 16 download_size: 18275 dataset_size: 16336 - config_name: similarities_abstraction_zero_shot 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: 23416 num_examples: 76 - name: train num_bytes: 18545 num_examples: 60 - name: validation num_bytes: 4871 num_examples: 16 download_size: 31521 dataset_size: 46832 - config_name: simp_turing_concept_zero_shot 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: 1017646 num_examples: 6390 - name: train num_bytes: 813220 num_examples: 5112 - name: validation num_bytes: 204426 num_examples: 1278 download_size: 402574 dataset_size: 2035292 - config_name: simple_arithmetic_json_multiple_choice_zero_shot 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: 924 num_examples: 8 - name: train num_bytes: 0 num_examples: 0 - name: validation num_bytes: 0 num_examples: 0 download_size: 7777 dataset_size: 924 - config_name: simple_arithmetic_json_subtasks_zero_shot 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: 1145 num_examples: 30 - name: train num_bytes: 571 num_examples: 15 - name: validation num_bytes: 574 num_examples: 15 download_size: 10460 dataset_size: 2290 - config_name: simple_arithmetic_json_zero_shot 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: 1145 num_examples: 30 - name: train num_bytes: 540 num_examples: 14 - name: validation num_bytes: 605 num_examples: 16 download_size: 10645 dataset_size: 2290 - config_name: simple_arithmetic_multiple_targets_json_zero_shot 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: 414 num_examples: 10 - name: train num_bytes: 0 num_examples: 0 - name: validation num_bytes: 0 num_examples: 0 download_size: 7352 dataset_size: 414 - config_name: simple_ethical_questions_zero_shot 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: 76518 num_examples: 115 - name: train num_bytes: 60275 num_examples: 92 - name: validation num_bytes: 16243 num_examples: 23 download_size: 81285 dataset_size: 153036 - config_name: simple_text_editing_zero_shot 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: 27865 num_examples: 47 - name: train num_bytes: 18469 num_examples: 31 - name: validation num_bytes: 9396 num_examples: 16 download_size: 27100 dataset_size: 55730 - config_name: snarks_zero_shot 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: 45717 num_examples: 181 - name: train num_bytes: 36989 num_examples: 145 - name: validation num_bytes: 8728 num_examples: 36 download_size: 45434 dataset_size: 91434 - config_name: social_iqa_zero_shot 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: 643162 num_examples: 1935 - name: train num_bytes: 515686 num_examples: 1548 - name: validation num_bytes: 127476 num_examples: 387 download_size: 684043 dataset_size: 1286324 - config_name: social_support_zero_shot 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: 366705 num_examples: 897 - name: train num_bytes: 294793 num_examples: 718 - name: validation num_bytes: 71912 num_examples: 179 download_size: 288867 dataset_size: 733410 - config_name: sports_understanding_zero_shot 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: 226654 num_examples: 986 - name: train num_bytes: 181328 num_examples: 789 - name: validation num_bytes: 45326 num_examples: 197 download_size: 82415 dataset_size: 453308 - config_name: strange_stories_zero_shot 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: 120500 num_examples: 174 - name: train num_bytes: 98055 num_examples: 140 - name: validation num_bytes: 22445 num_examples: 34 download_size: 106428 dataset_size: 241000 - config_name: strategyqa_zero_shot 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: 659967 num_examples: 2289 - name: train num_bytes: 527670 num_examples: 1832 - name: validation num_bytes: 132297 num_examples: 457 download_size: 814405 dataset_size: 1319934 - config_name: sufficient_information_zero_shot 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: 9425 num_examples: 39 - name: train num_bytes: 5594 num_examples: 23 - name: validation num_bytes: 3831 num_examples: 16 download_size: 17766 dataset_size: 18850 - config_name: suicide_risk_zero_shot 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: 37952 num_examples: 40 - name: train num_bytes: 23067 num_examples: 24 - name: validation num_bytes: 14885 num_examples: 16 download_size: 60518 dataset_size: 75904 - config_name: swahili_english_proverbs_zero_shot 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: 90246 num_examples: 153 - name: train num_bytes: 72467 num_examples: 123 - name: validation num_bytes: 17779 num_examples: 30 download_size: 95186 dataset_size: 180492 - config_name: swedish_to_german_proverbs_zero_shot 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: 35204 num_examples: 72 - name: train num_bytes: 27266 num_examples: 56 - name: validation num_bytes: 7938 num_examples: 16 download_size: 55102 dataset_size: 70408 - config_name: symbol_interpretation_zero_shot 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: 1148958 num_examples: 990 - name: train num_bytes: 927326 num_examples: 795 - name: validation num_bytes: 221632 num_examples: 195 download_size: 320412 dataset_size: 2297916 - config_name: temporal_sequences_zero_shot 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: 687086 num_examples: 1000 - name: train num_bytes: 549808 num_examples: 800 - name: validation num_bytes: 137278 num_examples: 200 download_size: 295316 dataset_size: 1374172 - config_name: tense_zero_shot 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: 43882 num_examples: 286 - name: train num_bytes: 35466 num_examples: 229 - name: validation num_bytes: 8416 num_examples: 57 download_size: 51466 dataset_size: 87764 - config_name: timedial_zero_shot 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: 2763178 num_examples: 2550 - name: train num_bytes: 2217190 num_examples: 2040 - name: validation num_bytes: 545988 num_examples: 510 download_size: 2444115 dataset_size: 5526356 - config_name: topical_chat_zero_shot 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: 30927758 num_examples: 22295 - name: train num_bytes: 24827254 num_examples: 17836 - name: validation num_bytes: 6100504 num_examples: 4459 download_size: 23505731 dataset_size: 61855516 - config_name: tracking_shuffled_objects_zero_shot 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: 2775972 num_examples: 3750 - name: train num_bytes: 2224037 num_examples: 3000 - name: validation num_bytes: 551935 num_examples: 750 download_size: 738413 dataset_size: 5551944 - config_name: understanding_fables_zero_shot 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: 227748 num_examples: 189 - name: train num_bytes: 181000 num_examples: 152 - name: validation num_bytes: 46748 num_examples: 37 download_size: 237036 dataset_size: 455496 - config_name: undo_permutation_zero_shot 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: 196118 num_examples: 300 - name: train num_bytes: 158562 num_examples: 240 - name: validation num_bytes: 37556 num_examples: 60 download_size: 137204 dataset_size: 392236 - config_name: unit_conversion_zero_shot 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: 4028628 num_examples: 23936 - name: train num_bytes: 3230357 num_examples: 19151 - name: validation num_bytes: 798271 num_examples: 4785 download_size: 3208622 dataset_size: 8057256 - config_name: unit_interpretation_zero_shot 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: 37363 num_examples: 100 - name: train num_bytes: 29939 num_examples: 80 - name: validation num_bytes: 7424 num_examples: 20 download_size: 34926 dataset_size: 74726 - config_name: unnatural_in_context_learning_zero_shot 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: 4599760 num_examples: 73420 - name: train num_bytes: 3679822 num_examples: 58736 - name: validation num_bytes: 919938 num_examples: 14684 download_size: 3840657 dataset_size: 9199520 - config_name: vitaminc_fact_verification_zero_shot 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: 32361818 num_examples: 54668 - name: train num_bytes: 25889850 num_examples: 43735 - name: validation num_bytes: 6471968 num_examples: 10933 download_size: 14264790 dataset_size: 64723636 - config_name: what_is_the_tao_zero_shot 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: 13268 num_examples: 36 - name: train num_bytes: 7435 num_examples: 20 - name: validation num_bytes: 5833 num_examples: 16 download_size: 27585 dataset_size: 26536 - config_name: which_wiki_edit_zero_shot 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: 6331683 num_examples: 571 - name: train num_bytes: 5233870 num_examples: 457 - name: validation num_bytes: 1097813 num_examples: 114 download_size: 3914574 dataset_size: 12663366 - config_name: winowhy_zero_shot 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: 1002434 num_examples: 2862 - name: train num_bytes: 800520 num_examples: 2290 - name: validation num_bytes: 201914 num_examples: 572 download_size: 449218 dataset_size: 2004868 - config_name: word_sorting_zero_shot 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: 491054 num_examples: 1900 - name: train num_bytes: 392738 num_examples: 1520 - name: validation num_bytes: 98316 num_examples: 380 download_size: 641536 dataset_size: 982108 - config_name: word_unscrambling_zero_shot 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: 882364 num_examples: 8917 - name: train num_bytes: 705755 num_examples: 7134 - name: validation num_bytes: 176609 num_examples: 1783 download_size: 563799 dataset_size: 1764728 configs: - config_name: abstract_narrative_understanding_zero_shot data_files: - split: default path: abstract_narrative_understanding_zero_shot/default-* - split: train path: abstract_narrative_understanding_zero_shot/train-* - split: validation path: abstract_narrative_understanding_zero_shot/validation-* - config_name: anachronisms_zero_shot data_files: - split: default path: anachronisms_zero_shot/default-* - split: train path: anachronisms_zero_shot/train-* - split: validation path: anachronisms_zero_shot/validation-* - config_name: analogical_similarity_zero_shot data_files: - split: default path: analogical_similarity_zero_shot/default-* - split: train path: analogical_similarity_zero_shot/train-* - split: validation path: analogical_similarity_zero_shot/validation-* - config_name: analytic_entailment_zero_shot data_files: - split: default path: analytic_entailment_zero_shot/default-* - split: train path: analytic_entailment_zero_shot/train-* - split: validation path: analytic_entailment_zero_shot/validation-* - config_name: arithmetic_zero_shot data_files: - split: default path: arithmetic_zero_shot/default-* - split: train path: arithmetic_zero_shot/train-* - split: validation path: arithmetic_zero_shot/validation-* - config_name: ascii_word_recognition_zero_shot data_files: - split: default path: ascii_word_recognition_zero_shot/default-* - split: train path: ascii_word_recognition_zero_shot/train-* - split: validation path: ascii_word_recognition_zero_shot/validation-* - config_name: authorship_verification_zero_shot data_files: - split: default path: authorship_verification_zero_shot/default-* - split: train path: authorship_verification_zero_shot/train-* - split: validation path: authorship_verification_zero_shot/validation-* - config_name: auto_categorization_zero_shot data_files: - split: default path: auto_categorization_zero_shot/default-* - split: train path: auto_categorization_zero_shot/train-* - split: validation path: auto_categorization_zero_shot/validation-* - config_name: auto_debugging_zero_shot data_files: - split: default path: auto_debugging_zero_shot/default-* - split: train path: auto_debugging_zero_shot/train-* - split: validation path: auto_debugging_zero_shot/validation-* - config_name: bbq_lite_json_zero_shot data_files: - split: default path: bbq_lite_json_zero_shot/default-* - split: train path: bbq_lite_json_zero_shot/train-* - split: validation path: bbq_lite_json_zero_shot/validation-* - config_name: bridging_anaphora_resolution_barqa_zero_shot data_files: - split: default path: bridging_anaphora_resolution_barqa_zero_shot/default-* - split: train path: bridging_anaphora_resolution_barqa_zero_shot/train-* - split: validation path: bridging_anaphora_resolution_barqa_zero_shot/validation-* - config_name: causal_judgment_zero_shot data_files: - split: default path: causal_judgment_zero_shot/default-* - split: train path: causal_judgment_zero_shot/train-* - split: validation path: causal_judgment_zero_shot/validation-* - config_name: cause_and_effect_zero_shot data_files: - split: default path: cause_and_effect_zero_shot/default-* - split: train path: cause_and_effect_zero_shot/train-* - split: validation path: cause_and_effect_zero_shot/validation-* - config_name: checkmate_in_one_zero_shot data_files: - split: default path: checkmate_in_one_zero_shot/default-* - split: train path: checkmate_in_one_zero_shot/train-* - split: validation path: checkmate_in_one_zero_shot/validation-* - config_name: chess_state_tracking_zero_shot data_files: - split: default path: chess_state_tracking_zero_shot/default-* - split: train path: chess_state_tracking_zero_shot/train-* - split: validation path: chess_state_tracking_zero_shot/validation-* - config_name: chinese_remainder_theorem_zero_shot data_files: - split: default path: chinese_remainder_theorem_zero_shot/default-* - split: train path: chinese_remainder_theorem_zero_shot/train-* - split: validation path: chinese_remainder_theorem_zero_shot/validation-* - config_name: cifar10_classification_zero_shot data_files: - split: default path: cifar10_classification_zero_shot/default-* - split: train path: cifar10_classification_zero_shot/train-* - split: validation path: cifar10_classification_zero_shot/validation-* - config_name: code_line_description_zero_shot data_files: - split: default path: code_line_description_zero_shot/default-* - split: train path: code_line_description_zero_shot/train-* - split: validation path: code_line_description_zero_shot/validation-* - config_name: codenames_zero_shot data_files: - split: default path: codenames_zero_shot/default-* - split: train path: codenames_zero_shot/train-* - split: validation path: codenames_zero_shot/validation-* - config_name: color_zero_shot data_files: - split: default path: color_zero_shot/default-* - split: train path: color_zero_shot/train-* - split: validation path: color_zero_shot/validation-* - config_name: common_morpheme_zero_shot data_files: - split: default path: common_morpheme_zero_shot/default-* - split: train path: common_morpheme_zero_shot/train-* - split: validation path: common_morpheme_zero_shot/validation-* - config_name: conceptual_combinations_zero_shot data_files: - split: default path: conceptual_combinations_zero_shot/default-* - split: train path: conceptual_combinations_zero_shot/train-* - split: validation path: conceptual_combinations_zero_shot/validation-* - config_name: conlang_translation_zero_shot data_files: - split: default path: conlang_translation_zero_shot/default-* - split: train path: conlang_translation_zero_shot/train-* - split: validation path: conlang_translation_zero_shot/validation-* - config_name: contextual_parametric_knowledge_conflicts_zero_shot data_files: - split: default path: contextual_parametric_knowledge_conflicts_zero_shot/default-* - split: train path: contextual_parametric_knowledge_conflicts_zero_shot/train-* - split: validation path: contextual_parametric_knowledge_conflicts_zero_shot/validation-* - config_name: crash_blossom_zero_shot data_files: - split: default path: crash_blossom_zero_shot/default-* - split: train path: crash_blossom_zero_shot/train-* - split: validation path: crash_blossom_zero_shot/validation-* - config_name: crass_ai_zero_shot data_files: - split: default path: crass_ai_zero_shot/default-* - split: train path: crass_ai_zero_shot/train-* - split: validation path: crass_ai_zero_shot/validation-* - config_name: cryobiology_spanish_zero_shot data_files: - split: default path: cryobiology_spanish_zero_shot/default-* - split: train path: cryobiology_spanish_zero_shot/train-* - split: validation path: cryobiology_spanish_zero_shot/validation-* - config_name: cryptonite_zero_shot data_files: - split: default path: cryptonite_zero_shot/default-* - split: train path: cryptonite_zero_shot/train-* - split: validation path: cryptonite_zero_shot/validation-* - config_name: cs_algorithms_zero_shot data_files: - split: default path: cs_algorithms_zero_shot/default-* - split: train path: cs_algorithms_zero_shot/train-* - split: validation path: cs_algorithms_zero_shot/validation-* - config_name: dark_humor_detection_zero_shot data_files: - split: default path: dark_humor_detection_zero_shot/default-* - split: train path: dark_humor_detection_zero_shot/train-* - split: validation path: dark_humor_detection_zero_shot/validation-* - config_name: date_understanding_zero_shot data_files: - split: default path: date_understanding_zero_shot/default-* - split: train path: date_understanding_zero_shot/train-* - split: validation path: date_understanding_zero_shot/validation-* - config_name: disambiguation_qa_zero_shot data_files: - split: default path: disambiguation_qa_zero_shot/default-* - split: train path: disambiguation_qa_zero_shot/train-* - split: validation path: disambiguation_qa_zero_shot/validation-* - config_name: discourse_marker_prediction_zero_shot data_files: - split: default path: discourse_marker_prediction_zero_shot/default-* - split: train path: discourse_marker_prediction_zero_shot/train-* - split: validation path: discourse_marker_prediction_zero_shot/validation-* - config_name: disfl_qa_zero_shot data_files: - split: default path: disfl_qa_zero_shot/default-* - split: train path: disfl_qa_zero_shot/train-* - split: validation path: disfl_qa_zero_shot/validation-* - config_name: dyck_languages_zero_shot data_files: - split: default path: dyck_languages_zero_shot/default-* - split: train path: dyck_languages_zero_shot/train-* - split: validation path: dyck_languages_zero_shot/validation-* - config_name: elementary_math_qa_zero_shot data_files: - split: default path: elementary_math_qa_zero_shot/default-* - split: train path: elementary_math_qa_zero_shot/train-* - split: validation path: elementary_math_qa_zero_shot/validation-* - config_name: emoji_movie_zero_shot data_files: - split: default path: emoji_movie_zero_shot/default-* - split: train path: emoji_movie_zero_shot/train-* - split: validation path: emoji_movie_zero_shot/validation-* - config_name: emojis_emotion_prediction_zero_shot data_files: - split: default path: emojis_emotion_prediction_zero_shot/default-* - split: train path: emojis_emotion_prediction_zero_shot/train-* - split: validation path: emojis_emotion_prediction_zero_shot/validation-* - config_name: empirical_judgments_zero_shot data_files: - split: default path: empirical_judgments_zero_shot/default-* - split: train path: empirical_judgments_zero_shot/train-* - split: validation path: empirical_judgments_zero_shot/validation-* - config_name: english_proverbs_zero_shot data_files: - split: default path: english_proverbs_zero_shot/default-* - split: train path: english_proverbs_zero_shot/train-* - split: validation path: english_proverbs_zero_shot/validation-* - config_name: english_russian_proverbs_zero_shot data_files: - split: default path: english_russian_proverbs_zero_shot/default-* - split: train path: english_russian_proverbs_zero_shot/train-* - split: validation path: english_russian_proverbs_zero_shot/validation-* - config_name: entailed_polarity_hindi_zero_shot data_files: - split: default path: entailed_polarity_hindi_zero_shot/default-* - split: train path: entailed_polarity_hindi_zero_shot/train-* - split: validation path: entailed_polarity_hindi_zero_shot/validation-* - config_name: entailed_polarity_zero_shot data_files: - split: default path: entailed_polarity_zero_shot/default-* - split: train path: entailed_polarity_zero_shot/train-* - split: validation path: entailed_polarity_zero_shot/validation-* - config_name: epistemic_reasoning_zero_shot data_files: - split: default path: epistemic_reasoning_zero_shot/default-* - split: train path: epistemic_reasoning_zero_shot/train-* - split: validation path: epistemic_reasoning_zero_shot/validation-* - config_name: evaluating_information_essentiality_zero_shot data_files: - split: default path: evaluating_information_essentiality_zero_shot/default-* - split: train path: evaluating_information_essentiality_zero_shot/train-* - split: validation path: evaluating_information_essentiality_zero_shot/validation-* - config_name: fact_checker_zero_shot data_files: - split: default path: fact_checker_zero_shot/default-* - split: train path: fact_checker_zero_shot/train-* - split: validation path: fact_checker_zero_shot/validation-* - config_name: fantasy_reasoning_zero_shot data_files: - split: default path: fantasy_reasoning_zero_shot/default-* - split: train path: fantasy_reasoning_zero_shot/train-* - split: validation path: fantasy_reasoning_zero_shot/validation-* - config_name: few_shot_nlg_zero_shot data_files: - split: default path: few_shot_nlg_zero_shot/default-* - split: train path: few_shot_nlg_zero_shot/train-* - split: validation path: few_shot_nlg_zero_shot/validation-* - config_name: figure_of_speech_detection_zero_shot data_files: - split: default path: figure_of_speech_detection_zero_shot/default-* - split: train path: figure_of_speech_detection_zero_shot/train-* - split: validation path: figure_of_speech_detection_zero_shot/validation-* - config_name: formal_fallacies_syllogisms_negation_zero_shot data_files: - split: default path: formal_fallacies_syllogisms_negation_zero_shot/default-* - split: train path: formal_fallacies_syllogisms_negation_zero_shot/train-* - split: validation path: formal_fallacies_syllogisms_negation_zero_shot/validation-* - config_name: gem_zero_shot data_files: - split: default path: gem_zero_shot/default-* - split: train path: gem_zero_shot/train-* - split: validation path: gem_zero_shot/validation-* - config_name: gender_inclusive_sentences_german_zero_shot data_files: - split: default path: gender_inclusive_sentences_german_zero_shot/default-* - split: train path: gender_inclusive_sentences_german_zero_shot/train-* - split: validation path: gender_inclusive_sentences_german_zero_shot/validation-* - config_name: general_knowledge_zero_shot data_files: - split: default path: general_knowledge_zero_shot/default-* - split: train path: general_knowledge_zero_shot/train-* - split: validation path: general_knowledge_zero_shot/validation-* - config_name: geometric_shapes_zero_shot data_files: - split: default path: geometric_shapes_zero_shot/default-* - split: train path: geometric_shapes_zero_shot/train-* - split: validation path: geometric_shapes_zero_shot/validation-* - config_name: goal_step_wikihow_zero_shot data_files: - split: default path: goal_step_wikihow_zero_shot/default-* - split: train path: goal_step_wikihow_zero_shot/train-* - split: validation path: goal_step_wikihow_zero_shot/validation-* - config_name: gre_reading_comprehension_zero_shot data_files: - split: default path: gre_reading_comprehension_zero_shot/default-* - split: train path: gre_reading_comprehension_zero_shot/train-* - split: validation path: gre_reading_comprehension_zero_shot/validation-* - config_name: hhh_alignment_zero_shot data_files: - split: default path: hhh_alignment_zero_shot/default-* - split: train path: hhh_alignment_zero_shot/train-* - split: validation path: hhh_alignment_zero_shot/validation-* - config_name: hindi_question_answering_zero_shot data_files: - split: default path: hindi_question_answering_zero_shot/default-* - split: train path: hindi_question_answering_zero_shot/train-* - split: validation path: hindi_question_answering_zero_shot/validation-* - config_name: hindu_knowledge_zero_shot data_files: - split: default path: hindu_knowledge_zero_shot/default-* - split: train path: hindu_knowledge_zero_shot/train-* - split: validation path: hindu_knowledge_zero_shot/validation-* - config_name: hinglish_toxicity_zero_shot data_files: - split: default path: hinglish_toxicity_zero_shot/default-* - split: train path: hinglish_toxicity_zero_shot/train-* - split: validation path: hinglish_toxicity_zero_shot/validation-* - config_name: human_organs_senses_zero_shot data_files: - split: default path: human_organs_senses_zero_shot/default-* - split: train path: human_organs_senses_zero_shot/train-* - split: validation path: human_organs_senses_zero_shot/validation-* - config_name: hyperbaton_zero_shot data_files: - split: default path: hyperbaton_zero_shot/default-* - split: train path: hyperbaton_zero_shot/train-* - split: validation path: hyperbaton_zero_shot/validation-* - config_name: identify_math_theorems_zero_shot data_files: - split: default path: identify_math_theorems_zero_shot/default-* - split: train path: identify_math_theorems_zero_shot/train-* - split: validation path: identify_math_theorems_zero_shot/validation-* - config_name: identify_odd_metaphor_zero_shot data_files: - split: default path: identify_odd_metaphor_zero_shot/default-* - split: train path: identify_odd_metaphor_zero_shot/train-* - split: validation path: identify_odd_metaphor_zero_shot/validation-* - config_name: implicatures_zero_shot data_files: - split: default path: implicatures_zero_shot/default-* - split: train path: implicatures_zero_shot/train-* - split: validation path: implicatures_zero_shot/validation-* - config_name: implicit_relations_zero_shot data_files: - split: default path: implicit_relations_zero_shot/default-* - split: train path: implicit_relations_zero_shot/train-* - split: validation path: implicit_relations_zero_shot/validation-* - config_name: intent_recognition_zero_shot data_files: - split: default path: intent_recognition_zero_shot/default-* - split: train path: intent_recognition_zero_shot/train-* - split: validation path: intent_recognition_zero_shot/validation-* - config_name: international_phonetic_alphabet_nli_zero_shot data_files: - split: default path: international_phonetic_alphabet_nli_zero_shot/default-* - split: train path: international_phonetic_alphabet_nli_zero_shot/train-* - split: validation path: international_phonetic_alphabet_nli_zero_shot/validation-* - config_name: international_phonetic_alphabet_transliterate_zero_shot data_files: - split: default path: international_phonetic_alphabet_transliterate_zero_shot/default-* - split: train path: international_phonetic_alphabet_transliterate_zero_shot/train-* - split: validation path: international_phonetic_alphabet_transliterate_zero_shot/validation-* - config_name: intersect_geometry_zero_shot data_files: - split: default path: intersect_geometry_zero_shot/default-* - split: train path: intersect_geometry_zero_shot/train-* - split: validation path: intersect_geometry_zero_shot/validation-* - config_name: irony_identification_zero_shot data_files: - split: default path: irony_identification_zero_shot/default-* - split: train path: irony_identification_zero_shot/train-* - split: validation path: irony_identification_zero_shot/validation-* - config_name: kanji_ascii_zero_shot data_files: - split: default path: kanji_ascii_zero_shot/default-* - split: train path: kanji_ascii_zero_shot/train-* - split: validation path: kanji_ascii_zero_shot/validation-* - config_name: kannada_zero_shot data_files: - split: default path: kannada_zero_shot/default-* - split: train path: kannada_zero_shot/train-* - split: validation path: kannada_zero_shot/validation-* - config_name: key_value_maps_zero_shot data_files: - split: default path: key_value_maps_zero_shot/default-* - split: train path: key_value_maps_zero_shot/train-* - split: validation path: key_value_maps_zero_shot/validation-* - config_name: known_unknowns_zero_shot data_files: - split: default path: known_unknowns_zero_shot/default-* - split: train path: known_unknowns_zero_shot/train-* - split: validation path: known_unknowns_zero_shot/validation-* - config_name: language_games_zero_shot data_files: - split: default path: language_games_zero_shot/default-* - split: train path: language_games_zero_shot/train-* - split: validation path: language_games_zero_shot/validation-* - config_name: language_identification_zero_shot data_files: - split: default path: language_identification_zero_shot/default-* - split: train path: language_identification_zero_shot/train-* - split: validation path: language_identification_zero_shot/validation-* - config_name: linguistic_mappings_zero_shot data_files: - split: default path: linguistic_mappings_zero_shot/default-* - split: train path: linguistic_mappings_zero_shot/train-* - split: validation path: linguistic_mappings_zero_shot/validation-* - config_name: linguistics_puzzles_zero_shot data_files: - split: default path: linguistics_puzzles_zero_shot/default-* - split: train path: linguistics_puzzles_zero_shot/train-* - split: validation path: linguistics_puzzles_zero_shot/validation-* - config_name: list_functions_zero_shot data_files: - split: default path: list_functions_zero_shot/default-* - split: train path: list_functions_zero_shot/train-* - split: validation path: list_functions_zero_shot/validation-* - config_name: logic_grid_puzzle_zero_shot data_files: - split: default path: logic_grid_puzzle_zero_shot/default-* - split: train path: logic_grid_puzzle_zero_shot/train-* - split: validation path: logic_grid_puzzle_zero_shot/validation-* - config_name: logical_args_zero_shot data_files: - split: default path: logical_args_zero_shot/default-* - split: train path: logical_args_zero_shot/train-* - split: validation path: logical_args_zero_shot/validation-* - config_name: logical_deduction_zero_shot data_files: - split: default path: logical_deduction_zero_shot/default-* - split: train path: logical_deduction_zero_shot/train-* - split: validation path: logical_deduction_zero_shot/validation-* - config_name: logical_fallacy_detection_zero_shot data_files: - split: default path: logical_fallacy_detection_zero_shot/default-* - split: train path: logical_fallacy_detection_zero_shot/train-* - split: validation path: logical_fallacy_detection_zero_shot/validation-* - config_name: logical_sequence_zero_shot data_files: - split: default path: logical_sequence_zero_shot/default-* - split: train path: logical_sequence_zero_shot/train-* - split: validation path: logical_sequence_zero_shot/validation-* - config_name: mathematical_induction_zero_shot data_files: - split: default path: mathematical_induction_zero_shot/default-* - split: train path: mathematical_induction_zero_shot/train-* - split: validation path: mathematical_induction_zero_shot/validation-* - config_name: matrixshapes_zero_shot data_files: - split: default path: matrixshapes_zero_shot/default-* - split: train path: matrixshapes_zero_shot/train-* - split: validation path: matrixshapes_zero_shot/validation-* - config_name: metaphor_boolean_zero_shot data_files: - split: default path: metaphor_boolean_zero_shot/default-* - split: train path: metaphor_boolean_zero_shot/train-* - split: validation path: metaphor_boolean_zero_shot/validation-* - config_name: metaphor_understanding_zero_shot data_files: - split: default path: metaphor_understanding_zero_shot/default-* - split: train path: metaphor_understanding_zero_shot/train-* - split: validation path: metaphor_understanding_zero_shot/validation-* - config_name: minute_mysteries_qa_zero_shot data_files: - split: default path: minute_mysteries_qa_zero_shot/default-* - split: train path: minute_mysteries_qa_zero_shot/train-* - split: validation path: minute_mysteries_qa_zero_shot/validation-* - config_name: misconceptions_russian_zero_shot data_files: - split: default path: misconceptions_russian_zero_shot/default-* - split: train path: misconceptions_russian_zero_shot/train-* - split: validation path: misconceptions_russian_zero_shot/validation-* - config_name: misconceptions_zero_shot data_files: - split: default path: misconceptions_zero_shot/default-* - split: train path: misconceptions_zero_shot/train-* - split: validation path: misconceptions_zero_shot/validation-* - config_name: mnist_ascii_zero_shot data_files: - split: default path: mnist_ascii_zero_shot/default-* - split: train path: mnist_ascii_zero_shot/train-* - split: validation path: mnist_ascii_zero_shot/validation-* - config_name: modified_arithmetic_zero_shot data_files: - split: default path: modified_arithmetic_zero_shot/default-* - split: train path: modified_arithmetic_zero_shot/train-* - split: validation path: modified_arithmetic_zero_shot/validation-* - config_name: moral_permissibility_zero_shot data_files: - split: default path: moral_permissibility_zero_shot/default-* - split: train path: moral_permissibility_zero_shot/train-* - split: validation path: moral_permissibility_zero_shot/validation-* - config_name: movie_dialog_same_or_different_zero_shot data_files: - split: default path: movie_dialog_same_or_different_zero_shot/default-* - split: train path: movie_dialog_same_or_different_zero_shot/train-* - split: validation path: movie_dialog_same_or_different_zero_shot/validation-* - config_name: movie_recommendation_zero_shot data_files: - split: default path: movie_recommendation_zero_shot/default-* - split: train path: movie_recommendation_zero_shot/train-* - split: validation path: movie_recommendation_zero_shot/validation-* - config_name: mult_data_wrangling_zero_shot data_files: - split: default path: mult_data_wrangling_zero_shot/default-* - split: train path: mult_data_wrangling_zero_shot/train-* - split: validation path: mult_data_wrangling_zero_shot/validation-* - config_name: multiemo_zero_shot data_files: - split: default path: multiemo_zero_shot/default-* - split: train path: multiemo_zero_shot/train-* - split: validation path: multiemo_zero_shot/validation-* - config_name: natural_instructions_zero_shot data_files: - split: default path: natural_instructions_zero_shot/default-* - split: train path: natural_instructions_zero_shot/train-* - split: validation path: natural_instructions_zero_shot/validation-* - config_name: navigate_zero_shot data_files: - split: default path: navigate_zero_shot/default-* - split: train path: navigate_zero_shot/train-* - split: validation path: navigate_zero_shot/validation-* - config_name: nonsense_words_grammar_zero_shot data_files: - split: default path: nonsense_words_grammar_zero_shot/default-* - split: train path: nonsense_words_grammar_zero_shot/train-* - split: validation path: nonsense_words_grammar_zero_shot/validation-* - config_name: novel_concepts_zero_shot data_files: - split: default path: novel_concepts_zero_shot/default-* - split: train path: novel_concepts_zero_shot/train-* - split: validation path: novel_concepts_zero_shot/validation-* - config_name: object_counting_zero_shot data_files: - split: default path: object_counting_zero_shot/default-* - split: train path: object_counting_zero_shot/train-* - split: validation path: object_counting_zero_shot/validation-* - config_name: odd_one_out_zero_shot data_files: - split: default path: odd_one_out_zero_shot/default-* - split: train path: odd_one_out_zero_shot/train-* - split: validation path: odd_one_out_zero_shot/validation-* - config_name: operators_zero_shot data_files: - split: default path: operators_zero_shot/default-* - split: train path: operators_zero_shot/train-* - split: validation path: operators_zero_shot/validation-* - config_name: paragraph_segmentation_zero_shot data_files: - split: default path: paragraph_segmentation_zero_shot/default-* - split: train path: paragraph_segmentation_zero_shot/train-* - split: validation path: paragraph_segmentation_zero_shot/validation-* - config_name: parsinlu_qa_zero_shot data_files: - split: default path: parsinlu_qa_zero_shot/default-* - split: train path: parsinlu_qa_zero_shot/train-* - split: validation path: parsinlu_qa_zero_shot/validation-* - config_name: parsinlu_reading_comprehension_zero_shot data_files: - split: default path: parsinlu_reading_comprehension_zero_shot/default-* - split: train path: parsinlu_reading_comprehension_zero_shot/train-* - split: validation path: parsinlu_reading_comprehension_zero_shot/validation-* - config_name: penguins_in_a_table_zero_shot data_files: - split: default path: penguins_in_a_table_zero_shot/default-* - split: train path: penguins_in_a_table_zero_shot/train-* - split: validation path: penguins_in_a_table_zero_shot/validation-* - config_name: periodic_elements_zero_shot data_files: - split: default path: periodic_elements_zero_shot/default-* - split: train path: periodic_elements_zero_shot/train-* - split: validation path: periodic_elements_zero_shot/validation-* - config_name: persian_idioms_zero_shot data_files: - split: default path: persian_idioms_zero_shot/default-* - split: train path: persian_idioms_zero_shot/train-* - split: validation path: persian_idioms_zero_shot/validation-* - config_name: phrase_relatedness_zero_shot data_files: - split: default path: phrase_relatedness_zero_shot/default-* - split: train path: phrase_relatedness_zero_shot/train-* - split: validation path: phrase_relatedness_zero_shot/validation-* - config_name: physical_intuition_zero_shot data_files: - split: default path: physical_intuition_zero_shot/default-* - split: train path: physical_intuition_zero_shot/train-* - split: validation path: physical_intuition_zero_shot/validation-* - config_name: physics_questions_zero_shot data_files: - split: default path: physics_questions_zero_shot/default-* - split: train path: physics_questions_zero_shot/train-* - split: validation path: physics_questions_zero_shot/validation-* - config_name: physics_zero_shot data_files: - split: default path: physics_zero_shot/default-* - split: train path: physics_zero_shot/train-* - split: validation path: physics_zero_shot/validation-* - config_name: play_dialog_same_or_different_zero_shot data_files: - split: default path: play_dialog_same_or_different_zero_shot/default-* - split: train path: play_dialog_same_or_different_zero_shot/train-* - split: validation path: play_dialog_same_or_different_zero_shot/validation-* - config_name: polish_sequence_labeling_zero_shot data_files: - split: default path: polish_sequence_labeling_zero_shot/default-* - split: train path: polish_sequence_labeling_zero_shot/train-* - split: validation path: polish_sequence_labeling_zero_shot/validation-* - config_name: presuppositions_as_nli_zero_shot data_files: - split: default path: presuppositions_as_nli_zero_shot/default-* - split: train path: presuppositions_as_nli_zero_shot/train-* - split: validation path: presuppositions_as_nli_zero_shot/validation-* - config_name: qa_wikidata_zero_shot data_files: - split: default path: qa_wikidata_zero_shot/default-* - split: train path: qa_wikidata_zero_shot/train-* - split: validation path: qa_wikidata_zero_shot/validation-* - config_name: question_selection_zero_shot data_files: - split: default path: question_selection_zero_shot/default-* - split: train path: question_selection_zero_shot/train-* - split: validation path: question_selection_zero_shot/validation-* - config_name: real_or_fake_text_zero_shot data_files: - split: default path: real_or_fake_text_zero_shot/default-* - split: train path: real_or_fake_text_zero_shot/train-* - split: validation path: real_or_fake_text_zero_shot/validation-* - config_name: reasoning_about_colored_objects_zero_shot data_files: - split: default path: reasoning_about_colored_objects_zero_shot/default-* - split: train path: reasoning_about_colored_objects_zero_shot/train-* - split: validation path: reasoning_about_colored_objects_zero_shot/validation-* - config_name: repeat_copy_logic_zero_shot data_files: - split: default path: repeat_copy_logic_zero_shot/default-* - split: train path: repeat_copy_logic_zero_shot/train-* - split: validation path: repeat_copy_logic_zero_shot/validation-* - config_name: rephrase_zero_shot data_files: - split: default path: rephrase_zero_shot/default-* - split: train path: rephrase_zero_shot/train-* - split: validation path: rephrase_zero_shot/validation-* - config_name: riddle_sense_zero_shot data_files: - split: default path: riddle_sense_zero_shot/default-* - split: train path: riddle_sense_zero_shot/train-* - split: validation path: riddle_sense_zero_shot/validation-* - config_name: ruin_names_zero_shot data_files: - split: default path: ruin_names_zero_shot/default-* - split: train path: ruin_names_zero_shot/train-* - split: validation path: ruin_names_zero_shot/validation-* - config_name: salient_translation_error_detection_zero_shot data_files: - split: default path: salient_translation_error_detection_zero_shot/default-* - split: train path: salient_translation_error_detection_zero_shot/train-* - split: validation path: salient_translation_error_detection_zero_shot/validation-* - config_name: scientific_press_release_zero_shot data_files: - split: default path: scientific_press_release_zero_shot/default-* - split: train path: scientific_press_release_zero_shot/train-* - split: validation path: scientific_press_release_zero_shot/validation-* - config_name: semantic_parsing_in_context_sparc_zero_shot data_files: - split: default path: semantic_parsing_in_context_sparc_zero_shot/default-* - split: train path: semantic_parsing_in_context_sparc_zero_shot/train-* - split: validation path: semantic_parsing_in_context_sparc_zero_shot/validation-* - config_name: semantic_parsing_spider_zero_shot data_files: - split: default path: semantic_parsing_spider_zero_shot/default-* - split: train path: semantic_parsing_spider_zero_shot/train-* - split: validation path: semantic_parsing_spider_zero_shot/validation-* - config_name: sentence_ambiguity_zero_shot data_files: - split: default path: sentence_ambiguity_zero_shot/default-* - split: train path: sentence_ambiguity_zero_shot/train-* - split: validation path: sentence_ambiguity_zero_shot/validation-* - config_name: similarities_abstraction_zero_shot data_files: - split: default path: similarities_abstraction_zero_shot/default-* - split: train path: similarities_abstraction_zero_shot/train-* - split: validation path: similarities_abstraction_zero_shot/validation-* - config_name: simp_turing_concept_zero_shot data_files: - split: default path: simp_turing_concept_zero_shot/default-* - split: train path: simp_turing_concept_zero_shot/train-* - split: validation path: simp_turing_concept_zero_shot/validation-* - config_name: simple_arithmetic_json_multiple_choice_zero_shot data_files: - split: default path: simple_arithmetic_json_multiple_choice_zero_shot/default-* - split: train path: simple_arithmetic_json_multiple_choice_zero_shot/train-* - split: validation path: simple_arithmetic_json_multiple_choice_zero_shot/validation-* - config_name: simple_arithmetic_json_subtasks_zero_shot data_files: - split: default path: simple_arithmetic_json_subtasks_zero_shot/default-* - split: train path: simple_arithmetic_json_subtasks_zero_shot/train-* - split: validation path: simple_arithmetic_json_subtasks_zero_shot/validation-* - config_name: simple_arithmetic_json_zero_shot data_files: - split: default path: simple_arithmetic_json_zero_shot/default-* - split: train path: simple_arithmetic_json_zero_shot/train-* - split: validation path: simple_arithmetic_json_zero_shot/validation-* - config_name: simple_arithmetic_multiple_targets_json_zero_shot data_files: - split: default path: simple_arithmetic_multiple_targets_json_zero_shot/default-* - split: train path: simple_arithmetic_multiple_targets_json_zero_shot/train-* - split: validation path: simple_arithmetic_multiple_targets_json_zero_shot/validation-* - config_name: simple_ethical_questions_zero_shot data_files: - split: default path: simple_ethical_questions_zero_shot/default-* - split: train path: simple_ethical_questions_zero_shot/train-* - split: validation path: simple_ethical_questions_zero_shot/validation-* - config_name: simple_text_editing_zero_shot data_files: - split: default path: simple_text_editing_zero_shot/default-* - split: train path: simple_text_editing_zero_shot/train-* - split: validation path: simple_text_editing_zero_shot/validation-* - config_name: snarks_zero_shot data_files: - split: default path: snarks_zero_shot/default-* - split: train path: snarks_zero_shot/train-* - split: validation path: snarks_zero_shot/validation-* - config_name: social_iqa_zero_shot data_files: - split: default path: social_iqa_zero_shot/default-* - split: train path: social_iqa_zero_shot/train-* - split: validation path: social_iqa_zero_shot/validation-* - config_name: social_support_zero_shot data_files: - split: default path: social_support_zero_shot/default-* - split: train path: social_support_zero_shot/train-* - split: validation path: social_support_zero_shot/validation-* - config_name: sports_understanding_zero_shot data_files: - split: default path: sports_understanding_zero_shot/default-* - split: train path: sports_understanding_zero_shot/train-* - split: validation path: sports_understanding_zero_shot/validation-* - config_name: strange_stories_zero_shot data_files: - split: default path: strange_stories_zero_shot/default-* - split: train path: strange_stories_zero_shot/train-* - split: validation path: strange_stories_zero_shot/validation-* - config_name: strategyqa_zero_shot data_files: - split: default path: strategyqa_zero_shot/default-* - split: train path: strategyqa_zero_shot/train-* - split: validation path: strategyqa_zero_shot/validation-* - config_name: sufficient_information_zero_shot data_files: - split: default path: sufficient_information_zero_shot/default-* - split: train path: sufficient_information_zero_shot/train-* - split: validation path: sufficient_information_zero_shot/validation-* - config_name: suicide_risk_zero_shot data_files: - split: default path: suicide_risk_zero_shot/default-* - split: train path: suicide_risk_zero_shot/train-* - split: validation path: suicide_risk_zero_shot/validation-* - config_name: swahili_english_proverbs_zero_shot data_files: - split: default path: swahili_english_proverbs_zero_shot/default-* - split: train path: swahili_english_proverbs_zero_shot/train-* - split: validation path: swahili_english_proverbs_zero_shot/validation-* - config_name: swedish_to_german_proverbs_zero_shot data_files: - split: default path: swedish_to_german_proverbs_zero_shot/default-* - split: train path: swedish_to_german_proverbs_zero_shot/train-* - split: validation path: swedish_to_german_proverbs_zero_shot/validation-* - config_name: symbol_interpretation_zero_shot data_files: - split: default path: symbol_interpretation_zero_shot/default-* - split: train path: symbol_interpretation_zero_shot/train-* - split: validation path: symbol_interpretation_zero_shot/validation-* - config_name: temporal_sequences_zero_shot data_files: - split: default path: temporal_sequences_zero_shot/default-* - split: train path: temporal_sequences_zero_shot/train-* - split: validation path: temporal_sequences_zero_shot/validation-* - config_name: tense_zero_shot data_files: - split: default path: tense_zero_shot/default-* - split: train path: tense_zero_shot/train-* - split: validation path: tense_zero_shot/validation-* - config_name: timedial_zero_shot data_files: - split: default path: timedial_zero_shot/default-* - split: train path: timedial_zero_shot/train-* - split: validation path: timedial_zero_shot/validation-* - config_name: topical_chat_zero_shot data_files: - split: default path: topical_chat_zero_shot/default-* - split: train path: topical_chat_zero_shot/train-* - split: validation path: topical_chat_zero_shot/validation-* - config_name: tracking_shuffled_objects_zero_shot data_files: - split: default path: tracking_shuffled_objects_zero_shot/default-* - split: train path: tracking_shuffled_objects_zero_shot/train-* - split: validation path: tracking_shuffled_objects_zero_shot/validation-* - config_name: understanding_fables_zero_shot data_files: - split: default path: understanding_fables_zero_shot/default-* - split: train path: understanding_fables_zero_shot/train-* - split: validation path: understanding_fables_zero_shot/validation-* - config_name: undo_permutation_zero_shot data_files: - split: default path: undo_permutation_zero_shot/default-* - split: train path: undo_permutation_zero_shot/train-* - split: validation path: undo_permutation_zero_shot/validation-* - config_name: unit_conversion_zero_shot data_files: - split: default path: unit_conversion_zero_shot/default-* - split: train path: unit_conversion_zero_shot/train-* - split: validation path: unit_conversion_zero_shot/validation-* - config_name: unit_interpretation_zero_shot data_files: - split: default path: unit_interpretation_zero_shot/default-* - split: train path: unit_interpretation_zero_shot/train-* - split: validation path: unit_interpretation_zero_shot/validation-* - config_name: unnatural_in_context_learning_zero_shot data_files: - split: default path: unnatural_in_context_learning_zero_shot/default-* - split: train path: unnatural_in_context_learning_zero_shot/train-* - split: validation path: unnatural_in_context_learning_zero_shot/validation-* - config_name: vitaminc_fact_verification_zero_shot data_files: - split: default path: vitaminc_fact_verification_zero_shot/default-* - split: train path: vitaminc_fact_verification_zero_shot/train-* - split: validation path: vitaminc_fact_verification_zero_shot/validation-* - config_name: what_is_the_tao_zero_shot data_files: - split: default path: what_is_the_tao_zero_shot/default-* - split: train path: what_is_the_tao_zero_shot/train-* - split: validation path: what_is_the_tao_zero_shot/validation-* - config_name: which_wiki_edit_zero_shot data_files: - split: default path: which_wiki_edit_zero_shot/default-* - split: train path: which_wiki_edit_zero_shot/train-* - split: validation path: which_wiki_edit_zero_shot/validation-* - config_name: winowhy_zero_shot data_files: - split: default path: winowhy_zero_shot/default-* - split: train path: winowhy_zero_shot/train-* - split: validation path: winowhy_zero_shot/validation-* - config_name: word_sorting_zero_shot data_files: - split: default path: word_sorting_zero_shot/default-* - split: train path: word_sorting_zero_shot/train-* - split: validation path: word_sorting_zero_shot/validation-* - config_name: word_unscrambling_zero_shot data_files: - split: default path: word_unscrambling_zero_shot/default-* - split: train path: word_unscrambling_zero_shot/train-* - split: validation path: word_unscrambling_zero_shot/validation-* --- # Dataset Card for "bigbench" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
open-llm-leaderboard/contents	open-llm-leaderboard	"2025-03-20T12:17:27Z"	18,423	15	[ "size_categories:1K<n<10K", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]	null	"2024-06-26T08:33:17Z"	--- dataset_info: features: - name: eval_name dtype: string - name: Precision dtype: string - name: Type dtype: string - name: T dtype: string - name: Weight type dtype: string - name: Architecture dtype: string - name: Model dtype: string - name: fullname dtype: string - name: Model sha dtype: string - name: Average ⬆️ dtype: float64 - name: Hub License dtype: string - name: Hub ❤️ dtype: int64 - name: '#Params (B)' dtype: float64 - name: Available on the hub dtype: bool - name: MoE dtype: bool - name: Flagged dtype: bool - name: Chat Template dtype: bool - name: CO₂ cost (kg) dtype: float64 - name: IFEval Raw dtype: float64 - name: IFEval dtype: float64 - name: BBH Raw dtype: float64 - name: BBH dtype: float64 - name: MATH Lvl 5 Raw dtype: float64 - name: MATH Lvl 5 dtype: float64 - name: GPQA Raw dtype: float64 - name: GPQA dtype: float64 - name: MUSR Raw dtype: float64 - name: MUSR dtype: float64 - name: MMLU-PRO Raw dtype: float64 - name: MMLU-PRO dtype: float64 - name: Merged dtype: bool - name: Official Providers dtype: bool - name: Upload To Hub Date dtype: string - name: Submission Date dtype: string - name: Generation dtype: int64 - name: Base Model dtype: string splits: - name: train num_bytes: 4004719 num_examples: 4576 download_size: 1109997 dataset_size: 4004719 configs: - config_name: default data_files: - split: train path: data/train-* ---
textmachinelab/quail	textmachinelab	"2024-01-04T16:18:32Z"	18,305	7	[ "task_categories:multiple-choice", "task_ids:multiple-choice-qa", "annotations_creators:crowdsourced", "language_creators:found", "multilinguality:monolingual", "source_datasets:original", "language:en", "license:cc-by-nc-sa-4.0", "size_categories:10K<n<100K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]	[ "multiple-choice" ]	"2022-03-02T23:29:22Z"	--- annotations_creators: - crowdsourced language_creators: - found language: - en license: - cc-by-nc-sa-4.0 multilinguality: - monolingual size_categories: - 10K<n<100K source_datasets: - original task_categories: - multiple-choice task_ids: - multiple-choice-qa paperswithcode_id: quail pretty_name: Question Answering for Artificial Intelligence (QuAIL) dataset_info: config_name: quail features: - name: id dtype: string - name: context_id dtype: string - name: question_id dtype: string - name: domain dtype: string - name: metadata struct: - name: author dtype: string - name: title dtype: string - name: url dtype: string - name: context dtype: string - name: question dtype: string - name: question_type dtype: string - name: answers sequence: string - name: correct_answer_id dtype: int32 splits: - name: train num_bytes: 23432601 num_examples: 10246 - name: validation num_bytes: 4989531 num_examples: 2164 - name: challenge num_bytes: 1199792 num_examples: 556 download_size: 2286403 dataset_size: 29621924 configs: - config_name: quail data_files: - split: train path: quail/train-* - split: validation path: quail/validation-* - split: challenge path: quail/challenge-* default: true --- # Dataset Card for "quail" ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - Homepage: [https://text-machine-lab.github.io/blog/2020/quail/](https://text-machine-lab.github.io/blog/2020/quail/) - Repository: https://github.com/text-machine-lab/quail - Paper: [Getting Closer to AI Complete Question Answering: A Set of Prerequisite Real Tasks](https://doi.org/10.1609/aaai.v34i05.6398 ) - Point of Contact: [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - Size of downloaded dataset files: 6.41 MB - Size of the generated dataset: 29.62 MB - Total amount of disk used: 36.03 MB ### Dataset Summary QuAIL is a reading comprehension dataset. QuAIL contains 15K multi-choice questions in texts 300-350 tokens long 4 domains (news, user stories, fiction, blogs).QuAIL is balanced and annotated for question types. ### Supported Tasks and Leaderboards [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Languages [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Dataset Structure ### Data Instances #### quail - Size of downloaded dataset files: 6.41 MB - Size of the generated dataset: 29.62 MB - Total amount of disk used: 36.03 MB An example of 'train' looks as follows. ``` This example was too long and was cropped: { "answers": ["the cousin is not friendly", "the cousin could have been pretier", "not enough information", "the cousin was too nice"], "context": "\"That fall came and I went back to Michigan and the school year went by and summer came and I never really thought about it. I'm...", "context_id": "f001", "correct_answer_id": 0, "domain": "fiction", "id": "f001_19", "metadata": { "author": "Joseph Devon", "title": "Black Eyed Susan", "url": "http://manybooks.net/pages/devonjother08black_eyed_susan/0.html" }, "question": "After the events in the text what does the author think about the cousin?", "question_id": "19", "question_type": "Subsequent_state" } ``` ### Data Fields The data fields are the same among all splits. #### quail - `id`: a `string` feature. - `context_id`: a `string` feature. - `question_id`: a `string` feature. - `domain`: a `string` feature. - `author`: a `string` feature. - `title`: a `string` feature. - `url`: a `string` feature. - `context`: a `string` feature. - `question`: a `string` feature. - `question_type`: a `string` feature. - `answers`: a `list` of `string` features. - `correct_answer_id`: a `int32` feature. ### Data Splits \|name \|train\|challenge\|validation\| \|-----\|----:\|--------:\|---------:\| \|quail\|10246\| 556\| 2164\| ## Dataset Creation ### Curation Rationale [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Source Data #### Initial Data Collection and Normalization [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the source language producers? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Annotations #### Annotation process [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the annotators? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Personal and Sensitive Information [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Discussion of Biases [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Other Known Limitations [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Additional Information ### Dataset Curators [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Licensing Information [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Citation Information ``` @inproceedings{DBLP:conf/aaai/RogersKDR20, author = {Anna Rogers and Olga Kovaleva and Matthew Downey and Anna Rumshisky}, title = {Getting Closer to {AI} Complete Question Answering: {A} Set of Prerequisite Real Tasks}, booktitle = {The Thirty-Fourth {AAAI} Conference on Artificial Intelligence, {AAAI} 2020, The Thirty-Second Innovative Applications of Artificial Intelligence Conference, {IAAI} 2020, The Tenth {AAAI} Symposium on Educational Advances in Artificial Intelligence, {EAAI} 2020, New York, NY, USA, February 7-12, 2020}, pages = {8722--8731}, publisher = {{AAAI} Press}, year = {2020}, url = {https://aaai.org/ojs/index.php/AAAI/article/view/6398}, timestamp = {Thu, 04 Jun 2020 13:18:48 +0200}, biburl = {https://dblp.org/rec/conf/aaai/RogersKDR20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} } ``` ### Contributions Thanks to [@sai-prasanna](https://github.com/sai-prasanna), [@ngdodd](https://github.com/ngdodd) for adding this dataset.
avery00/MomentSeeker	avery00	"2025-03-26T03:18:37Z"	18,222	1	[ "task_categories:question-answering", "language:en", "license:cc-by-nc-sa-4.0", "size_categories:1K<n<10K", "format:imagefolder", "modality:image", "modality:video", "library:datasets", "library:mlcroissant", "arxiv:2502.12558", "region:us" ]	[ "question-answering" ]	"2025-03-07T08:35:58Z"	--- license: cc-by-nc-sa-4.0 extra_gated_prompt: >- You acknowledge and understand that: This dataset is provided solely for academic research purposes. It is not intended for commercial use or any other non-research activities. All copyrights, trademarks, and other intellectual property rights related to the videos in the dataset remain the exclusive property of their respective owners. You assume full responsibility for any additional use or dissemination of this dataset and for any consequences that may arise from such actions. You are also aware that the copyright holders of the original videos retain the right to request the removal of their videos from the dataset. Furthermore, it is your responsibility to respect these conditions and to use the dataset ethically and in compliance with all applicable laws and regulations. Any violation of these terms may result in the immediate termination of your access to the dataset. extra_gated_fields: Institution: text Name: text Country: country I want to use this dataset for: type: select options: - Research I agree to use this dataset solely for research purposes: checkbox I will not use this dataset in any way that infringes upon the rights of the copyright holders of the original videos, and strictly prohibit its use for any commercial purposes: checkbox task_categories: - question-answering language: - en --- <h1 align="center">MomentSeeker: A Comprehensive Benchmark and A Strong Baseline For Moment Retrieval Within Long Videos</h1> <p align="center"> <a href="https://arxiv.org/abs/2502.12558"> <img alt="Build" src="http://img.shields.io/badge/cs.CV-arXiv%3A2406.04264-B31B1B.svg"> </a> <a href="https://github.com/yhy-2000/MomentSeeker"> <img alt="Build" src="https://img.shields.io/badge/Github-MomentSeeker: A Comprehensive Benchmark and A Strong Baseline For Moment Retrieval Within Long Videos-blue"> </a> </p> This repo contains the annotation data for the paper "[MomentSeeker: A Comprehensive Benchmark and A Strong Baseline For Moment Retrieval Within Long Videos](https://arxiv.org/abs/2502.12558)". ## 🔔 News: - 🥳 2025/03/07: We have released the MomentSeeker [Benchmark](https://huggingface.co/datasets/avery00/MomentSeeker) and [Paper](https://arxiv.org/abs/2502.12558)! 🔥 ## License Our dataset is under the CC-BY-NC-SA-4.0 license. ⚠️ If you need to access and use our dataset, you must understand and agree: This dataset is for research purposes only and cannot be used for any commercial or other purposes. The user assumes all effects arising from any other use and dissemination. We do not own the copyright of any raw video files. Currently, we provide video access to researchers under the condition of acknowledging the above license. For the video data used, we respect and acknowledge any copyrights of the video authors. Therefore, for the movies, TV series, documentaries, and cartoons used in the dataset, we have reduced the resolution, clipped the length, adjusted dimensions, etc. of the original videos to minimize the impact on the rights of the original works. If the original authors of the related works still believe that the videos should be removed, please contact [email protected] or directly raise an issue. ## Introduction We present MomentSeeker, a comprehensive benchmark to evaluate retrieval models' performance in handling general long-video moment retrieval (LVMR) tasks. MomentSeeker offers three key advantages. First, it incorporates long videos of over 500 seconds on average, making it the first benchmark specialized for long-video moment retrieval. Second, it covers a wide range of task categories (including Moment Search, Caption Alignment, Image-conditioned Moment Search, and Video-conditioned Moment Search) and diverse application scenarios (e.g., sports, movies, cartoons, and ego), making it a comprehensive tool for assessing retrieval models' general LVMR performance. Additionally, the evaluation tasks are carefully curated through human annotation, ensuring the reliability of assessment. We further fine-tune an MLLM-based LVMR retriever on synthetic data, which demonstrates strong performance on our benchmark. The checkpoint will release soon. ![Illustrative overview of our MomentSeeker dataset.](https://cdn-uploads.huggingface.co/production/uploads/66d916a7b86f0d569aa19b60/ff-9bFKlN466wElhiA4Wi.png) ## 🏆 Mini Leaderboard \| Rank \| Method \| Backbone \| # Params \| CA \| MS \| IMS \| VMS \| Overall \| \|------\|------------------------------------------\|-----------------\|---------\|--------\|--------\|--------\|--------\|--------\| \| 1 \| V-Embedder \| InternVideo2-Chat\| 8B \| <u>42.2</u> \| 20.4 \| 15.0 \| 15.8 \| 23.3 \| \| 2 \| CoVR \| BLIP-Large \| 588M \| 25.8 \| 17.4 \| <u>12.3</u> \| <u>12.3</u> \| <u>17.1</u> \| \| 3 \| InternVideo2 \| ViT \| 1B \| 44.6 \| <u>18.2</u> \| 4.8 \| 0.0 \| 16.9 \| \| 4 \| MM-Ret \| CLIP-Base \| 149M \| 23.2 \| 15.4 \| 10.5 \| 10.5 \| 14.9 \| \| 5 \| LanguageBind \| CLIP-Large \| 428M \| 39.6 \| 16.4 \| 3.2 \| 0.0 \| 14.8 \| \| 6 \| E5V \| LLaVA-1.6 \| 8.4B \| 25.8 \| 16.8 \| 6.2 \| 5.2 \| 13.5 \| \| 7 \| UniIR \| CLIP-Large \| 428M \| 25.0 \| 15.2 \| 6.4 \| 0.0 \| 10.9 \| \| 8 \| MLLM2VEC \| LLaVA-1.6 \| 8.4B \| 6.4 \| 6.2 \| 3.0 \| 3.0 \| 4.7 \| \| 9 \| MagicLens \| CLIP-Large \| 428M \| 9.0 \| 2.4 \| 3.2 \| 2.8 \| 4.4 \| ## License Our dataset is under the CC-BY-NC-SA-4.0 license. ⚠️ If you need to access and use our dataset, you must understand and agree: This dataset is for research purposes only and cannot be used for any commercial or other purposes. The user assumes all effects arising from any other use and dissemination. We do not own the copyright of any raw video files. Currently, we provide video access to researchers under the condition of acknowledging the above license. For the video data used, we respect and acknowledge any copyrights of the video authors. Therefore, for the movies, TV series, documentaries, and cartoons used in the dataset, we have reduced the resolution, clipped the length, adjusted dimensions, etc. of the original videos to minimize the impact on the rights of the original works. If the original authors of the related works still believe that the videos should be removed, please contact [email protected] or directly raise an issue. ## Evaluation > Before you access our dataset, we kindly ask you to thoroughly read and understand the license outlined above. If you cannot agree to these terms, we request that you refrain from downloading our video data. The JSON file provides candidate videos for each question. The candidates can be ranked, and metrics such as Recall@1 and MAP@5 can be computed accordingly. ## Hosting and Maintenance The annotation files will be permanently retained. If some videos are requested to be removed, we will replace them with a set of video frames sparsely sampled from the video and adjusted in resolution. Since all the questions in MomentSeeker are only related to visual content and do not involve audio, this will not significantly affect the validity of MomentSeeker (most existing MLLMs also understand videos by frame extraction). If even retaining the frame set is not allowed, we will still keep the relevant annotation files, and replace them with the meta-information of the video, or actively seek more reliable and risk-free video sources. ## Citation If you find this repository useful, please consider giving a star 🌟 and citation ``` @misc{yuan2025momentseekercomprehensivebenchmarkstrong, title={MomentSeeker: A Comprehensive Benchmark and A Strong Baseline For Moment Retrieval Within Long Videos}, author={Huaying Yuan and Jian Ni and Yueze Wang and Junjie Zhou and Zhengyang Liang and Zheng Liu and Zhao Cao and Zhicheng Dou and Ji-Rong Wen}, year={2025}, eprint={2502.12558}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2502.12558}, } ```
jkot/parliament_hearings_processed	jkot	"2023-04-25T08:53:38Z"	18,135	1	[ "size_categories:100K<n<1M", "format:parquet", "modality:audio", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]	null	"2023-04-21T10:06:00Z"	--- dataset_info: features: - name: id dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: transcription dtype: string splits: - name: train num_bytes: 51234859011.0 num_examples: 191455 - name: test num_bytes: 762989296.0 num_examples: 2726 download_size: 51507735963 dataset_size: 51997848307.0 --- # Preprocessed parliament hearings ASR dataset to truecased form. ## Original dataset: https://lindat.mff.cuni.cz/repository/xmlui/handle/11234/1-3126 --- dataset_info: features: - name: id dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: string splits: - name: train num_bytes: 53645064353.18 num_examples: 191455 - name: test num_bytes: 740331298.0 num_examples: 2726 download_size: 51507379112 dataset_size: 54385395651.18 ---
AppThreat/vdb	AppThreat	"2025-04-11T20:48:34Z"	18,132	1	[ "language:en", "license:mit", "region:us", "vulnerabilities", "vdb", "sca", "osv", "nvd", "ghsa", "vers", "purl" ]	null	"2025-02-17T23:35:01Z"	--- viewer: false license: mit language: - en tags: - vulnerabilities - vdb - sca - osv - nvd - ghsa - vers - purl --- This dataset comprises application and OS vulnerabilities aggregated from multiple sources, including OSV, GitHub, NVD, and Linux vendor feeds, in the form of SQLite data files (.vdb6). ## Vulnerability Data sources - Linux [vuln-list](https://github.com/appthreat/vuln-list) - OSV (1) - NVD - GitHub ## Linux distros - AlmaLinux - Debian - Alpine - Amazon Linux - Arch Linux - RHEL/CentOS - Rocky Linux - Ubuntu - OpenSUSE - Photon - Chainguard - Wolfi OS ## Database files The vulnerability database comprises two SQLite database files. - data.index.vdb6 - A smaller index database optimized for quick purl or cpe string searches and vers-based range comparisons. ![Index schema](./docs/vdb-index-schema.png) - data.vdb6 - Full CVE source database containing normalized data in CVE 5.1 specification formation and purl prefix. ![Data schema](./docs/vdb-schema.png) ## Folders - app - Application only vulnerabilities from 2018 - app-10y - Application only vulnerabilities from 2014 - app-os - Application and OS vulnerabilities from 2018 - app-os-10y - Application and OS vulnerabilities from 2014 Download data.vdb6 and data.index.vdb6 files from a single folder of your choice. ## Searching for CVEs Use the smaller index database for all search operations. ### Searching by purl Given a purl string (`purl_str`), perform the following steps to convert this into a suitable purl prefix (`purl_prefix`) string: In most cases, a purl prefix is a substring at index 0 after a split by "@". Eg: `purl_prefix = purl_str.split("@")[0]`. A more robust approach: - Parse and validate the string using a suitable [library](https://github.com/package-url/). Retain the parsed purl object (`purl_obj`) - Construct a purl prefix string with the following logic: - Set the value for `purl_prefix` to `"pkg:" + purl_obj["type"]` - If there is a namespace, append it to purl_prefix after the slash character. Eg: `purl_prefix = purl_prefix + "/" + purl_obj['namespace']` - Optional for Linux distros: If there is a qualifier string with the name `distro_name`, append it to the purl_prefix after the slash character. Eg: `purl_prefix = purl_prefix + "/" + purl_obj['qualifiers']['distro_name']` - Append the name after the slash character. Eg: `purl_prefix = purl_prefix + "/" + purl_obj['name']` Use the below SQL query to search by purl_prefix: ``` SELECT DISTINCT cve_id, type, namespace, name, vers, purl_prefix FROM cve_index where purl_prefix = ?; ``` ### Searching by cpe Parse the cpe string to extract the vendor, product, and version. The regex for python is shown below: ```python import re CPE_FULL_REGEX = re.compile( "cpe:?:[^:]+:(?P<cve_type>[^:]+):(?P<vendor>[^:]+):(?P<package>[^:]+):(?P<version>[^:]+):(?P<update>[^:]+):(?P<edition>[^:]+):(?P<lang>[^:]+):(?P<sw_edition>[^:]+):(?P<target_sw>[^:]+):(?P<target_hw>[^:]+):(?P<other>[^:]+)" ) ``` In the `cve_index` table, vendor maps to namespace and package maps to name. The SQL query is below: ```sql SELECT DISTINCT cve_id, type, namespace, name, vers, purl_prefix FROM cve_index where namespace = ? AND name = ?; ``` ### Comparing version ranges using vers Refer to the vers [documentation](https://github.com/package-url/purl-spec/blob/version-range-spec/VERSION-RANGE-SPEC.rst) for information regarding vers and a logic to parse and check if a version is within a range. To simplify the logic, a value from the vers column in `cve_index` would contain only a maximum of two constraints (one greater than and one lesser than). ## Combining data Search the `cve_index` table in the index database first to retrieve any matching cve_id and purl_prefix values. Use these two column values to retrieve the full CVE source information from the `cve_data` table. An example query is shown below: ```sql SELECT DISTINCT cve_id, type, namespace, name, source_data_hash, json(source_data), json(override_data), purl_prefix FROM cve_data WHERE cve_id = ? AND purl_prefix = ? GROUP BY purl_prefix ORDER BY cve_id DESC; ``` Use the `source_data_hash` values to filter out any duplicate results for the same CVE. Duplicate results are possible when multiple vers match the same CVE and purl prefixes. ## Citation Use the below citation in your research. ```text @misc{vdb, author = {Team AppThreat}, month = Feb, title = {{AppThreat vulnerability-db}}, howpublished = {{https://huggingface.co/datasets/AppThreat/vdb}}, year = {2025} } ```
ptb-text-only/ptb_text_only	ptb-text-only	"2024-01-18T11:13:39Z"	18,045	16	[ "task_categories:text-generation", "task_categories:fill-mask", "task_ids:language-modeling", "task_ids:masked-language-modeling", "annotations_creators:expert-generated", "language_creators:found", "multilinguality:monolingual", "source_datasets:original", "language:en", "license:other", "size_categories:10K<n<100K", "region:us" ]	[ "text-generation", "fill-mask" ]	"2022-03-02T23:29:22Z"	--- annotations_creators: - expert-generated language_creators: - found language: - en license: - other license_details: LDC User Agreement for Non-Members multilinguality: - monolingual size_categories: - 10K<n<100K source_datasets: - original task_categories: - text-generation - fill-mask task_ids: - language-modeling - masked-language-modeling paperswithcode_id: null pretty_name: Penn Treebank dataset_info: features: - name: sentence dtype: string config_name: penn_treebank splits: - name: train num_bytes: 5143706 num_examples: 42068 - name: test num_bytes: 453710 num_examples: 3761 - name: validation num_bytes: 403156 num_examples: 3370 download_size: 5951345 dataset_size: 6000572 --- # Dataset Card for Penn Treebank ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - Homepage: https://catalog.ldc.upenn.edu/LDC99T42 - Repository: 'https://raw.githubusercontent.com/wojzaremba/lstm/master/data/ptb.train.txt', 'https://raw.githubusercontent.com/wojzaremba/lstm/master/data/ptb.valid.txt', 'https://raw.githubusercontent.com/wojzaremba/lstm/master/data/ptb.test.txt' - Paper: https://www.aclweb.org/anthology/J93-2004.pdf - Leaderboard: [Needs More Information] - Point of Contact: [Needs More Information] ### Dataset Summary This is the Penn Treebank Project: Release 2 CDROM, featuring a million words of 1989 Wall Street Journal material. The rare words in this version are already replaced with <unk> token. The numbers are replaced with <N> token. ### Supported Tasks and Leaderboards Language Modelling ### Languages The text in the dataset is in American English ## Dataset Structure ### Data Instances [Needs More Information] ### Data Fields [Needs More Information] ### Data Splits [Needs More Information] ## Dataset Creation ### Curation Rationale [Needs More Information] ### Source Data #### Initial Data Collection and Normalization [Needs More Information] #### Who are the source language producers? [Needs More Information] ### Annotations #### Annotation process [Needs More Information] #### Who are the annotators? [Needs More Information] ### Personal and Sensitive Information [Needs More Information] ## Considerations for Using the Data ### Social Impact of Dataset [Needs More Information] ### Discussion of Biases [Needs More Information] ### Other Known Limitations [Needs More Information] ## Additional Information ### Dataset Curators [Needs More Information] ### Licensing Information Dataset provided for research purposes only. Please check dataset license for additional information. ### Citation Information @article{marcus-etal-1993-building, title = "Building a Large Annotated Corpus of {E}nglish: The {P}enn {T}reebank", author = "Marcus, Mitchell P. and Santorini, Beatrice and Marcinkiewicz, Mary Ann", journal = "Computational Linguistics", volume = "19", number = "2", year = "1993", url = "https://www.aclweb.org/anthology/J93-2004", pages = "313--330", } ### Contributions Thanks to [@harshalmittal4](https://github.com/harshalmittal4) for adding this dataset.
allenai/sciq	allenai	"2024-01-04T16:23:51Z"	18,019	104	[ "task_categories:question-answering", "task_ids:closed-domain-qa", "annotations_creators:no-annotation", "language_creators:crowdsourced", "multilinguality:monolingual", "source_datasets:original", "language:en", "license:cc-by-nc-3.0", "size_categories:10K<n<100K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]	[ "question-answering" ]	"2022-03-02T23:29:22Z"	--- annotations_creators: - no-annotation language_creators: - crowdsourced language: - en license: - cc-by-nc-3.0 multilinguality: - monolingual size_categories: - 10K<n<100K source_datasets: - original task_categories: - question-answering task_ids: - closed-domain-qa paperswithcode_id: sciq pretty_name: SciQ dataset_info: features: - name: question dtype: string - name: distractor3 dtype: string - name: distractor1 dtype: string - name: distractor2 dtype: string - name: correct_answer dtype: string - name: support dtype: string splits: - name: train num_bytes: 6546183 num_examples: 11679 - name: validation num_bytes: 554120 num_examples: 1000 - name: test num_bytes: 563927 num_examples: 1000 download_size: 4674410 dataset_size: 7664230 configs: - config_name: default data_files: - split: train path: data/train-* - split: validation path: data/validation-* - split: test path: data/test-* --- # Dataset Card for "sciq" ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - Homepage: [https://allenai.org/data/sciq](https://allenai.org/data/sciq) - Repository: [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - Paper: [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - Point of Contact: [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - Size of downloaded dataset files: 2.82 MB - Size of the generated dataset: 7.68 MB - Total amount of disk used: 10.50 MB ### Dataset Summary The SciQ dataset contains 13,679 crowdsourced science exam questions about Physics, Chemistry and Biology, among others. The questions are in multiple-choice format with 4 answer options each. For the majority of the questions, an additional paragraph with supporting evidence for the correct answer is provided. ### Supported Tasks and Leaderboards [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Languages [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Dataset Structure ### Data Instances #### default - Size of downloaded dataset files: 2.82 MB - Size of the generated dataset: 7.68 MB - Total amount of disk used: 10.50 MB An example of 'train' looks as follows. ``` This example was too long and was cropped: { "correct_answer": "coriolis effect", "distractor1": "muon effect", "distractor2": "centrifugal effect", "distractor3": "tropical effect", "question": "What phenomenon makes global winds blow northeast to southwest or the reverse in the northern hemisphere and northwest to southeast or the reverse in the southern hemisphere?", "support": "\"Without Coriolis Effect the global winds would blow north to south or south to north. But Coriolis makes them blow northeast to..." } ``` ### Data Fields The data fields are the same among all splits. #### default - `question`: a `string` feature. - `distractor3`: a `string` feature. - `distractor1`: a `string` feature. - `distractor2`: a `string` feature. - `correct_answer`: a `string` feature. - `support`: a `string` feature. ### Data Splits \| name \|train\|validation\|test\| \|-------\|----:\|---------:\|---:\| \|default\|11679\| 1000\|1000\| ## Dataset Creation ### Curation Rationale [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Source Data #### Initial Data Collection and Normalization [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the source language producers? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Annotations #### Annotation process [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the annotators? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Personal and Sensitive Information [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Discussion of Biases [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Other Known Limitations [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Additional Information ### Dataset Curators [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Licensing Information The dataset is licensed under the [Creative Commons Attribution-NonCommercial 3.0 Unported License](http://creativecommons.org/licenses/by-nc/3.0/). ### Citation Information ``` @inproceedings{SciQ, title={Crowdsourcing Multiple Choice Science Questions}, author={Johannes Welbl, Nelson F. Liu, Matt Gardner}, year={2017}, journal={arXiv:1707.06209v1} } ``` ### Contributions Thanks to [@patrickvonplaten](https://github.com/patrickvonplaten), [@lewtun](https://github.com/lewtun), [@thomwolf](https://github.com/thomwolf) for adding this dataset.
mlfoundations/MINT-1T-PDF-CC-2024-18	mlfoundations	"2024-09-19T21:02:55Z"	17,909	19	[ "task_categories:image-to-text", "task_categories:text-generation", "language:en", "license:cc-by-4.0", "size_categories:100B<n<1T", "arxiv:2406.11271", "region:us", "multimodal" ]	[ "image-to-text", "text-generation" ]	"2024-07-15T03:19:33Z"	--- license: cc-by-4.0 task_categories: - image-to-text - text-generation language: - en tags: - multimodal pretty_name: MINT-1T size_categories: - 100B<n<1T configs: - config_name: default data_files: - split: train path: CC-MAIN-/ --- <h1 align="center"> 🍃 MINT-1T:<br>Scaling Open-Source Multimodal Data by 10x:<br> A Multimodal Dataset with One Trillion Tokens </h1> 🍃 MINT-1T is an open-source Multimodal INTerleaved dataset with 1 trillion text tokens and 3.4 billion images, a 10x scale-up from existing open-source datasets. Additionally, we include previously untapped sources such as PDFs and ArXiv papers. 🍃 MINT-1T is designed to facilitate research in multimodal pretraining. 🍃 MINT-1T is created by a team from the University of Washington in collaboration with Salesforce Research, other academic institutions including Stanford University, University of Texas at Austin, and University of California Berkeley. You are currently viewing a subset of the PDF portion of 🍃 MINT-1T associated with CommonCrawl dump `CC-2024-18`. For other PDF, HTML, and ArXiv subsets, refer to the [🍃 MINT-1T collection](https://huggingface.co/collections/mlfoundations/mint-1t-6690216ca4d0df7e518dde1c). ![Examples](interleaved-example-twitter.png) ## Updates ### 9/19/24 We have removed roughly 10% of the PDF samples as there was a mismatch between the frames in the TIFF images and the document metadata. ### 8/8/24 We have become aware that the image hashes in the PDF subset of MINT-1T do not match the images in the documents. We want to emphasize that the images for each document are correct, and only the image hashes in the documents' metadata are mislabeled. ## Dataset Details ### Dataset Sources - Repository: https://github.com/mlfoundations/MINT-1T - Paper: https://arxiv.org/abs/2406.11271 - Blog: https://blog.salesforceairesearch.com/mint-1t/ ## Uses ### Direct Use <!-- This section describes suitable use cases for the dataset. --> 🍃 MINT-1T is designed to facilitate research in multimodal pretraining. The dataset can be used for training multimodal models that can reson about interleaved text and images sequences such as [Idefics2](https://huggingface.co/HuggingFaceM4/idefics2-8b), [XGen-MM](https://huggingface.co/Salesforce/xgen-mm-phi3-mini-instruct-r-v1), and [Chameleon](https://huggingface.co/facebook/chameleon-30b). ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the dataset will not work well for. --> 🍃 MINT-1T was built to make research into large multimodal models more accessible. Using the dataset to train models that ingest or generate personally identifying information (such as images of people’s faces and other sensitive content) as well as military applications are all inappropriate use cases of 🍃 MINT-1T. ## Dataset Creation ### Curation Rationale 🍃 MINT-1T was created to address a significant gap in the open-source domain by providing a large-scale multimodal interleaved dataset for pre-training large multimodal models. This dataset aims to be a valuable resource for the research community, facilitating open science in multimodal pretraining. ### Source Data The dataset is a comprehensive collection of multimodal documents from various sources: - HTML documents: Filtered from CommonCrawl WARC dumps spanning from 2017 to 2024 - PDF documents: Extracted from CommonCrawl WAT dumps covering 2023 to 2024 - ArXiv documents: A subset of papers from the ArXiv repository In total, 🍃 MINT-1T contains 1056.8 million documents, broken down as follows: - 1029.4 million HTML documents - 24.0 million PDF documents - 0.6 million ArXiv documents #### Data Collection and Processing The data collection and processing involved several steps: 1. Document Extraction: - HTML documents were parsed from CommonCrawl WARC files - PDF documents were extracted from CommonCrawl WAT files - ArXiv papers were directly sourced from ArXiv S3 buckets 2. Filtering Process: - Applied text quality filters to ensure content relevance and readability - Removed duplicate content at both paragraph and document levels - Filtered out undesirable content based on predefined criteria - Verified image availability and quality for HTML documents - Limited PDF size to 50MB and 50 pages to manage dataset size and quality 3. Image Processing: - Used NSFW image detection to remove pornographic or otherwise undesirable images - Removed images smaller than 150 pixels or larger than 20,000 pixels - Adjusted aspect ratio thresholds for HTML (2:1) and PDF (3:1) to preserve scientific figures 4. Text Processing: - Used fasttext for language identification, focusing on English content - Masked personally identifiable information such as email addresses and IP addresses - Applied paragraph and document-level deduplication using Bloom filters 5. PDF Specific Processing: - Used PyMuPDF for parsing PDFs and extracting reading order - Clustered text blocks based on columns and ordered from top left to bottom right 6. ArXiv Specific Processing: - Used TexSoup to parse LaTeX source code and interleave images with text - Cleaned up LaTeX code by removing imports, bibliography, tables, and citation tags Various open-source tools were utilized in this process, including fasttext, [PyMuPDF](https://github.com/pymupdf/PyMuPDF), and [DCLM](https://www.datacomp.ai/dclm/) and [bff](https://github.com/revbucket/bff) for deduplication and content filtering. #### Personal and Sensitive Information Despite sourcing from public web data, significant efforts were made to minimize the inclusion of personal and sensitive information: - Email addresses and IP addresses were masked to protect privacy - An NSFW image classifierto remove inappropriate visual content - URLs containing substrings associated with undesirable or sensitive content were filtered out However, users should be aware that as the data originates from the public web, it may still contain some sensitive or personal information. The dataset creators acknowledge this limitation and advise users to exercise caution and potentially apply additional filtering based on their specific use cases. ## Bias, Risks, and Limitations Several potential biases, risks, and limitations have been identified: 1. Data Bias: As the dataset is sourced from web crawls, it may inherit biases present in online content. 2. Content Risks: Despite extensive filtering, there's a possibility that some offensive, insensitive, or inappropriate content may remain in the dataset. 3. Image Availability: The dataset relies on external image URLs, which may become unavailable over time due to link rot, potentially affecting the dataset's long-term usability. 4. PDF Parsing Limitations: The current method for extracting reading order from PDFs may not always accurately capture the intended flow, especially for documents with complex layouts. 5. Potential Legal and Ethical Concerns: While efforts were made to respect robots.txt files and remove sensitive information, there may still be content that individuals did not explicitly consent to include. ### Recommendations Given these considerations, the following recommendations are provided: 1. Additional Filtering: Users are strongly encouraged to apply additional filtering based on their specific use case and ethical considerations. 2. Inappropriate Use Cases: The dataset is not recommended for applications involving the processing or generation of personally identifying information, nor for military applications. 3. Legal Compliance: Users should independently verify compliance with applicable laws before employing MINT-1T for commercial purposes. 4. Bias Awareness: Researchers and developers should be cognizant of potential biases in the dataset and consider their impact on model training and outputs. ## License We release 🍃 MINT-1T under a CC-BY-4.0 license, designating it primarily as a research artifact. While the dataset is freely available, users are responsible for ensuring its legal use in commercial settings. Users must independently verify compliance with applicable laws before employing MINT-1T for commercial purposes. ## Citation ``` @article{awadalla2024mint1t, title={MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokens}, author={Anas Awadalla and Le Xue and Oscar Lo and Manli Shu and Hannah Lee and Etash Kumar Guha and Matt Jordan and Sheng Shen and Mohamed Awadalla and Silvio Savarese and Caiming Xiong and Ran Xu and Yejin Choi and Ludwig Schmidt}, year={2024} } ```
gigant/tib_slides	gigant	"2025-01-28T14:40:52Z"	17,901	0	[ "size_categories:100K<n<1M", "format:parquet", "modality:image", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]	null	"2023-01-27T01:44:02Z"	--- dataset_info: features: - name: Image dtype: image - name: file_name dtype: string splits: - name: train num_bytes: 131956494917.654 num_examples: 484843 download_size: 0 dataset_size: 131956494917.654 --- # Dataset Card for "tib_slides" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
bhatvineet/shrutilipi_mr	bhatvineet	"2023-03-13T18:54:45Z"	17,888	0	[ "size_categories:100K<n<1M", "format:parquet", "modality:audio", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]	null	"2023-03-13T07:12:52Z"	--- dataset_info: features: - name: audio dtype: audio - name: transcriptions dtype: string splits: - name: train num_bytes: 114253169328.11655 num_examples: 474332 - name: test num_bytes: 39048725811.21545 num_examples: 158111 download_size: 147662822982 dataset_size: 153301895139.332 --- # Dataset Card for "shrutilipi_mr" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
google/IFEval	google	"2024-08-14T08:21:56Z"	17,851	64	[ "task_categories:text-generation", "language:en", "license:apache-2.0", "size_categories:n<1K", "format:json", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "arxiv:2311.07911", "region:us" ]	[ "text-generation" ]	"2023-12-22T11:20:03Z"	--- license: apache-2.0 task_categories: - text-generation language: - en pretty_name: IFEval --- # Dataset Card for IFEval <!-- Provide a quick summary of the dataset. --> ## Dataset Description - Repository: https://github.com/google-research/google-research/tree/master/instruction_following_eval - Paper: https://huggingface.co/papers/2311.07911 - Leaderboard: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard - Point of Contact: [Le Hou]([email protected]) ### Dataset Summary This dataset contains the prompts used in the [Instruction-Following Eval (IFEval) benchmark](https://arxiv.org/abs/2311.07911) for large language models. It contains around 500 "verifiable instructions" such as "write in more than 400 words" and "mention the keyword of AI at least 3 times" which can be verified by heuristics. To load the dataset, run: ```python from datasets import load_dataset ifeval = load_dataset("google/IFEval") ``` ### Supported Tasks and Leaderboards The IFEval dataset is designed for evaluating chat or instruction fine-tuned language models and is one of the core benchmarks used in the [Open LLM Leaderboard](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard). ### Languages The data in IFEval are in English (BCP-47 en). ## Dataset Structure ### Data Instances An example of the `train` split looks as follows: ``` { "key": 1000, "prompt": 'Write a 300+ word summary of the wikipedia page "https://en.wikipedia.org/wiki/Raymond_III,_Count_of_Tripoli". Do not use any commas and highlight at least 3 sections that has titles in markdown format, for example highlighted section part 1, highlighted section part 2, highlighted section part 3.', "instruction_id_list": [ "punctuation:no_comma", "detectable_format:number_highlighted_sections", "length_constraints:number_words", ], "kwargs": [ { "num_highlights": None, "relation": None, "num_words": None, "num_placeholders": None, "prompt_to_repeat": None, "num_bullets": None, "section_spliter": None, "num_sections": None, "capital_relation": None, "capital_frequency": None, "keywords": None, "num_paragraphs": None, "language": None, "let_relation": None, "letter": None, "let_frequency": None, "end_phrase": None, "forbidden_words": None, "keyword": None, "frequency": None, "num_sentences": None, "postscript_marker": None, "first_word": None, "nth_paragraph": None, }, { "num_highlights": 3, "relation": None, "num_words": None, "num_placeholders": None, "prompt_to_repeat": None, "num_bullets": None, "section_spliter": None, "num_sections": None, "capital_relation": None, "capital_frequency": None, "keywords": None, "num_paragraphs": None, "language": None, "let_relation": None, "letter": None, "let_frequency": None, "end_phrase": None, "forbidden_words": None, "keyword": None, "frequency": None, "num_sentences": None, "postscript_marker": None, "first_word": None, "nth_paragraph": None, }, { "num_highlights": None, "relation": "at least", "num_words": 300, "num_placeholders": None, "prompt_to_repeat": None, "num_bullets": None, "section_spliter": None, "num_sections": None, "capital_relation": None, "capital_frequency": None, "keywords": None, "num_paragraphs": None, "language": None, "let_relation": None, "letter": None, "let_frequency": None, "end_phrase": None, "forbidden_words": None, "keyword": None, "frequency": None, "num_sentences": None, "postscript_marker": None, "first_word": None, "nth_paragraph": None, }, ], } ``` ### Data Fields The data fields are as follows: * `key`: A unique ID for the prompt. * `prompt`: Describes the task the model should perform. * `instruction_id_list`: An array of verifiable instructions. See Table 1 of the paper for the full set with their descriptions. * `kwargs`: An array of arguments used to specify each verifiable instruction in `instruction_id_list`. ### Data Splits \| \| train \| \|---------------\|------:\| \| IFEval \| 541 \| ### Licensing Information The dataset is available under the [Apache 2.0 license](https://www.apache.org/licenses/LICENSE-2.0). ### Citation Information ``` @misc{zhou2023instructionfollowingevaluationlargelanguage, title={Instruction-Following Evaluation for Large Language Models}, author={Jeffrey Zhou and Tianjian Lu and Swaroop Mishra and Siddhartha Brahma and Sujoy Basu and Yi Luan and Denny Zhou and Le Hou}, year={2023}, eprint={2311.07911}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2311.07911}, } ```
mythicinfinity/libritts	mythicinfinity	"2024-02-09T21:19:32Z"	17,754	14	[ "task_categories:text-to-speech", "language:en", "license:cc-by-4.0", "size_categories:100K<n<1M", "format:parquet", "modality:audio", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "arxiv:1904.02882", "region:us" ]	[ "text-to-speech" ]	"2024-02-08T02:07:23Z"	--- license: cc-by-4.0 task_categories: - text-to-speech language: - en size_categories: - 10K<n<100K configs: - config_name: dev data_files: - split: dev.clean path: "data/dev.clean/dev.clean.parquet" - config_name: clean data_files: - split: dev.clean path: "data/dev.clean/dev.clean.parquet" - split: test.clean path: "data/test.clean/test.clean.parquet" - split: train.clean.100 path: "data/train.clean.100/train.clean.100.parquet" - split: train.clean.360 path: "data/train.clean.360/train.clean.360.parquet" - config_name: other data_files: - split: dev.other path: "data/dev.other/dev.other.parquet" - split: test.other path: "data/test.other/test.other.parquet" - split: train.other.500 path: "data/train.other.500/train.other.500.parquet" - config_name: all data_files: - split: dev.clean path: "data/dev.clean/dev.clean.parquet" - split: dev.other path: "data/dev.other/dev.other.parquet" - split: test.clean path: "data/test.clean/test.clean.parquet" - split: test.other path: "data/test.other/test.other.parquet" - split: train.clean.100 path: "data/train.clean.100/train.clean.100.parquet" - split: train.clean.360 path: "data/train.clean.360/train.clean.360.parquet" - split: train.other.500 path: "data/train.other.500/train.other.500.parquet" --- # Dataset Card for LibriTTS <!-- Provide a quick summary of the dataset. --> LibriTTS is a multi-speaker English corpus of approximately 585 hours of read English speech at 24kHz sampling rate, prepared by Heiga Zen with the assistance of Google Speech and Google Brain team members. The LibriTTS corpus is designed for TTS research. It is derived from the original materials (mp3 audio files from LibriVox and text files from Project Gutenberg) of the LibriSpeech corpus. ## Overview This is the LibriTTS dataset, adapted for the `datasets` library. ## Usage ### Splits There are 7 splits (dots replace dashes from the original dataset, to comply with hf naming requirements): - dev.clean - dev.other - test.clean - test.other - train.clean.100 - train.clean.360 - train.other.500 ### Configurations There are 3 configurations, each which limits the splits the `load_dataset()` function will download. The default configuration is "all". - "dev": only the "dev.clean" split (good for testing the dataset quickly) - "clean": contains only "clean" splits - "other": contains only "other" splits - "all": contains only "all" splits ### Example Loading the `clean` config with only the `train.clean.360` split. ``` load_dataset("blabble-io/libritts", "clean", split="train.clean.100") ``` Streaming is also supported. ``` load_dataset("blabble-io/libritts", streaming=True) ``` ### Columns ``` { "audio": datasets.Audio(sampling_rate=24_000), "text_normalized": datasets.Value("string"), "text_original": datasets.Value("string"), "speaker_id": datasets.Value("string"), "path": datasets.Value("string"), "chapter_id": datasets.Value("string"), "id": datasets.Value("string"), } ``` ### Example Row ``` { 'audio': { 'path': '/home/user/.cache/huggingface/datasets/downloads/extracted/5551a515e85b9e463062524539c2e1cb52ba32affe128dffd866db0205248bdd/LibriTTS/dev-clean/3081/166546/3081_166546_000028_000002.wav', 'array': ..., 'sampling_rate': 24000 }, 'text_normalized': 'How quickly he disappeared!"', 'text_original': 'How quickly he disappeared!"', 'speaker_id': '3081', 'path': '/home/user/.cache/huggingface/datasets/downloads/extracted/5551a515e85b9e463062524539c2e1cb52ba32affe128dffd866db0205248bdd/LibriTTS/dev-clean/3081/166546/3081_166546_000028_000002.wav', 'chapter_id': '166546', 'id': '3081_166546_000028_000002' } ``` ## Dataset Details ### Dataset Description - License:* CC BY 4.0 ### Dataset Sources [optional] <!-- Provide the basic links for the dataset. --> - Homepage: https://www.openslr.org/60/ - Paper: https://arxiv.org/abs/1904.02882 ## Citation <!-- If there is a paper or blog post introducing the dataset, the APA and Bibtex information for that should go in this section. --> ``` @ARTICLE{Zen2019-kz, title = "{LibriTTS}: A corpus derived from {LibriSpeech} for text-to-speech", author = "Zen, Heiga and Dang, Viet and Clark, Rob and Zhang, Yu and Weiss, Ron J and Jia, Ye and Chen, Zhifeng and Wu, Yonghui", abstract = "This paper introduces a new speech corpus called ``LibriTTS'' designed for text-to-speech use. It is derived from the original audio and text materials of the LibriSpeech corpus, which has been used for training and evaluating automatic speech recognition systems. The new corpus inherits desired properties of the LibriSpeech corpus while addressing a number of issues which make LibriSpeech less than ideal for text-to-speech work. The released corpus consists of 585 hours of speech data at 24kHz sampling rate from 2,456 speakers and the corresponding texts. Experimental results show that neural end-to-end TTS models trained from the LibriTTS corpus achieved above 4.0 in mean opinion scores in naturalness in five out of six evaluation speakers. The corpus is freely available for download from http://www.openslr.org/60/.", month = apr, year = 2019, copyright = "http://arxiv.org/licenses/nonexclusive-distrib/1.0/", archivePrefix = "arXiv", primaryClass = "cs.SD", eprint = "1904.02882" } ```
Helsinki-NLP/opus_openoffice	Helsinki-NLP	"2024-02-22T15:14:50Z"	17,712	7	[ "task_categories:translation", "annotations_creators:found", "language_creators:found", "multilinguality:multilingual", "source_datasets:original", "language:de", "language:en", "language:es", "language:fr", "language:ja", "language:ru", "language:sv", "language:zh", "license:unknown", "size_categories:1M<n<10M", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]	[ "translation" ]	"2022-03-02T23:29:22Z"	--- annotations_creators: - found language_creators: - found language: - de - en - es - fr - ja - ru - sv - zh license: - unknown multilinguality: - multilingual size_categories: - 10K<n<100K source_datasets: - original task_categories: - translation task_ids: [] pretty_name: OpusOpenoffice config_names: - de-en_GB - de-es - de-fr - de-ja - de-ru - de-sv - de-zh_CN - en_GB-es - en_GB-fr - en_GB-ja - en_GB-ru - en_GB-sv - en_GB-zh_CN - es-fr - es-ja - es-ru - es-sv - es-zh_CN - fr-ja - fr-ru - fr-sv - fr-zh_CN - ja-ru - ja-sv - ja-zh_CN - ru-sv - ru-zh_CN - sv-zh_CN language_bcp47: - en-GB - zh-CN dataset_info: - config_name: de-en_GB features: - name: translation dtype: translation: languages: - de - en_GB splits: - name: train num_bytes: 6201077 num_examples: 77052 download_size: 2983173 dataset_size: 6201077 - config_name: de-es features: - name: translation dtype: translation: languages: - de - es splits: - name: train num_bytes: 6571615 num_examples: 77000 download_size: 3145841 dataset_size: 6571615 - config_name: de-fr features: - name: translation dtype: translation: languages: - de - fr splits: - name: train num_bytes: 6715805 num_examples: 76684 download_size: 3167189 dataset_size: 6715805 - config_name: de-ja features: - name: translation dtype: translation: languages: - de - ja splits: - name: train num_bytes: 7084951 num_examples: 69396 download_size: 3137719 dataset_size: 7084951 - config_name: de-ru features: - name: translation dtype: translation: languages: - de - ru splits: - name: train num_bytes: 8333241 num_examples: 75511 download_size: 3585304 dataset_size: 8333241 - config_name: de-sv features: - name: translation dtype: translation: languages: - de - sv splits: - name: train num_bytes: 6288962 num_examples: 77366 download_size: 3053987 dataset_size: 6288962 - config_name: de-zh_CN features: - name: translation dtype: translation: languages: - de - zh_CN splits: - name: train num_bytes: 5836628 num_examples: 68712 download_size: 2862703 dataset_size: 5836628 - config_name: en_GB-es features: - name: translation dtype: translation: languages: - en_GB - es splits: - name: train num_bytes: 6147581 num_examples: 77646 download_size: 2933203 dataset_size: 6147581 - config_name: en_GB-fr features: - name: translation dtype: translation: languages: - en_GB - fr splits: - name: train num_bytes: 6297779 num_examples: 77696 download_size: 2952170 dataset_size: 6297779 - config_name: en_GB-ja features: - name: translation dtype: translation: languages: - en_GB - ja splits: - name: train num_bytes: 6636722 num_examples: 69149 download_size: 2920159 dataset_size: 6636722 - config_name: en_GB-ru features: - name: translation dtype: translation: languages: - en_GB - ru splits: - name: train num_bytes: 7877970 num_examples: 75401 download_size: 3356420 dataset_size: 7877970 - config_name: en_GB-sv features: - name: translation dtype: translation: languages: - en_GB - sv splits: - name: train num_bytes: 5861461 num_examples: 77815 download_size: 2839624 dataset_size: 5861461 - config_name: en_GB-zh_CN features: - name: translation dtype: translation: languages: - en_GB - zh_CN splits: - name: train num_bytes: 5424865 num_examples: 69400 download_size: 2663377 dataset_size: 5424865 - config_name: es-fr features: - name: translation dtype: translation: languages: - es - fr splits: - name: train num_bytes: 6663092 num_examples: 77417 download_size: 3115129 dataset_size: 6663092 - config_name: es-ja features: - name: translation dtype: translation: languages: - es - ja splits: - name: train num_bytes: 7005123 num_examples: 68944 download_size: 3075174 dataset_size: 7005123 - config_name: es-ru features: - name: translation dtype: translation: languages: - es - ru splits: - name: train num_bytes: 8283703 num_examples: 76461 download_size: 3533017 dataset_size: 8283703 - config_name: es-sv features: - name: translation dtype: translation: languages: - es - sv splits: - name: train num_bytes: 6232466 num_examples: 77825 download_size: 2999454 dataset_size: 6232466 - config_name: es-zh_CN features: - name: translation dtype: translation: languages: - es - zh_CN splits: - name: train num_bytes: 5776827 num_examples: 68583 download_size: 2815094 dataset_size: 5776827 - config_name: fr-ja features: - name: translation dtype: translation: languages: - fr - ja splits: - name: train num_bytes: 7160332 num_examples: 69026 download_size: 3104825 dataset_size: 7160332 - config_name: fr-ru features: - name: translation dtype: translation: languages: - fr - ru splits: - name: train num_bytes: 8432061 num_examples: 76464 download_size: 3553215 dataset_size: 8432061 - config_name: fr-sv features: - name: translation dtype: translation: languages: - fr - sv splits: - name: train num_bytes: 6373350 num_examples: 77398 download_size: 3020247 dataset_size: 6373350 - config_name: fr-zh_CN features: - name: translation dtype: translation: languages: - fr - zh_CN splits: - name: train num_bytes: 5918482 num_examples: 68723 download_size: 2834942 dataset_size: 5918482 - config_name: ja-ru features: - name: translation dtype: translation: languages: - ja - ru splits: - name: train num_bytes: 8781230 num_examples: 68589 download_size: 3534714 dataset_size: 8781230 - config_name: ja-sv features: - name: translation dtype: translation: languages: - ja - sv splits: - name: train num_bytes: 6709627 num_examples: 69154 download_size: 2983777 dataset_size: 6709627 - config_name: ja-zh_CN features: - name: translation dtype: translation: languages: - ja - zh_CN splits: - name: train num_bytes: 6397676 num_examples: 68953 download_size: 2877818 dataset_size: 6397676 - config_name: ru-sv features: - name: translation dtype: translation: languages: - ru - sv splits: - name: train num_bytes: 7966150 num_examples: 75560 download_size: 3425447 dataset_size: 7966150 - config_name: ru-zh_CN features: - name: translation dtype: translation: languages: - ru - zh_CN splits: - name: train num_bytes: 7393659 num_examples: 66259 download_size: 3224677 dataset_size: 7393659 - config_name: sv-zh_CN features: - name: translation dtype: translation: languages: - sv - zh_CN splits: - name: train num_bytes: 5492902 num_examples: 68846 download_size: 2722340 dataset_size: 5492902 configs: - config_name: de-en_GB data_files: - split: train path: de-en_GB/train-* - config_name: de-es data_files: - split: train path: de-es/train-* - config_name: de-fr data_files: - split: train path: de-fr/train-* - config_name: de-ja data_files: - split: train path: de-ja/train-* - config_name: de-ru data_files: - split: train path: de-ru/train-* - config_name: de-sv data_files: - split: train path: de-sv/train-* - config_name: de-zh_CN data_files: - split: train path: de-zh_CN/train-* - config_name: en_GB-es data_files: - split: train path: en_GB-es/train-* - config_name: en_GB-fr data_files: - split: train path: en_GB-fr/train-* - config_name: en_GB-ja data_files: - split: train path: en_GB-ja/train-* - config_name: en_GB-ru data_files: - split: train path: en_GB-ru/train-* - config_name: en_GB-sv data_files: - split: train path: en_GB-sv/train-* - config_name: en_GB-zh_CN data_files: - split: train path: en_GB-zh_CN/train-* - config_name: es-fr data_files: - split: train path: es-fr/train-* - config_name: es-ja data_files: - split: train path: es-ja/train-* - config_name: es-ru data_files: - split: train path: es-ru/train-* - config_name: es-sv data_files: - split: train path: es-sv/train-* - config_name: es-zh_CN data_files: - split: train path: es-zh_CN/train-* - config_name: fr-ja data_files: - split: train path: fr-ja/train-* - config_name: fr-ru data_files: - split: train path: fr-ru/train-* - config_name: fr-sv data_files: - split: train path: fr-sv/train-* - config_name: fr-zh_CN data_files: - split: train path: fr-zh_CN/train-* - config_name: ja-ru data_files: - split: train path: ja-ru/train-* - config_name: ja-sv data_files: - split: train path: ja-sv/train-* - config_name: ja-zh_CN data_files: - split: train path: ja-zh_CN/train-* - config_name: ru-sv data_files: - split: train path: ru-sv/train-* - config_name: ru-zh_CN data_files: - split: train path: ru-zh_CN/train-* - config_name: sv-zh_CN data_files: - split: train path: sv-zh_CN/train-* --- # Dataset Card for [Dataset Name] ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - Homepage: https://opus.nlpl.eu/OpenOffice/corpus/version/OpenOffice - Repository: - Paper: - Leaderboard: - Point of Contact: ### Dataset Summary A collection of documents from http://www.openoffice.org/. 8 languages, 28 bitexts ### Supported Tasks and Leaderboards The underlying task is machine translation. ### Languages [More Information Needed] ## Dataset Structure ### Data Instances [More Information Needed] ### Data Fields [More Information Needed] ### Data Splits [More Information Needed] ## Dataset Creation ### Curation Rationale [More Information Needed] ### Source Data #### Initial Data Collection and Normalization [More Information Needed] #### Who are the source language producers? [More Information Needed] ### Annotations #### Annotation process [More Information Needed] #### Who are the annotators? [More Information Needed] ### Personal and Sensitive Information [More Information Needed] ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed] ### Discussion of Biases [More Information Needed] ### Other Known Limitations [More Information Needed] ## Additional Information ### Dataset Curators [More Information Needed] ### Licensing Information [More Information Needed] ### Citation Information ``` @InProceedings{TIEDEMANN12.463, author = {J�rg Tiedemann}, title = {Parallel Data, Tools and Interfaces in OPUS}, booktitle = {Proceedings of the Eight International Conference on Language Resources and Evaluation (LREC'12)}, year = {2012}, month = {may}, date = {23-25}, address = {Istanbul, Turkey}, editor = {Nicoletta Calzolari (Conference Chair) and Khalid Choukri and Thierry Declerck and Mehmet Ugur Dogan and Bente Maegaard and Joseph Mariani and Jan Odijk and Stelios Piperidis}, publisher = {European Language Resources Association (ELRA)}, isbn = {978-2-9517408-7-7}, language = {english} } ``` ### Contributions Thanks to [@patil-suraj](https://github.com/patil-suraj) for adding this dataset.
MMMU/MMMU	MMMU	"2024-09-19T17:11:03Z"	17,684	242	[ "task_categories:question-answering", "task_categories:visual-question-answering", "task_categories:multiple-choice", "language:en", "license:apache-2.0", "size_categories:10K<n<100K", "format:parquet", "modality:image", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "arxiv:2311.16502", "region:us", "biology", "medical", "finance", "chemistry", "music", "art", "art_theory", "design", "business", "accounting", "economics", "manage", "marketing", "health", "medicine", "basic_medical_science", "clinical", "pharmacy", "public_health", "humanities", "social_science", "history", "literature", "sociology", "psychology", "science", "geography", "math", "physics", "engineering", "agriculture", "architecture", "computer_science", "electronics", "energy_and_power", "materials", "mechanical_engineering" ]	[ "question-answering", "visual-question-answering", "multiple-choice" ]	"2023-11-27T17:52:01Z"	--- language: - en license: apache-2.0 size_categories: - 10K<n<100K task_categories: - question-answering - visual-question-answering - multiple-choice pretty_name: mmmu dataset_info: - config_name: Accounting features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 262599.0 num_examples: 5 - name: validation num_bytes: 1598285.0 num_examples: 30 - name: test num_bytes: 22135625.0 num_examples: 380 download_size: 37363379 dataset_size: 23996509.0 - config_name: Agriculture features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 22082656.0 num_examples: 5 - name: validation num_bytes: 119217558.0 num_examples: 30 - name: test num_bytes: 993664077.0 num_examples: 287 download_size: 1158036990 dataset_size: 1134964291.0 - config_name: Architecture_and_Engineering features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 137750.0 num_examples: 5 - name: validation num_bytes: 721378.0 num_examples: 30 - name: test num_bytes: 16054607.0 num_examples: 551 download_size: 48763955 dataset_size: 16913735.0 - config_name: Art features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 6241184.0 num_examples: 5 - name: validation num_bytes: 29934534.0 num_examples: 30 - name: test num_bytes: 237801390.0 num_examples: 231 download_size: 585798641 dataset_size: 273977108.0 - config_name: Art_Theory features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 7435106.0 num_examples: 5 - name: validation num_bytes: 33481558.0 num_examples: 30 - name: test num_bytes: 553174647.0 num_examples: 429 download_size: 930525695 dataset_size: 594091311.0 - config_name: Basic_Medical_Science features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 814310.0 num_examples: 5 - name: validation num_bytes: 4125930.0 num_examples: 30 - name: test num_bytes: 48125891.0 num_examples: 326 download_size: 84666454 dataset_size: 53066131.0 - config_name: Biology features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 574342.0 num_examples: 5 - name: validation num_bytes: 8491863.0 num_examples: 30 - name: test num_bytes: 132966151.0 num_examples: 345 download_size: 410242502 dataset_size: 142032356.0 - config_name: Chemistry features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 262397.0 num_examples: 5 - name: validation num_bytes: 1518573.0 num_examples: 30 - name: test num_bytes: 37219529.0 num_examples: 603 download_size: 108345562 dataset_size: 39000499.0 - config_name: Clinical_Medicine features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 1467945.0 num_examples: 5 - name: validation num_bytes: 10882484.0 num_examples: 30 - name: test num_bytes: 98201863.0 num_examples: 325 download_size: 160611488 dataset_size: 110552292.0 - config_name: Computer_Science features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 440523.0 num_examples: 5 - name: validation num_bytes: 2072018.0 num_examples: 30 - name: test num_bytes: 32047381.0 num_examples: 371 download_size: 55640991 dataset_size: 34559922.0 - config_name: Design features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 2259873.0 num_examples: 5 - name: validation num_bytes: 17923120.0 num_examples: 30 - name: test num_bytes: 77676331.0 num_examples: 169 download_size: 142866617 dataset_size: 97859324.0 - config_name: Diagnostics_and_Laboratory_Medicine features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 2056117.0 num_examples: 5 - name: validation num_bytes: 37106233.0 num_examples: 30 - name: test num_bytes: 157003069.0 num_examples: 162 download_size: 603957093 dataset_size: 196165419.0 - config_name: Economics features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 171434.0 num_examples: 5 - name: validation num_bytes: 1487048.0 num_examples: 30 - name: test num_bytes: 11852300.0 num_examples: 267 download_size: 20777635 dataset_size: 13510782.0 - config_name: Electronics features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 123632.0 num_examples: 5 - name: validation num_bytes: 641377.0 num_examples: 30 - name: test num_bytes: 5717686.0 num_examples: 256 download_size: 11602832 dataset_size: 6482695.0 - config_name: Energy_and_Power features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 105006.0 num_examples: 5 - name: validation num_bytes: 1641935.0 num_examples: 30 - name: test num_bytes: 14748428.0 num_examples: 432 download_size: 35246567 dataset_size: 16495369.0 - config_name: Finance features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 296124.0 num_examples: 5 - name: validation num_bytes: 1071060.0 num_examples: 30 - name: test num_bytes: 12065803.0 num_examples: 355 download_size: 29551521 dataset_size: 13432987.0 - config_name: Geography features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 1494060.0 num_examples: 5 - name: validation num_bytes: 6671316.0 num_examples: 30 - name: test num_bytes: 137218400.0 num_examples: 565 download_size: 374766631 dataset_size: 145383776.0 - config_name: History features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 1444231.0 num_examples: 5 - name: validation num_bytes: 8819857.0 num_examples: 30 - name: test num_bytes: 115228815.0 num_examples: 278 download_size: 232549641 dataset_size: 125492903.0 - config_name: Literature features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 2451201.0 num_examples: 5 - name: validation num_bytes: 14241046.0 num_examples: 30 - name: test num_bytes: 50301541.0 num_examples: 112 download_size: 132145895 dataset_size: 66993788.0 - config_name: Manage features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 449514.0 num_examples: 5 - name: validation num_bytes: 3277436.0 num_examples: 30 - name: test num_bytes: 29963963.0 num_examples: 245 download_size: 51186888 dataset_size: 33690913.0 - config_name: Marketing features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 116960.0 num_examples: 5 - name: validation num_bytes: 1472981.0 num_examples: 30 - name: test num_bytes: 7732976.0 num_examples: 181 download_size: 13146078 dataset_size: 9322917.0 - config_name: Materials features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 239632.0 num_examples: 5 - name: validation num_bytes: 2305223.0 num_examples: 30 - name: test num_bytes: 25256854.0 num_examples: 458 download_size: 105773156 dataset_size: 27801709.0 - config_name: Math features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 175839.0 num_examples: 5 - name: validation num_bytes: 1444496.0 num_examples: 30 - name: test num_bytes: 27701845.0 num_examples: 505 download_size: 174098418 dataset_size: 29322180.0 - config_name: Mechanical_Engineering features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 152542.0 num_examples: 5 - name: validation num_bytes: 874988.0 num_examples: 30 - name: test num_bytes: 15093746.0 num_examples: 429 download_size: 30450114 dataset_size: 16121276.0 - config_name: Music features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 1417615.0 num_examples: 5 - name: validation num_bytes: 9359372.0 num_examples: 30 - name: test num_bytes: 134096770.0 num_examples: 334 download_size: 174725052 dataset_size: 144873757.0 - config_name: Pharmacy features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 207924.0 num_examples: 5 - name: validation num_bytes: 1656342.0 num_examples: 30 - name: test num_bytes: 31866248.0 num_examples: 430 download_size: 62721263 dataset_size: 33730514.0 - config_name: Physics features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 233734.0 num_examples: 5 - name: validation num_bytes: 1114130.0 num_examples: 30 - name: test num_bytes: 15905705.0 num_examples: 408 download_size: 35238571 dataset_size: 17253569.0 - config_name: Psychology features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 600864.0 num_examples: 5 - name: validation num_bytes: 4403886.0 num_examples: 30 - name: test num_bytes: 53813915.0 num_examples: 305 download_size: 102466671 dataset_size: 58818665.0 - config_name: Public_Health features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 234781.0 num_examples: 5 - name: validation num_bytes: 1508761.0 num_examples: 30 - name: test num_bytes: 32150088.0 num_examples: 509 download_size: 48231609 dataset_size: 33893630.0 - config_name: Sociology features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 3769220.0 num_examples: 5 - name: validation num_bytes: 18455336.0 num_examples: 30 - name: test num_bytes: 144301123.0 num_examples: 252 download_size: 310313826 dataset_size: 166525679.0 configs: - config_name: Accounting data_files: - split: dev path: Accounting/dev-* - split: validation path: Accounting/validation-* - split: test path: Accounting/test-* - config_name: Agriculture data_files: - split: dev path: Agriculture/dev-* - split: validation path: Agriculture/validation-* - split: test path: Agriculture/test-* - config_name: Architecture_and_Engineering data_files: - split: dev path: Architecture_and_Engineering/dev-* - split: validation path: Architecture_and_Engineering/validation-* - split: test path: Architecture_and_Engineering/test-* - config_name: Art data_files: - split: dev path: Art/dev-* - split: validation path: Art/validation-* - split: test path: Art/test-* - config_name: Art_Theory data_files: - split: dev path: Art_Theory/dev-* - split: validation path: Art_Theory/validation-* - split: test path: Art_Theory/test-* - config_name: Basic_Medical_Science data_files: - split: dev path: Basic_Medical_Science/dev-* - split: validation path: Basic_Medical_Science/validation-* - split: test path: Basic_Medical_Science/test-* - config_name: Biology data_files: - split: dev path: Biology/dev-* - split: validation path: Biology/validation-* - split: test path: Biology/test-* - config_name: Chemistry data_files: - split: dev path: Chemistry/dev-* - split: validation path: Chemistry/validation-* - split: test path: Chemistry/test-* - config_name: Clinical_Medicine data_files: - split: dev path: Clinical_Medicine/dev-* - split: validation path: Clinical_Medicine/validation-* - split: test path: Clinical_Medicine/test-* - config_name: Computer_Science data_files: - split: dev path: Computer_Science/dev-* - split: validation path: Computer_Science/validation-* - split: test path: Computer_Science/test-* - config_name: Design data_files: - split: dev path: Design/dev-* - split: validation path: Design/validation-* - split: test path: Design/test-* - config_name: Diagnostics_and_Laboratory_Medicine data_files: - split: dev path: Diagnostics_and_Laboratory_Medicine/dev-* - split: validation path: Diagnostics_and_Laboratory_Medicine/validation-* - split: test path: Diagnostics_and_Laboratory_Medicine/test-* - config_name: Economics data_files: - split: dev path: Economics/dev-* - split: validation path: Economics/validation-* - split: test path: Economics/test-* - config_name: Electronics data_files: - split: dev path: Electronics/dev-* - split: validation path: Electronics/validation-* - split: test path: Electronics/test-* - config_name: Energy_and_Power data_files: - split: dev path: Energy_and_Power/dev-* - split: validation path: Energy_and_Power/validation-* - split: test path: Energy_and_Power/test-* - config_name: Finance data_files: - split: dev path: Finance/dev-* - split: validation path: Finance/validation-* - split: test path: Finance/test-* - config_name: Geography data_files: - split: dev path: Geography/dev-* - split: validation path: Geography/validation-* - split: test path: Geography/test-* - config_name: History data_files: - split: dev path: History/dev-* - split: validation path: History/validation-* - split: test path: History/test-* - config_name: Literature data_files: - split: dev path: Literature/dev-* - split: validation path: Literature/validation-* - split: test path: Literature/test-* - config_name: Manage data_files: - split: dev path: Manage/dev-* - split: validation path: Manage/validation-* - split: test path: Manage/test-* - config_name: Marketing data_files: - split: dev path: Marketing/dev-* - split: validation path: Marketing/validation-* - split: test path: Marketing/test-* - config_name: Materials data_files: - split: dev path: Materials/dev-* - split: validation path: Materials/validation-* - split: test path: Materials/test-* - config_name: Math data_files: - split: dev path: Math/dev-* - split: validation path: Math/validation-* - split: test path: Math/test-* - config_name: Mechanical_Engineering data_files: - split: dev path: Mechanical_Engineering/dev-* - split: validation path: Mechanical_Engineering/validation-* - split: test path: Mechanical_Engineering/test-* - config_name: Music data_files: - split: dev path: Music/dev-* - split: validation path: Music/validation-* - split: test path: Music/test-* - config_name: Pharmacy data_files: - split: dev path: Pharmacy/dev-* - split: validation path: Pharmacy/validation-* - split: test path: Pharmacy/test-* - config_name: Physics data_files: - split: dev path: Physics/dev-* - split: validation path: Physics/validation-* - split: test path: Physics/test-* - config_name: Psychology data_files: - split: dev path: Psychology/dev-* - split: validation path: Psychology/validation-* - split: test path: Psychology/test-* - config_name: Public_Health data_files: - split: dev path: Public_Health/dev-* - split: validation path: Public_Health/validation-* - split: test path: Public_Health/test-* - config_name: Sociology data_files: - split: dev path: Sociology/dev-* - split: validation path: Sociology/validation-* - split: test path: Sociology/test-* tags: - biology - medical - finance - chemistry - music - art - art_theory - design - music - business - accounting - economics - finance - manage - marketing - health - medicine - basic_medical_science - clinical - pharmacy - public_health - humanities - social_science - history - literature - sociology - psychology - science - biology - chemistry - geography - math - physics - engineering - agriculture - architecture - computer_science - electronics - energy_and_power - materials - mechanical_engineering --- # MMMU (A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI) [🌐 Homepage](https://mmmu-benchmark.github.io/) \| [🏆 Leaderboard](https://mmmu-benchmark.github.io/#leaderboard) \| [🤗 Dataset](https://huggingface.co/datasets/MMMU/MMMU/) \| [🤗 Paper](https://huggingface.co/papers/2311.16502) \| [📖 arXiv](https://arxiv.org/abs/2311.16502) \| [GitHub](https://github.com/MMMU-Benchmark/MMMU) ## 🔔News - 🛠️[2024-05-30]: Fixed duplicate option issues in Materials dataset items (validation_Materials_25; test_Materials_17, 242) and content error in validation_Materials_25. - 🛠️[2024-04-30]: Fixed missing "-" or "^" signs in Math dataset items (dev_Math_2, validation_Math_11, 12, 16; test_Math_8, 23, 43, 113, 164, 223, 236, 287, 329, 402, 498) and corrected option errors in validation_Math_2. If you encounter any issues with the dataset, please contact us promptly! - 🚀[2024-01-31]: We added Human Expert performance on the [Leaderboard](https://mmmu-benchmark.github.io/#leaderboard)!🌟 - 🔥[2023-12-04]: Our evaluation server for test set is now availble on [EvalAI](https://eval.ai/web/challenges/challenge-page/2179/overview). We welcome all submissions and look forward to your participation! 😆 ## Dataset Details ### Dataset Description We introduce MMMU: a new benchmark designed to evaluate multimodal models on massive multi-discipline tasks demanding college-level subject knowledge and deliberate reasoning. MMMU includes 11.5K meticulously collected multimodal questions from college exams, quizzes, and textbooks, covering six core disciplines: Art & Design, Business, Science, Health & Medicine, Humanities & Social Science, and Tech & Engineering. These questions span 30 subjects and 183 subfields, comprising 30 highly heterogeneous image types, such as charts, diagrams, maps, tables, music sheets, and chemical structures. We believe MMMU will stimulate the community to build next-generation multimodal foundation models towards expert artificial general intelligence (AGI). 🎯 We have released a full set comprising 150 development samples and 900 validation samples. We have released 10,500 test questions without their answers. The development set is used for few-shot/in-context learning, and the validation set is used for debugging models, selecting hyperparameters, or quick evaluations. The answers and explanations for the test set questions are withheld. You can submit your model's predictions for the test set on [EvalAI](https://eval.ai/web/challenges/challenge-page/2179/overview). ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6230d750d93e84e233882dbc/2Ulh9yznm1dvISV4xJ_Ok.png) ### Dataset Creation MMMU was created to challenge multimodal models with tasks that demand college-level subject knowledge and deliberate reasoning, pushing the boundaries of what these models can achieve in terms of expert-level perception and reasoning. The data for the MMMU dataset was manually collected by a team of college students from various disciplines, using online sources, textbooks, and lecture materials. - Content: The dataset contains 11.5K college-level problems across six broad disciplines (Art & Design, Business, Science, Health & Medicine, Humanities & Social Science, Tech & Engineering) and 30 college subjects. - Image Types: The dataset includes 30 highly heterogeneous image types, such as charts, diagrams, maps, tables, music sheets, and chemical structures, interleaved with text. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6230d750d93e84e233882dbc/Mbf8O5lEH8I8czprch0AG.png) ## 🏆 Mini-Leaderboard We show a mini-leaderboard here and please find more information in our paper or [homepage](https://mmmu-benchmark.github.io/). \| Model \| Val (900) \| Test (10.5K) \| \|--------------------------------\|:---------:\|:------------:\| \| Expert (Best) \| 88.6 \| - \| \| Expert (Medium) \| 82.6 \| - \| \| Expert (Worst) \| 76.2 \| - \| \| GPT-4o* \| 69.1 \| - \| \| Gemini 1.5 Pro* \| 62.2 \| - \| \| InternVL2-Pro* \| 62.0 \| 55.7 \| \| Gemini 1.0 Ultra* \| 59.4 \| - \| \| Claude 3 Opus* \| 59.4 \| - \| \| GPT-4V(ision) (Playground) \| 56.8 \| 55.7 \| \| Reka Core* \| 56.3 \| - \| \| Gemini 1.5 Flash* \| 56.1 \| - \| \| SenseChat-Vision-0423-Preview* \| 54.6 \| 50.3 \| \| Reka Flash* \| 53.3 \| - \| \| Claude 3 Sonnet* \| 53.1 \| - \| \| HPT Pro* \| 52.0 \| - \| \| VILA1.5* \| 51.9 \| 46.9 \| \| Qwen-VL-MAX* \| 51.4 \| 46.8 \| \| InternVL-Chat-V1.2* \| 51.6 \| 46.2 \| \| Skywork-VL* \| 51.4 \| 46.2 \| \| LLaVA-1.6-34B* \| 51.1 \| 44.7 \| \| Claude 3 Haiku* \| 50.2 \| - \| \| Adept Fuyu-Heavy* \| 48.3 \| - \| \| Gemini 1.0 Pro* \| 47.9 \| - \| \| Marco-VL-Plus* \| 46.2 \| 44.3 \| \| Yi-VL-34B* \| 45.9 \| 41.6 \| \| Qwen-VL-PLUS* \| 45.2 \| 40.8 \| \| HPT Air* \| 44.0 \| - \| \| Reka Edge* \| 42.8 \| - \| \| Marco-VL* \| 41.2 \| 40.4 \| \| OmniLMM-12B* \| 41.1 \| 40.4 \| \| Bunny-8B* \| 43.3 \| 39.0 \| \| Bunny-4B* \| 41.4 \| 38.4 \| \| Weitu-VL-1.0-15B* \| - \| 38.4 \| \| InternLM-XComposer2-VL* \| 43.0 \| 38.2 \| \| Yi-VL-6B* \| 39.1 \| 37.8 \| \| InfiMM-Zephyr-7B* \| 39.4 \| 35.5 \| \| InternVL-Chat-V1.1* \| 39.1 \| 35.3 \| \| Math-LLaVA-13B* \| 38.3 \| 34.6 \| \| SVIT* \| 38.0 \| 34.1 \| \| MiniCPM-V* \| 37.2 \| 34.1 \| \| MiniCPM-V-2* \| 37.1 \| - \| \| Emu2-Chat* \| 36.3 \| 34.1 \| \| BLIP-2 FLAN-T5-XXL \| 35.4 \| 34.0 \| \| InstructBLIP-T5-XXL \| 35.7 \| 33.8 \| \| LLaVA-1.5-13B \| 36.4 \| 33.6 \| \| Bunny-3B* \| 38.2 \| 33.0 \| \| Qwen-VL-7B-Chat \| 35.9 \| 32.9 \| \| SPHINX* \| 32.9 \| 32.9 \| \| mPLUG-OWL2* \| 32.7 \| 32.1 \| \| BLIP-2 FLAN-T5-XL \| 34.4 \| 31.0 \| \| InstructBLIP-T5-XL \| 32.9 \| 30.6 \| \| Gemini Nano2* \| 32.6 \| - \| \| CogVLM \| 32.1 \| 30.1 \| \| Otter \| 32.2 \| 29.1 \| \| LLaMA-Adapter2-7B \| 29.8 \| 27.7 \| \| MiniGPT4-Vicuna-13B \| 26.8 \| 27.6 \| \| Adept Fuyu-8B \| 27.9 \| 27.4 \| \| Kosmos2 \| 24.4 \| 26.6 \| \| OpenFlamingo2-9B \| 28.7 \| 26.3 \| \| Frequent Choice \| 22.1 \| 23.9 \| \| Random Choice \| 26.8 \| 25.8 \| : results provided by the authors. ## Limitations Despite its comprehensive nature, MMMU, like any benchmark, is not without limitations. The manual curation process, albeit thorough, may carry biases. And the focus on college-level subjects might not fully be a sufficient test for Expert AGI. However, we believe it should be necessary for an Expert AGI to achieve strong performance on MMMU to demonstrate their broad and deep subject knowledge as well as expert-level understanding and reasoning capabilities. In future work, we plan to incorporate human evaluations into MMMU. This will provide a more grounded comparison between model capabilities and expert performance, shedding light on the proximity of current AI systems to achieving Expert AGI. ## Disclaimers The guidelines for the annotators emphasized strict compliance with copyright and licensing rules from the initial data source, specifically avoiding materials from websites that forbid copying and redistribution. Should you encounter any data samples potentially breaching the copyright or licensing regulations of any site, we encourage you to notify us. Upon verification, such samples will be promptly removed. ## Contact - Xiang Yue: [email protected] - Yu Su: [email protected] - Wenhu Chen: [email protected] ## Citation BibTeX:* ```bibtex @inproceedings{yue2023mmmu, title={MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI}, author={Xiang Yue and Yuansheng Ni and Kai Zhang and Tianyu Zheng and Ruoqi Liu and Ge Zhang and Samuel Stevens and Dongfu Jiang and Weiming Ren and Yuxuan Sun and Cong Wei and Botao Yu and Ruibin Yuan and Renliang Sun and Ming Yin and Boyuan Zheng and Zhenzhu Yang and Yibo Liu and Wenhao Huang and Huan Sun and Yu Su and Wenhu Chen}, booktitle={Proceedings of CVPR}, year={2024}, } ```
sggetao/PwC	sggetao	"2024-03-30T20:03:44Z"	17,618	3	[ "license:apache-2.0", "size_categories:100K<n<1M", "format:json", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]	null	"2024-03-30T20:01:08Z"	--- license: apache-2.0 ---
alvations/c4p0-x1-en-es	alvations	"2024-03-24T03:55:08Z"	17,528	0	[ "size_categories:n<1K", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]	null	"2024-03-23T10:03:20Z"	--- dataset_info: features: - name: source dtype: string - name: target dtype: string - name: target_backto_source dtype: string - name: raw_target list: - name: generated_text dtype: string - name: raw_target_backto_source list: - name: generated_text dtype: string - name: prompt dtype: string - name: reverse_prompt dtype: string - name: source_langid dtype: string - name: target_langid dtype: string - name: target_backto_source_langid dtype: string - name: doc_id dtype: int64 - name: sent_id dtype: int64 - name: timestamp dtype: string - name: url dtype: string - name: doc_hash dtype: string splits: - name: train num_bytes: 2308 num_examples: 2 download_size: 15489 dataset_size: 2308 configs: - config_name: default data_files: - split: train path: 1f24f16745a166b0/train-* ---
weizhiwang/Open-Qwen2VL-Data	weizhiwang	"2025-04-03T02:23:45Z"	17,528	9	[ "task_categories:image-text-to-text", "size_categories:10M<n<100M", "format:parquet", "modality:image", "modality:tabular", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "arxiv:2504.00595", "region:us" ]	[ "image-text-to-text" ]	"2024-09-27T06:48:06Z"	--- task_categories: - image-text-to-text --- This repository contains the data for [Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources](https://huggingface.co/papers/2504.00595). Project page: https://victorwz.github.io/Open-Qwen2VL Code: https://github.com/Victorwz/Open-Qwen2VL
lmms-lab/GQA	lmms-lab	"2024-03-08T05:02:22Z"	17,310	14	[ "license:mit", "size_categories:10M<n<100M", "format:parquet", "modality:image", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]	null	"2023-12-26T13:11:16Z"	--- license: mit dataset_info: - config_name: challenge_all_images features: - name: id dtype: string - name: image dtype: image splits: - name: challenge num_bytes: 261636425.25 num_examples: 1590 download_size: 261271928 dataset_size: 261636425.25 - config_name: challenge_all_instructions features: - name: id dtype: string - name: imageId dtype: string - name: question dtype: string - name: isBalanced dtype: bool splits: - name: challenge num_bytes: 50797705 num_examples: 713449 download_size: 19869828 dataset_size: 50797705 - config_name: challenge_balanced_images features: - name: id dtype: string - name: image dtype: image splits: - name: challenge num_bytes: 261636425.25 num_examples: 1590 download_size: 261333538 dataset_size: 261636425.25 - config_name: challenge_balanced_instructions features: - name: id dtype: string - name: imageId dtype: string - name: question dtype: string - name: isBalanced dtype: bool splits: - name: challenge num_bytes: 3523973 num_examples: 50726 download_size: 1787024 dataset_size: 3523973 - config_name: submission_all_images features: - name: id dtype: string - name: image dtype: image splits: - name: submission num_bytes: 2314978438.875 num_examples: 15545 download_size: 2309217874 dataset_size: 2314978438.875 - config_name: submission_all_instructions features: - name: id dtype: string - name: imageId dtype: string - name: question dtype: string - name: isBalanced dtype: bool splits: - name: submission num_bytes: 298875520 num_examples: 4237524 download_size: 121458425 dataset_size: 298875520 - config_name: test_all_images features: - name: id dtype: string - name: image dtype: image splits: - name: test num_bytes: 492571840.875 num_examples: 2993 download_size: 491611526 dataset_size: 492571840.875 - config_name: test_all_instructions features: - name: id dtype: string - name: imageId dtype: string - name: question dtype: string - name: isBalanced dtype: bool splits: - name: test num_bytes: 95588974 num_examples: 1340048 download_size: 39561711 dataset_size: 95588974 - config_name: test_balanced_images features: - name: id dtype: string - name: image dtype: image splits: - name: test num_bytes: 491210370.625 num_examples: 2987 download_size: 490293506 dataset_size: 491210370.625 - config_name: test_balanced_instructions features: - name: id dtype: string - name: imageId dtype: string - name: question dtype: string - name: isBalanced dtype: bool splits: - name: test num_bytes: 6622775 num_examples: 95336 download_size: 3401070 dataset_size: 6622775 - config_name: testdev_all_images features: - name: id dtype: string - name: image dtype: image splits: - name: testdev num_bytes: 65779269.0 num_examples: 398 download_size: 65670255 dataset_size: 65779269.0 - config_name: testdev_all_instructions features: - name: id dtype: string - name: imageId dtype: string - name: question dtype: string - name: answer dtype: string - name: fullAnswer dtype: string - name: isBalanced dtype: bool - name: groups struct: - name: global dtype: string - name: local dtype: string - name: entailed dtype: string - name: equivalent dtype: string - name: types struct: - name: structural dtype: string - name: semantic dtype: string - name: detailed dtype: string - name: annotations sequence: - name: question struct: - name: objectId dtype: string - name: value dtype: string - name: answer struct: - name: objectId dtype: string - name: value dtype: string - name: fullAnswer struct: - name: objectId dtype: string - name: value dtype: string - name: semantic list: - name: operation dtype: string - name: argument dtype: string - name: dependencies sequence: int32 - name: semanticStr dtype: string splits: - name: testdev num_bytes: 86970760 num_examples: 172174 download_size: 23385535 dataset_size: 86970760 - config_name: testdev_balanced_images features: - name: id dtype: string - name: image dtype: image splits: - name: testdev num_bytes: 65779269.0 num_examples: 398 download_size: 65647745 dataset_size: 65779269.0 - config_name: testdev_balanced_instructions features: - name: id dtype: string - name: imageId dtype: string - name: question dtype: string - name: answer dtype: string - name: fullAnswer dtype: string - name: isBalanced dtype: bool - name: groups struct: - name: global dtype: string - name: local dtype: string - name: entailed dtype: string - name: equivalent dtype: string - name: types struct: - name: structural dtype: string - name: semantic dtype: string - name: detailed dtype: string - name: annotations sequence: - name: question struct: - name: objectId dtype: string - name: value dtype: string - name: answer struct: - name: objectId dtype: string - name: value dtype: string - name: fullAnswer struct: - name: objectId dtype: string - name: value dtype: string - name: semantic list: - name: operation dtype: string - name: argument dtype: string - name: dependencies sequence: int32 - name: semanticStr dtype: string splits: - name: testdev num_bytes: 6113469 num_examples: 12578 download_size: 2090335 dataset_size: 6113469 - config_name: train_all_images features: - name: id dtype: string - name: image dtype: image splits: - name: train num_bytes: 10509758457.0 num_examples: 74256 download_size: 10480239090 dataset_size: 10509758457.0 - config_name: train_all_instructions features: - name: id dtype: string - name: imageId dtype: string - name: question dtype: string - name: answer dtype: string - name: fullAnswer dtype: string - name: isBalanced dtype: bool - name: groups struct: - name: global dtype: string - name: local dtype: string - name: entailed dtype: string - name: equivalent dtype: string - name: types struct: - name: structural dtype: string - name: semantic dtype: string - name: detailed dtype: string - name: annotations sequence: - name: question struct: - name: objectId dtype: string - name: value dtype: string - name: answer struct: - name: objectId dtype: string - name: value dtype: string - name: fullAnswer struct: - name: objectId dtype: string - name: value dtype: string - name: semantic list: - name: operation dtype: string - name: argument dtype: string - name: dependencies sequence: int32 - name: semanticStr dtype: string splits: - name: train num_bytes: 6891129609 num_examples: 14305356 download_size: 1874173198 dataset_size: 6891129609 - config_name: train_balanced_images features: - name: id dtype: string - name: image dtype: image splits: - name: train num_bytes: 10200292415.5 num_examples: 72140 download_size: 10171627271 dataset_size: 10200292415.5 - config_name: train_balanced_instructions features: - name: id dtype: string - name: imageId dtype: string - name: question dtype: string - name: answer dtype: string - name: fullAnswer dtype: string - name: isBalanced dtype: bool - name: groups struct: - name: global dtype: string - name: local dtype: string - name: entailed dtype: string - name: equivalent dtype: string - name: types struct: - name: structural dtype: string - name: semantic dtype: string - name: detailed dtype: string - name: annotations sequence: - name: question struct: - name: objectId dtype: string - name: value dtype: string - name: answer struct: - name: objectId dtype: string - name: value dtype: string - name: fullAnswer struct: - name: objectId dtype: string - name: value dtype: string - name: semantic list: - name: operation dtype: string - name: argument dtype: string - name: dependencies sequence: int32 - name: semanticStr dtype: string splits: - name: train num_bytes: 460429581 num_examples: 943000 download_size: 183979778 dataset_size: 460429581 - config_name: val_all_images features: - name: id dtype: string - name: image dtype: image splits: - name: val num_bytes: 1494990904.5 num_examples: 10564 download_size: 1490744689 dataset_size: 1494990904.5 - config_name: val_all_instructions features: - name: id dtype: string - name: imageId dtype: string - name: question dtype: string - name: answer dtype: string - name: fullAnswer dtype: string - name: isBalanced dtype: bool - name: groups struct: - name: global dtype: string - name: local dtype: string - name: entailed dtype: string - name: equivalent dtype: string - name: types struct: - name: structural dtype: string - name: semantic dtype: string - name: detailed dtype: string - name: annotations sequence: - name: question struct: - name: objectId dtype: string - name: value dtype: string - name: answer struct: - name: objectId dtype: string - name: value dtype: string - name: fullAnswer struct: - name: objectId dtype: string - name: value dtype: string - name: semantic list: - name: operation dtype: string - name: argument dtype: string - name: dependencies sequence: int32 - name: semanticStr dtype: string splits: - name: val num_bytes: 967338322 num_examples: 2011853 download_size: 266476025 dataset_size: 967338322 - config_name: val_balanced_images features: - name: id dtype: string - name: image dtype: image splits: - name: val num_bytes: 1447074448.75 num_examples: 10234 download_size: 1443033919 dataset_size: 1447074448.75 - config_name: val_balanced_instructions features: - name: id dtype: string - name: imageId dtype: string - name: question dtype: string - name: answer dtype: string - name: fullAnswer dtype: string - name: isBalanced dtype: bool - name: groups struct: - name: global dtype: string - name: local dtype: string - name: entailed dtype: string - name: equivalent dtype: string - name: types struct: - name: structural dtype: string - name: semantic dtype: string - name: detailed dtype: string - name: annotations sequence: - name: question struct: - name: objectId dtype: string - name: value dtype: string - name: answer struct: - name: objectId dtype: string - name: value dtype: string - name: fullAnswer struct: - name: objectId dtype: string - name: value dtype: string - name: semantic list: - name: operation dtype: string - name: argument dtype: string - name: dependencies sequence: int32 - name: semanticStr dtype: string splits: - name: val num_bytes: 64498952 num_examples: 132062 download_size: 25794272 dataset_size: 64498952 configs: - config_name: challenge_all_images data_files: - split: challenge path: challenge_all_images/challenge-* - config_name: challenge_all_instructions data_files: - split: challenge path: challenge_all_instructions/challenge-* - config_name: challenge_balanced_images data_files: - split: challenge path: challenge_balanced_images/challenge-* - config_name: challenge_balanced_instructions data_files: - split: challenge path: challenge_balanced_instructions/challenge-* - config_name: submission_all_images data_files: - split: submission path: submission_all_images/submission-* - config_name: submission_all_instructions data_files: - split: submission path: submission_all_instructions/submission-* - config_name: test_all_images data_files: - split: test path: test_all_images/test-* - config_name: test_all_instructions data_files: - split: test path: test_all_instructions/test-* - config_name: test_balanced_images data_files: - split: test path: test_balanced_images/test-* - config_name: test_balanced_instructions data_files: - split: test path: test_balanced_instructions/test-* - config_name: testdev_all_images data_files: - split: testdev path: testdev_all_images/testdev-* - config_name: testdev_all_instructions data_files: - split: testdev path: testdev_all_instructions/testdev-* - config_name: testdev_balanced_images data_files: - split: testdev path: testdev_balanced_images/testdev-* - config_name: testdev_balanced_instructions data_files: - split: testdev path: testdev_balanced_instructions/testdev-* - config_name: train_all_images data_files: - split: train path: train_all_images/train-* - config_name: train_all_instructions data_files: - split: train path: train_all_instructions/train-* - config_name: train_balanced_images data_files: - split: train path: train_balanced_images/train-* - config_name: train_balanced_instructions data_files: - split: train path: train_balanced_instructions/train-* - config_name: val_all_images data_files: - split: val path: val_all_images/val-* - config_name: val_all_instructions data_files: - split: val path: val_all_instructions/val-* - config_name: val_balanced_images data_files: - split: val path: val_balanced_images/val-* - config_name: val_balanced_instructions data_files: - split: val path: val_balanced_instructions/val-* --- <p align="center" width="100%"> <img src="https://i.postimg.cc/g0QRgMVv/WX20240228-113337-2x.png" width="100%" height="80%"> </p> # Large-scale Multi-modality Models Evaluation Suite > Accelerating the development of large-scale multi-modality models (LMMs) with `lmms-eval` 🏠 [Homepage](https://lmms-lab.github.io/) \| 📚 [Documentation](docs/README.md) \| 🤗 [Huggingface Datasets](https://huggingface.co/lmms-lab) # This Dataset This is a formatted version of [GQA](hhttps://cs.stanford.edu/people/dorarad/gqa/about.html). It is used in our `lmms-eval` pipeline to allow for one-click evaluations of large multi-modality models. ``` @inproceedings{hudson2019gqa, title={Gqa: A new dataset for real-world visual reasoning and compositional question answering}, author={Hudson, Drew A and Manning, Christopher D}, booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition}, pages={6700--6709}, year={2019} } ```
facebook/xnli	facebook	"2024-01-05T08:30:52Z"	17,244	56	[ "language:ar", "language:bg", "language:de", "language:el", "language:en", "language:es", "language:fr", "language:hi", "language:ru", "language:sw", "language:th", "language:tr", "language:ur", "language:vi", "language:zh", "size_categories:1M<n<10M", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]	null	"2022-03-02T23:29:22Z"	--- language: - ar - bg - de - el - en - es - fr - hi - ru - sw - th - tr - ur - vi - zh paperswithcode_id: xnli pretty_name: Cross-lingual Natural Language Inference dataset_info: - config_name: all_languages features: - name: premise dtype: translation: languages: - ar - bg - de - el - en - es - fr - hi - ru - sw - th - tr - ur - vi - zh - name: hypothesis dtype: translation_variable_languages: languages: - ar - bg - de - el - en - es - fr - hi - ru - sw - th - tr - ur - vi - zh num_languages: 15 - name: label dtype: class_label: names: '0': entailment '1': neutral '2': contradiction splits: - name: train num_bytes: 1581471691 num_examples: 392702 - name: test num_bytes: 19387432 num_examples: 5010 - name: validation num_bytes: 9566179 num_examples: 2490 download_size: 963942271 dataset_size: 1610425302 - config_name: ar features: - name: premise dtype: string - name: hypothesis dtype: string - name: label dtype: class_label: names: '0': entailment '1': neutral '2': contradiction splits: - name: train num_bytes: 107399614 num_examples: 392702 - name: test num_bytes: 1294553 num_examples: 5010 - name: validation num_bytes: 633001 num_examples: 2490 download_size: 59215902 dataset_size: 109327168 - config_name: bg features: - name: premise dtype: string - name: hypothesis dtype: string - name: label dtype: class_label: names: '0': entailment '1': neutral '2': contradiction splits: - name: train num_bytes: 125973225 num_examples: 392702 - name: test num_bytes: 1573034 num_examples: 5010 - name: validation num_bytes: 774061 num_examples: 2490 download_size: 66117878 dataset_size: 128320320 - config_name: de features: - name: premise dtype: string - name: hypothesis dtype: string - name: label dtype: class_label: names: '0': entailment '1': neutral '2': contradiction splits: - name: train num_bytes: 84684140 num_examples: 392702 - name: test num_bytes: 996488 num_examples: 5010 - name: validation num_bytes: 494604 num_examples: 2490 download_size: 55973883 dataset_size: 86175232 - config_name: el features: - name: premise dtype: string - name: hypothesis dtype: string - name: label dtype: class_label: names: '0': entailment '1': neutral '2': contradiction splits: - name: train num_bytes: 139753358 num_examples: 392702 - name: test num_bytes: 1704785 num_examples: 5010 - name: validation num_bytes: 841226 num_examples: 2490 download_size: 74551247 dataset_size: 142299369 - config_name: en features: - name: premise dtype: string - name: hypothesis dtype: string - name: label dtype: class_label: names: '0': entailment '1': neutral '2': contradiction splits: - name: train num_bytes: 74444026 num_examples: 392702 - name: test num_bytes: 875134 num_examples: 5010 - name: validation num_bytes: 433463 num_examples: 2490 download_size: 50627367 dataset_size: 75752623 - config_name: es features: - name: premise dtype: string - name: hypothesis dtype: string - name: label dtype: class_label: names: '0': entailment '1': neutral '2': contradiction splits: - name: train num_bytes: 81383284 num_examples: 392702 - name: test num_bytes: 969813 num_examples: 5010 - name: validation num_bytes: 478422 num_examples: 2490 download_size: 53677157 dataset_size: 82831519 - config_name: fr features: - name: premise dtype: string - name: hypothesis dtype: string - name: label dtype: class_label: names: '0': entailment '1': neutral '2': contradiction splits: - name: train num_bytes: 85808779 num_examples: 392702 - name: test num_bytes: 1029239 num_examples: 5010 - name: validation num_bytes: 510104 num_examples: 2490 download_size: 55968680 dataset_size: 87348122 - config_name: hi features: - name: premise dtype: string - name: hypothesis dtype: string - name: label dtype: class_label: names: '0': entailment '1': neutral '2': contradiction splits: - name: train num_bytes: 170593964 num_examples: 392702 - name: test num_bytes: 2073073 num_examples: 5010 - name: validation num_bytes: 1023915 num_examples: 2490 download_size: 70908548 dataset_size: 173690952 - config_name: ru features: - name: premise dtype: string - name: hypothesis dtype: string - name: label dtype: class_label: names: '0': entailment '1': neutral '2': contradiction splits: - name: train num_bytes: 129859615 num_examples: 392702 - name: test num_bytes: 1603466 num_examples: 5010 - name: validation num_bytes: 786442 num_examples: 2490 download_size: 70702606 dataset_size: 132249523 - config_name: sw features: - name: premise dtype: string - name: hypothesis dtype: string - name: label dtype: class_label: names: '0': entailment '1': neutral '2': contradiction splits: - name: train num_bytes: 69285725 num_examples: 392702 - name: test num_bytes: 871651 num_examples: 5010 - name: validation num_bytes: 429850 num_examples: 2490 download_size: 45564152 dataset_size: 70587226 - config_name: th features: - name: premise dtype: string - name: hypothesis dtype: string - name: label dtype: class_label: names: '0': entailment '1': neutral '2': contradiction splits: - name: train num_bytes: 176062892 num_examples: 392702 - name: test num_bytes: 2147015 num_examples: 5010 - name: validation num_bytes: 1061160 num_examples: 2490 download_size: 77222045 dataset_size: 179271067 - config_name: tr features: - name: premise dtype: string - name: hypothesis dtype: string - name: label dtype: class_label: names: '0': entailment '1': neutral '2': contradiction splits: - name: train num_bytes: 71637140 num_examples: 392702 - name: test num_bytes: 934934 num_examples: 5010 - name: validation num_bytes: 459308 num_examples: 2490 download_size: 48509680 dataset_size: 73031382 - config_name: ur features: - name: premise dtype: string - name: hypothesis dtype: string - name: label dtype: class_label: names: '0': entailment '1': neutral '2': contradiction splits: - name: train num_bytes: 96441486 num_examples: 392702 - name: test num_bytes: 1416241 num_examples: 5010 - name: validation num_bytes: 699952 num_examples: 2490 download_size: 46682785 dataset_size: 98557679 - config_name: vi features: - name: premise dtype: string - name: hypothesis dtype: string - name: label dtype: class_label: names: '0': entailment '1': neutral '2': contradiction splits: - name: train num_bytes: 101417430 num_examples: 392702 - name: test num_bytes: 1190217 num_examples: 5010 - name: validation num_bytes: 590680 num_examples: 2490 download_size: 57690058 dataset_size: 103198327 - config_name: zh features: - name: premise dtype: string - name: hypothesis dtype: string - name: label dtype: class_label: names: '0': entailment '1': neutral '2': contradiction splits: - name: train num_bytes: 72224841 num_examples: 392702 - name: test num_bytes: 777929 num_examples: 5010 - name: validation num_bytes: 384851 num_examples: 2490 download_size: 48269855 dataset_size: 73387621 configs: - config_name: all_languages data_files: - split: train path: all_languages/train-* - split: test path: all_languages/test-* - split: validation path: all_languages/validation-* - config_name: ar data_files: - split: train path: ar/train-* - split: test path: ar/test-* - split: validation path: ar/validation-* - config_name: bg data_files: - split: train path: bg/train-* - split: test path: bg/test-* - split: validation path: bg/validation-* - config_name: de data_files: - split: train path: de/train-* - split: test path: de/test-* - split: validation path: de/validation-* - config_name: el data_files: - split: train path: el/train-* - split: test path: el/test-* - split: validation path: el/validation-* - config_name: en data_files: - split: train path: en/train-* - split: test path: en/test-* - split: validation path: en/validation-* - config_name: es data_files: - split: train path: es/train-* - split: test path: es/test-* - split: validation path: es/validation-* - config_name: fr data_files: - split: train path: fr/train-* - split: test path: fr/test-* - split: validation path: fr/validation-* - config_name: hi data_files: - split: train path: hi/train-* - split: test path: hi/test-* - split: validation path: hi/validation-* - config_name: ru data_files: - split: train path: ru/train-* - split: test path: ru/test-* - split: validation path: ru/validation-* - config_name: sw data_files: - split: train path: sw/train-* - split: test path: sw/test-* - split: validation path: sw/validation-* - config_name: th data_files: - split: train path: th/train-* - split: test path: th/test-* - split: validation path: th/validation-* - config_name: tr data_files: - split: train path: tr/train-* - split: test path: tr/test-* - split: validation path: tr/validation-* - config_name: ur data_files: - split: train path: ur/train-* - split: test path: ur/test-* - split: validation path: ur/validation-* - config_name: vi data_files: - split: train path: vi/train-* - split: test path: vi/test-* - split: validation path: vi/validation-* - config_name: zh data_files: - split: train path: zh/train-* - split: test path: zh/test-* - split: validation path: zh/validation-* --- # Dataset Card for "xnli" ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - Homepage: [https://www.nyu.edu/projects/bowman/xnli/](https://www.nyu.edu/projects/bowman/xnli/) - Repository: [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - Paper: [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - Point of Contact: [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - Size of downloaded dataset files: 7.74 GB - Size of the generated dataset: 3.23 GB - Total amount of disk used: 10.97 GB ### Dataset Summary XNLI is a subset of a few thousand examples from MNLI which has been translated into a 14 different languages (some low-ish resource). As with MNLI, the goal is to predict textual entailment (does sentence A imply/contradict/neither sentence B) and is a classification task (given two sentences, predict one of three labels). ### Supported Tasks and Leaderboards [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Languages [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Dataset Structure ### Data Instances #### all_languages - Size of downloaded dataset files: 483.96 MB - Size of the generated dataset: 1.61 GB - Total amount of disk used: 2.09 GB An example of 'train' looks as follows. ``` This example was too long and was cropped: { "hypothesis": "{\"language\": [\"ar\", \"bg\", \"de\", \"el\", \"en\", \"es\", \"fr\", \"hi\", \"ru\", \"sw\", \"th\", \"tr\", \"ur\", \"vi\", \"zh\"], \"translation\": [\"احد اع...", "label": 0, "premise": "{\"ar\": \"واحدة من رقابنا ستقوم بتنفيذ تعليماتك كلها بكل دقة\", \"bg\": \"един от нашите номера ще ви даде инструкции .\", \"de\": \"Eine ..." } ``` #### ar - Size of downloaded dataset files: 483.96 MB - Size of the generated dataset: 109.32 MB - Total amount of disk used: 593.29 MB An example of 'validation' looks as follows. ``` { "hypothesis": "اتصل بأمه حالما أوصلته حافلة المدرسية.", "label": 1, "premise": "وقال، ماما، لقد عدت للمنزل." } ``` #### bg - Size of downloaded dataset files: 483.96 MB - Size of the generated dataset: 128.32 MB - Total amount of disk used: 612.28 MB An example of 'train' looks as follows. ``` This example was too long and was cropped: { "hypothesis": "\"губиш нещата на следното ниво , ако хората си припомнят .\"...", "label": 0, "premise": "\"по време на сезона и предполагам , че на твоето ниво ще ги загубиш на следващото ниво , ако те решат да си припомнят отбора на ..." } ``` #### de - Size of downloaded dataset files: 483.96 MB - Size of the generated dataset: 86.17 MB - Total amount of disk used: 570.14 MB An example of 'train' looks as follows. ``` This example was too long and was cropped: { "hypothesis": "Man verliert die Dinge auf die folgende Ebene , wenn sich die Leute erinnern .", "label": 0, "premise": "\"Du weißt , während der Saison und ich schätze , auf deiner Ebene verlierst du sie auf die nächste Ebene , wenn sie sich entschl..." } ``` #### el - Size of downloaded dataset files: 483.96 MB - Size of the generated dataset: 142.30 MB - Total amount of disk used: 626.26 MB An example of 'validation' looks as follows. ``` This example was too long and was cropped: { "hypothesis": "\"Τηλεφώνησε στη μαμά του μόλις το σχολικό λεωφορείο τον άφησε.\"...", "label": 1, "premise": "Και είπε, Μαμά, έφτασα στο σπίτι." } ``` ### Data Fields The data fields are the same among all splits. #### all_languages - `premise`: a multilingual `string` variable, with possible languages including `ar`, `bg`, `de`, `el`, `en`. - `hypothesis`: a multilingual `string` variable, with possible languages including `ar`, `bg`, `de`, `el`, `en`. - `label`: a classification label, with possible values including `entailment` (0), `neutral` (1), `contradiction` (2). #### ar - `premise`: a `string` feature. - `hypothesis`: a `string` feature. - `label`: a classification label, with possible values including `entailment` (0), `neutral` (1), `contradiction` (2). #### bg - `premise`: a `string` feature. - `hypothesis`: a `string` feature. - `label`: a classification label, with possible values including `entailment` (0), `neutral` (1), `contradiction` (2). #### de - `premise`: a `string` feature. - `hypothesis`: a `string` feature. - `label`: a classification label, with possible values including `entailment` (0), `neutral` (1), `contradiction` (2). #### el - `premise`: a `string` feature. - `hypothesis`: a `string` feature. - `label`: a classification label, with possible values including `entailment` (0), `neutral` (1), `contradiction` (2). ### Data Splits \| name \|train \|validation\|test\| \|-------------\|-----:\|---------:\|---:\| \|all_languages\|392702\| 2490\|5010\| \|ar \|392702\| 2490\|5010\| \|bg \|392702\| 2490\|5010\| \|de \|392702\| 2490\|5010\| \|el \|392702\| 2490\|5010\| ## Dataset Creation ### Curation Rationale [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Source Data #### Initial Data Collection and Normalization [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the source language producers? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Annotations #### Annotation process [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the annotators? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Personal and Sensitive Information [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Discussion of Biases [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Other Known Limitations [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Additional Information ### Dataset Curators [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Licensing Information [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Citation Information ``` @InProceedings{conneau2018xnli, author = {Conneau, Alexis and Rinott, Ruty and Lample, Guillaume and Williams, Adina and Bowman, Samuel R. and Schwenk, Holger and Stoyanov, Veselin}, title = {XNLI: Evaluating Cross-lingual Sentence Representations}, booktitle = {Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing}, year = {2018}, publisher = {Association for Computational Linguistics}, location = {Brussels, Belgium}, } ``` ### Contributions Thanks to [@lewtun](https://github.com/lewtun), [@mariamabarham](https://github.com/mariamabarham), [@thomwolf](https://github.com/thomwolf), [@lhoestq](https://github.com/lhoestq), [@patrickvonplaten](https://github.com/patrickvonplaten) for adding this dataset.
jkot/merged_preprocessed_parliament_commonvoice	jkot	"2023-05-01T13:35:28Z"	17,240	0	[ "size_categories:100K<n<1M", "format:parquet", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]	null	"2023-05-01T10:37:03Z"	--- dataset_info: features: - name: input_features sequence: sequence: float32 - name: labels sequence: int64 splits: - name: train num_bytes: 210499135424 num_examples: 219101 - name: test num_bytes: 11099630080 num_examples: 11555 download_size: 65027813279 dataset_size: 221598765504 --- # Dataset Card for "merged_preprocessed_parliament_commonvoice" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
misikoff/zillow	misikoff	"2024-03-20T22:24:59Z"	17,195	24	[ "task_categories:tabular-regression", "task_categories:time-series-forecasting", "language:en", "license:other", "region:us" ]	[ "tabular-regression", "time-series-forecasting" ]	"2024-02-16T16:36:27Z"	--- language: - en license: other task_categories: - tabular-regression - time-series-forecasting pretty_name: Zillow description: 'This dataset is comprised of seven different configurations of data covering different aspects of the housing market in the United States. All data is provided by Zillow. The seven configurations are: home_values_forecasts, new_construction, for_sale_listings, rentals, sales, home_values, and days_on_market. Each configuration has a different set of features and target variables. The data is provided in JSONL format.' homepage: https://www.zillow.com/research/data/ dataset_info: - config_name: days_on_market features: - name: Region ID dtype: string id: Region ID - name: Size Rank dtype: int32 id: Size Rank - name: Region dtype: string id: Region - name: Region Type dtype: class_label: names: '0': zip '1': city '2': county '3': msa '4': state '5': country - name: State dtype: string id: State - name: Home Type dtype: class_label: names: '0': multifamily '1': condo/co-op '2': SFR '3': all homes '4': all homes plus multifamily - name: Date dtype: timestamp[ms] id: Date - name: Mean Listings Price Cut Amount (Smoothed) dtype: float32 id: Mean Listings Price Cut Amount (Smoothed) - name: Percent Listings Price Cut dtype: float32 id: Percent Listings Price Cut - name: Mean Listings Price Cut Amount dtype: float32 id: Mean Listings Price Cut Amount - name: Percent Listings Price Cut (Smoothed) dtype: float32 id: Percent Listings Price Cut (Smoothed) - name: Median Days on Pending (Smoothed) dtype: float32 id: Median Days on Pending (Smoothed) - name: Median Days on Pending dtype: float32 id: Median Days on Pending splits: - name: train num_bytes: 50107320 num_examples: 586714 download_size: 229118598 dataset_size: 50107320 - config_name: for_sale_listings features: - name: Region ID dtype: string id: Region ID - name: Size Rank dtype: int32 id: Size Rank - name: Region dtype: string id: Region - name: Region Type dtype: class_label: names: '0': county '1': city '2': zip '3': country '4': msa - name: State dtype: string id: State - name: Home Type dtype: class_label: names: '0': all homes '1': all homes plus multifamily '2': SFR '3': condo/co-op '4': multifamily - name: Date dtype: timestamp[ms] id: Date - name: Median Listing Price dtype: float32 id: Median Listing Price - name: Median Listing Price (Smoothed) dtype: float32 id: Median Listing Price (Smoothed) - name: New Listings dtype: int32 id: New Listings - name: New Listings (Smoothed) dtype: int32 id: New Listings (Smoothed) - name: New Pending (Smoothed) dtype: int32 id: New Pending (Smoothed) - name: New Pending dtype: int32 id: New Pending splits: - name: train num_bytes: 49412198 num_examples: 578653 download_size: 180206592 dataset_size: 49412198 - config_name: home_values features: - name: Region ID dtype: string id: Region ID - name: Size Rank dtype: int32 id: Size Rank - name: Region dtype: string id: Region - name: Region Type dtype: class_label: names: '0': zip '1': city '2': county '3': msa '4': state '5': country - name: State dtype: string id: State - name: Home Type dtype: class_label: names: '0': multifamily '1': condo/co-op '2': SFR '3': all homes '4': all homes plus multifamily - name: Bedroom Count dtype: class_label: names: '0': 1-Bedroom '1': 2-Bedrooms '2': 3-Bedrooms '3': 4-Bedrooms '4': 5+-Bedrooms '5': All Bedrooms - name: Date dtype: timestamp[ms] id: Date - name: Bottom Tier ZHVI (Smoothed) (Seasonally Adjusted) dtype: float32 id: Bottom Tier ZHVI (Smoothed) (Seasonally Adjusted) - name: Mid Tier ZHVI (Smoothed) (Seasonally Adjusted) dtype: float32 id: Mid Tier ZHVI (Smoothed) (Seasonally Adjusted) - name: Top Tier ZHVI (Smoothed) (Seasonally Adjusted) dtype: float32 id: Top Tier ZHVI (Smoothed) (Seasonally Adjusted) splits: - name: train num_bytes: 9377759 num_examples: 117912 download_size: 41145800 dataset_size: 9377759 - config_name: home_values_forecasts features: - name: Region ID dtype: string id: Region ID - name: Size Rank dtype: int32 id: Size Rank - name: Region dtype: string id: Region - name: Region Type dtype: class_label: names: '0': county '1': city '2': zip '3': country '4': msa - name: State dtype: string id: State - name: City dtype: string id: City - name: Metro dtype: string id: Metro - name: County dtype: string id: County - name: Date dtype: timestamp[ms] id: Date - name: Month Over Month % (Smoothed) (Seasonally Adjusted) dtype: float32 id: Month Over Month % (Smoothed) (Seasonally Adjusted) - name: Quarter Over Quarter % (Smoothed) (Seasonally Adjusted) dtype: float32 id: Quarter Over Quarter % (Smoothed) (Seasonally Adjusted) - name: Year Over Year % (Smoothed) (Seasonally Adjusted) dtype: float32 id: Year Over Year % (Smoothed) (Seasonally Adjusted) - name: Month Over Month % dtype: float32 id: Month Over Month % - name: Quarter Over Quarter % dtype: float32 id: Quarter Over Quarter % - name: Year Over Year % dtype: float32 id: Year Over Year % splits: - name: train num_bytes: 3976869 num_examples: 31854 download_size: 14081979 dataset_size: 3976869 - config_name: new_construction features: - name: Region ID dtype: string id: Region ID - name: Size Rank dtype: int32 id: Size Rank - name: Region dtype: string id: Region - name: Region Type dtype: class_label: names: '0': county '1': city '2': zip '3': country '4': msa - name: State dtype: string id: State - name: Home Type dtype: class_label: names: '0': all homes '1': all homes plus multifamily '2': SFR '3': condo/co-op '4': multifamily - name: Date dtype: timestamp[ms] id: Date - name: Median Sale Price dtype: float32 id: Median Sale Price - name: Median Sale Price per Sqft dtype: float32 id: Sale Price per Sqft - name: Sales Count dtype: int32 id: Sales Count splits: - name: train num_bytes: 3624631 num_examples: 49487 download_size: 10937317 dataset_size: 3624631 - config_name: rentals features: - name: Region ID dtype: string id: Region ID - name: Size Rank dtype: int32 id: Size Rank - name: Region dtype: string id: Region - name: Region Type dtype: class_label: names: '0': county '1': city '2': zip '3': country '4': msa - name: State dtype: string id: State - name: Home Type dtype: class_label: names: '0': all homes '1': all homes plus multifamily '2': SFR '3': condo/co-op '4': multifamily - name: Date dtype: timestamp[ms] id: Date - name: Rent (Smoothed) dtype: float32 id: Rent (Smoothed) - name: Rent (Smoothed) (Seasonally Adjusted) dtype: float32 id: Rent (Smoothed) (Seasonally Adjusted) splits: - name: train num_bytes: 92914681 num_examples: 1258740 download_size: 447425069 dataset_size: 92914681 - config_name: sales features: - name: Region ID dtype: string id: Region ID - name: Size Rank dtype: int32 id: Size Rank - name: Region dtype: string id: Region - name: Region Type dtype: class_label: names: '0': county '1': city '2': zip '3': country '4': msa - name: State dtype: string id: State - name: Home Type dtype: class_label: names: '0': all homes '1': all homes plus multifamily '2': SFR '3': condo/co-op '4': multifamily - name: Date dtype: timestamp[ms] id: Date - name: Mean Sale to List Ratio (Smoothed) dtype: float32 id: Mean Sale to List Ratio (Smoothed) - name: Median Sale to List Ratio dtype: float32 id: Median Sale to List Ratio - name: Median Sale Price dtype: float32 id: Median Sale Price - name: Median Sale Price (Smoothed) (Seasonally Adjusted) dtype: float32 id: Median Sale Price (Smoothed) (Seasonally Adjusted) - name: Median Sale Price (Smoothed) dtype: float32 id: Median Sale Price (Smoothed) - name: Median Sale to List Ratio (Smoothed) dtype: float32 id: Median Sale to List Ratio (Smoothed) - name: '% Sold Below List' dtype: float32 id: '% Sold Below List' - name: '% Sold Below List (Smoothed)' dtype: float32 id: '% Sold Below List (Smoothed)' - name: '% Sold Above List' dtype: float32 id: '% Sold Above List' - name: '% Sold Above List (Smoothed)' dtype: float32 id: '% Sold Above List (Smoothed)' - name: Mean Sale to List Ratio dtype: float32 id: Mean Sale to List Ratio splits: - name: train num_bytes: 27088039 num_examples: 255024 download_size: 139297577 dataset_size: 27088039 --- # Housing Data Provided by Zillow Updated: 2023-02-01 This dataset contains several configs produced based on files available at https://www.zillow.com/research/data/. # Viewer Notes Because this repository includes the code used to process the raw Zillow data, the dataset viewer is not enabled. This is because the dataset viewer is not enabled for datasets that run arbitrary python code. For a normal viewer experience, please see the simplified version of this dataset at https://huggingface.co/datasets/misikoff/zillow-viewer. The viewer should be enabled there and the config files should match what is found here. Supported configs: - [`days_on_market`](#days-on-market): Days to pending, days to close, share of listings with a price cut, and price cuts. - [`for_sale_listings`](#for-sale-listings): Median listing price, new listings, and new pending listings. - [`home_values`](#home-values): Zillow Home Value Index (ZHVI) for all homes, mid-tier, bottom-tier, and top-tier homes. - [`home_values_forecasts`](#home-values-forecasts): Zillow Home Value Forecast (ZHVF) for all homes, mid-tier, bottom-tier, and top-tier homes. - [`new_construction`](#new-construction): Median sale price, median sale price per square foot, and sales count. - [`rentals`](#rentals): Zillow Observed Rent Index (ZORI) for all homes, mid-tier, bottom-tier, and top-tier homes. - [`sales`](#sales): Median sale price, median sale price per square foot, and sales count. ## DAYS ON MARKET AND PRICE CUTS Days to Pending: How long it takes homes in a region to change to pending status on Zillow.com after first being shown as for sale. The reported figure indicates the number of days (mean or median) that it took for homes that went pending during the week being reported, to go pending. This differs from the old “Days on Zillow” metric in that it excludes the in-contract period before a home sells. Days to Close (mean/median): Number of days between the listing going pending and the sale date. Share of Listings With a Price Cut: The number of unique properties with a list price at the end of the month that’s less than the list price at the beginning of the month, divided by the number of unique properties with an active listing at some point during the month. Price Cuts: The mean and median price cut for listings in a given region during a given time period, expressed as both dollars ($) and as a percentage (%) of list price. Base Columns - `Region ID`: dtype="string", a unique identifier for the region - `Size Rank`: dtype="int32", a rank of the region's size - `Region`: dtype="string", the name of the region - `Region Type`: dtype="class_label", the type of region - '0': zip - '1': city - '2': county - '3': msa - '4': state - '5': country - `State`: dtype="string", the US state abbreviation for the state containing the region - `Home Type`: dtype="string", the type of home - '0': multifamily - '1': condo/co-op - '2': SFR - '3': all homes - '4': all homes plus multifamily - `Date`: dtype="timestamp[ms]", the date of the last day of the week for this data Value Columns - `Mean Listings Price Cut Amount (Smoothed)`: dtype="float32" - `Percent Listings Price Cut`: dtype="float32", The number of unique properties with a list price at the end of the month that’s less than the list price at the beginning of the month, divided by the number of unique properties with an active listing at some point during the month. - `Mean Listings Price Cut Amount`: dtype="float32" - `Percent Listings Price Cut (Smoothed)`: dtype="float32" - `Median Days on Pending (Smoothed)`: dtype="float32", median number of days it takes for homes in a region to change to pending status on Zillow.com after first being shown as for sale. (smoothed) - `Median Days on Pending`: dtype="float32", median number of days it takes for homes in a region to change to pending status on Zillow.com after first being shown as for sale. ## FOR-SALE LISTINGS Base Columns - `Region ID`: dtype="string", a unique identifier for the region - `Size Rank`: dtype="int32", a rank of the region's size - `Region`: dtype="string", the name of the region - `Region Type`: dtype="class_label", the type of region - '0': zip - '1': city - '2': county - '3': msa - '4': state - `State`: dtype="string", the US state abbreviation for the state containing the region - `Home Type`: dtype="string", the type of home - '0': all homes - '1': all homes plus multifamily - '2': SFR - '3': condo/co-op - '4': multifamily - `Date`: dtype="timestamp[ms]", the date of the last day of the month for this data Value Columns - `Median Listing Price`: dtype="float32", The median price at which homes across various geographies were listed. - `Median Listing Price (Smoothed)`: dtype="float32", The median price at which homes across various geographies were listed. (smoothed) - `New Listings`: dtype="int32", how many new listings have come on the market in a given month - `New Listings (Smoothed)`: dtype="int32", how many new listings have come on the market in a given month. (smoothed) - `New Pending (Smoothed)`: dtype="int32", The count of listings that changed from for-sale to pending status on Zillow.com in a given time period. (smoothed) - `New Pending`: dtype="int32", The count of listings that changed from for-sale to pending status on Zillow.com in a given time period. ## HOME VALUES <!-- Zillow Home Value Index (ZHVI): A measure of the typical home value and market changes across a given region and housing type. It reflects the typical value for homes in the 35th to 65th percentile range. Available as a smoothed, seasonally adjusted measure and as a raw measure. --> <!-- Zillow publishes top-tier ZHVI (\$, typical value for homes within the 65th to 95th percentile range for a given region) and bottom-tier ZHVI (\$, typical value for homes within the 5th to 35th percentile range for a given region). --> <!-- Zillow also publishes ZHVI for all single-family residences (\$, typical value for all single-family homes in a given region), for condo/coops (\$), for all homes with 1, 2, 3, 4 and 5+ bedrooms (\$), and the ZHVI per square foot (\$, typical value of all homes per square foot calculated by taking the estimated home value for each home in a given region and dividing it by the home’s square footage). --> <!-- Note: Starting with the January 2023 data release, and for all subsequent releases, the full ZHVI time series has been upgraded to harness the power of the neural Zestimate. --> <!-- More information about what ZHVI is and how it’s calculated is available on this overview page. Here’s a handy ZHVI User Guide for information about properly citing and making calculations with this metric. --> Base Columns - `Region ID`: dtype="string", a unique identifier for the region - `Size Rank`: dtype="int32", a rank of the region's size - `Region`: dtype="string", the name of the region - `Region Type`: dtype="class_label", the type of region - '0': zip - '1': city - '2': county - '3': msa - '4': state - '5': country" - `State`: dtype="string", the US state abbreviation for the state containing the region - `Home Type`: dtype="class_label", the type of home - '0': multifamily - '1': condo/co-op - '2': SFR - '3': all homes - '4': all homes plus multifamily - `Bedroom Count`: dtype="class_label", the number of bedrooms - '0': 1-Bedroom - '1': 2-Bedrooms - '2': 3-Bedrooms - '3': 4-Bedrooms - '4': 5+-Bedrooms - '5': All Bedrooms - `Date`: dtype="timestamp[ms]", the date of the last day of the month for this data Value Columns - `Mid Tier ZHVI (Smoothed) (Seasonally Adjusted)`: dtype="float32", - `Bottom Tier ZHVI (Smoothed) (Seasonally Adjusted)`: dtype="float32", - `Top Tier ZHVI (Smoothed) (Seasonally Adjusted)`: dtype="float32", - `ZHVI`: dtype="float32", - `Mid Tier ZHVI`: dtype="float32" ## HOME VALUES FORECASTS <!-- Zillow Home Value Forecast (ZHVF): A month-ahead, quarter-ahead and year-ahead forecast of the Zillow Home Value Index (ZHVI). ZHVF is created using the all homes, mid-tier cut of ZHVI and is available both raw and smoothed, seasonally adjusted. --> <!-- Note: Starting with the January 2023 forecast (made available in February 2023), Zillow’s Home Value Forecast is based on the upgraded ZHVI that harnesses the power of the neural Zestimate. More information about what ZHVI is and how it’s calculated is available on this overview page. --> Base Columns - `Region ID`: dtype="string", a unique identifier for the region - `Size Rank`: dtype="int32", a rank of the region's size - `Region`: dtype="string", the name of the region - `Region Type`: dtype="class_label", the type of region - '0': county - '1': city - '2': zip - '3': country - '4': msa - `State`: dtype="string", the US state abbreviation for the state containing the region - `City`: dtype="string", - `Metro`: dtype="string", - `County`: dtype="string", - `Home Type`: dtype="string", the type of home - `Date`: dtype="timestamp[ms]", the date of these forecasts Value Columns - `Month Over Month % (Smoothed)`: dtype="float32", - `Quarter Over Quarter % (Smoothed)`: dtype="float32", - `Year Over Year % (Smoothed)`: dtype="float32" - `Month Over Month % (Raw)`: dtype="float32" - `Quarter Over Quarter % (Raw)`: dtype="float32" - `Year Over Year % (Raw)`: dtype="float32" ## NEW CONSTRUCTION Base Columns - `Region ID`: dtype="string", a unique identifier for the region - `Size Rank`: dtype="int32", a rank of the region's size - `Region`: dtype="string", the name of the region - `Region Type`: dtype="class_label", the type of region - '0': county - '1': city - '2': zip - '3': country - '4': msa - `State`: dtype="string", the US state abbreviation for the state containing the region - `Home Type`: dtype="class_label", the type of home - '0': all homes - '1': all homes plus multifamily - '2': SFR - '3': condo/co-op - '4': multifamily - `Date`: dtype="timestamp[ms]", the date of the last day of the month for this data Value Columns - `Median Sale Price`: dtype="float32", the median sale price of new construction homes that sold during the month in the specified region - `Median Sale Price per Sqft`: dtype="float32", the median sale price per square foot of new construction homes that sold during the month in the specified region - `Sales Count`: dtype="int32", the number of new construction homes that sold during the month in the specified region ## RENTALS Base Columns - `Region ID`: dtype="string", a unique identifier for the region - `Size Rank`: dtype="int32", a rank of the region's size - `Region`: dtype="string", the name of the region - `Region Type`: dtype="class_label", the type of region - '0': county - '1': city - '2': zip - '3': country - '4': msa - `State`: dtype="string", the US state abbreviation for the state containing the region - `Home Type`: dtype="string", the type of home - '0': all homes - '1': all homes plus multifamily - '2': SFR - '3': condo/co-op - '4': multifamily - `Date`: dtype="timestamp[ms]", the date of the last day of the month for this data Value Columns - `Rent (Smoothed)`: dtype="float32", Zillow Observed Rent Index (ZORI): A smoothed measure of the typical observed market rate rent across a given region. ZORI is a repeat-rent index that is weighted to the rental housing stock to ensure representativeness across the entire market, not just those homes currently listed for-rent. The index is dollar-denominated by computing the mean of listed rents that fall into the 40th to 60th percentile range for all homes and apartments in a given region, which is weighted to reflect the rental housing stock. - `Rent (Smoothed) (Seasonally Adjusted)`: dtype="float32", Zillow Observed Rent Index (ZORI) :A smoothed measure of the typical observed market rate rent across a given region. ZORI is a repeat-rent index that is weighted to the rental housing stock to ensure representativeness across the entire market, not just those homes currently listed for-rent. The index is dollar-denominated by computing the mean of listed rents that fall into the 40th to 60th percentile range for all homes and apartments in a given region, which is weighted to reflect the rental housing stock. ## SALES <!-- Sale-to-List Ratio (mean/median): Ratio of sale vs. final list price. --> <!-- Percent of Sales Below/Above List: Share of sales where sale price below/above the final list price; excludes homes sold for exactly the list price. --> Base Columns - `Region ID`: dtype="string", a unique identifier for the region - `Size Rank`: dtype="int32", a rank of the region's size - `Region`: dtype="string", the name of the region - `Region Type`: dtype="class_label", the type of region - '0': county - '1': city - '2': zip - '3': country - '4': msa - `State`: dtype="string", the US state abbreviation for the state containing the region - `Home Type`: dtype="class_label", the type of home - '0': all homes - '1': all homes plus multifamily - '2': SFR - '3': condo/co-op - '4': multifamily - `Date`: dtype="timestamp[ms]", the date of the last day of the month for this data Value Columns - `Median Sale Price`: dtype="float32", The median price at which homes across various geographies were sold. - `Median Sale Price per Sqft`: dtype="float32" The median price per square foot at which homes across various geographies were sold. - `Sales Count`: dtype="int32", The "Sales Count Nowcast" is the estimated number of unique properties that sold during the month after accounting for the latency between when sales occur and when they are reported. ## DEFINITIONS OF HOME TYPES - all Homes: Zillow defines all homes as single-family, condominium and co-operative homes with a county record. Unless specified, all series cover this segment of the housing stock. - SFR: single family residence - condo/co-op: Condominium and co-operative homes. - Multifamily 5+ units: Units in buildings with 5 or more housing units, that are not condominiums or co-ops. <!-- - Duplex/Triplex/Quadplex: Housing units in buildings with 2, 3, or 4 housing units. --> # Example Usage ```python from datasets import load_dataset dataset = load_dataset("misikoff/zillow", 'home_values', trust_remote_code=True) ``` ## Example Notebook Linked below is an example notebook that demonstrates usage and analysis of one of the configs of this dataset. [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1lEPLbWsOKmNBzkPWT30RCBVxhG1LWkGg?usp=sharing)
taesiri/arxiv_db	taesiri	"2024-05-07T22:36:44Z"	17,167	4	[ "license:cc-by-nc-4.0", "region:us" ]	null	"2023-10-26T23:53:25Z"	--- license: cc-by-nc-4.0 ---
IGNF/FLAIR_1_osm_clip	IGNF	"2024-09-18T09:05:07Z"	17,158	5	[ "size_categories:10K<n<100K", "format:parquet", "modality:image", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us", "IGN" ]	null	"2023-04-27T12:28:28Z"	--- size_categories: - 10K<n<100K dataset_info: features: - name: image dtype: image - name: segmentation dtype: image - name: metadata struct: - name: address struct: - name: ISO3166-2-lvl4 dtype: string - name: ISO3166-2-lvl6 dtype: string - name: ISO3166-2-lvl7 dtype: string - name: aerialway dtype: string - name: aeroway dtype: string - name: allotments dtype: string - name: amenity dtype: string - name: bridge dtype: string - name: building dtype: string - name: city dtype: string - name: city_district dtype: string - name: club dtype: string - name: commercial dtype: string - name: country dtype: string - name: country_code dtype: string - name: county dtype: string - name: craft dtype: string - name: emergency dtype: string - name: farm dtype: string - name: farmyard dtype: string - name: hamlet dtype: string - name: healthcare dtype: string - name: highway dtype: string - name: historic dtype: string - name: house_number dtype: string - name: industrial dtype: string - name: isolated_dwelling dtype: string - name: junction dtype: string - name: landuse dtype: string - name: leisure dtype: string - name: locality dtype: string - name: man_made dtype: string - name: military dtype: string - name: municipality dtype: string - name: natural dtype: string - name: neighbourhood dtype: string - name: office dtype: string - name: place dtype: string - name: postcode dtype: string - name: province dtype: string - name: quarter dtype: string - name: railway dtype: string - name: region dtype: string - name: residential dtype: string - name: retail dtype: string - name: road dtype: string - name: shop dtype: string - name: square dtype: string - name: state dtype: string - name: state_district dtype: string - name: suburb dtype: string - name: tourism dtype: string - name: town dtype: string - name: village dtype: string - name: boundingbox sequence: string - name: camera dtype: string - name: code dtype: string - name: date dtype: string - name: dimensions sequence: int64 - name: display_name dtype: string - name: domain dtype: string - name: lat dtype: string - name: latlong sequence: float64 - name: licence dtype: string - name: lon dtype: string - name: origin sequence: float64 - name: osm_id dtype: int64 - name: osm_type dtype: string - name: patch_centroid_x dtype: float64 - name: patch_centroid_y dtype: float64 - name: patch_centroid_z dtype: float64 - name: place_id dtype: int64 - name: time dtype: string - name: unit_system dtype: string - name: zone dtype: string - name: class_rep struct: - name: class_repartition struct: - name: agricultural land dtype: float64 - name: bare soil dtype: float64 - name: brushwood dtype: float64 - name: building dtype: float64 - name: clear cut dtype: float64 - name: coniferous dtype: float64 - name: deciduous dtype: float64 - name: greenhouse dtype: float64 - name: herbaceous vegetation dtype: float64 - name: impervious surface dtype: float64 - name: ligneous dtype: float64 - name: mixed dtype: float64 - name: other dtype: float64 - name: pervious surface dtype: float64 - name: plowed land dtype: float64 - name: snow dtype: float64 - name: swimming pool dtype: float64 - name: vineyard dtype: float64 - name: water dtype: float64 - name: prompt dtype: string - name: clip_label dtype: string - name: clip_embeddings sequence: float32 splits: - name: train num_bytes: 26969627407.0 num_examples: 61712 download_size: 26975935912 dataset_size: 26969627407.0 tags: - IGN configs: - config_name: default data_files: - split: train path: data/train-* --- # Dataset Card for "FLAIR_OSM_CLIP" Dataset for the Seg2Sat model: https://github.com/RubenGres/Seg2Sat Derived from [FLAIR#1](https://huggingface.co/datasets/IGNF/FLAIR) train split. This dataset incudes the following features: - image: FLAIR#1 .tif files RBG bands converted into a more managable jpg format - segmentation: FLAIR#1 segmentation converted to JPG using the [LUT from the documentation](https://ignf.github.io/FLAIR/index_fr.html) - metadata: OSM metadata for the centroid of the image - clip_label: [CLIP ViT-H](https://github.com/openai/CLIP) description - class_rep: ratio of appearance of each class in the segmentation - prompt: Prompt used for the Seg2Sat model - clip_embeddings: Embedding using openai/clip-vit-base-patch32 model <!--- [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) --->
fsicoli/common_voice_15_0	fsicoli	"2023-12-20T18:55:52Z"	16,944	5	[ "task_categories:automatic-speech-recognition", "language:ab", "language:af", "language:am", "language:ar", "language:as", "language:ast", "language:az", "language:ba", "language:bas", "language:be", "language:bg", "language:bn", "language:br", "language:ca", "language:ckb", "language:cnh", "language:cs", "language:cv", "language:cy", "language:da", "language:de", "language:dv", "language:dyu", "language:el", "language:en", "language:eo", "language:es", "language:et", "language:eu", "language:fa", "language:fi", "language:fr", "language:gl", "language:gn", "language:ha", "language:he", "language:hi", "language:hsb", "language:hu", "language:ia", "language:id", "language:ig", "language:is", "language:it", "language:ja", "language:ka", "language:kab", "language:kk", "language:kmr", "language:ko", "language:ky", "language:lg", "language:lo", "language:lt", "language:lv", "language:mdf", "language:mhr", "language:mk", "language:ml", "language:mn", "language:mr", "language:mrj", "language:mt", "language:myv", "language:nl", "language:oc", "language:or", "language:pl", "language:ps", "language:pt", "language:quy", "language:ro", "language:ru", "language:rw", "language:sah", "language:sat", "language:sc", "language:sk", "language:skr", "language:sl", "language:sq", "language:sr", "language:sw", "language:ta", "language:th", "language:ti", "language:tig", "language:tk", "language:tok", "language:tr", "language:tt", "language:tw", "language:ug", "language:uk", "language:ur", "language:uz", "language:vi", "language:vot", "language:yue", "language:zgh", "language:zh", "language:yo", "license:cc", "size_categories:100B<n<1T", "region:us", "mozilla", "foundation" ]	[ "automatic-speech-recognition" ]	"2023-11-13T13:27:04Z"	--- license: cc language: - ab - af - am - ar - as - ast - az - ba - bas - be - bg - bn - br - ca - ckb - cnh - cs - cv - cy - da - de - dv - dyu - el - en - eo - es - et - eu - fa - fi - fr - gl - gn - ha - he - hi - hsb - hu - ia - id - ig - is - it - ja - ka - kab - kk - kmr - ko - ky - lg - lo - lt - lv - mdf - mhr - mk - ml - mn - mr - mrj - mt - myv - nl - oc - or - pl - ps - pt - quy - ro - ru - rw - sah - sat - sc - sk - skr - sl - sq - sr - sw - ta - th - ti - tig - tk - tok - tr - tt - tw - ug - uk - ur - uz - vi - vot - yue - zgh - zh - yo task_categories: - automatic-speech-recognition pretty_name: Common Voice Corpus 15.0 size_categories: - 100B<n<1T tags: - mozilla - foundation --- # Dataset Card for Common Voice Corpus 15.0 <!-- Provide a quick summary of the dataset. --> This dataset is an unofficial version of the Mozilla Common Voice Corpus 15. It was downloaded and converted from the project's website https://commonvoice.mozilla.org/. ## Languages ``` Abkhaz, Albanian, Amharic, Arabic, Armenian, Assamese, Asturian, Azerbaijani, Basaa, Bashkir, Basque, Belarusian, Bengali, Breton, Bulgarian, Cantonese, Catalan, Central Kurdish, Chinese (China), Chinese (Hong Kong), Chinese (Taiwan), Chuvash, Czech, Danish, Dhivehi, Dioula, Dutch, English, Erzya, Esperanto, Estonian, Finnish, French, Frisian, Galician, Georgian, German, Greek, Guarani, Hakha Chin, Hausa, Hill Mari, Hindi, Hungarian, Icelandic, Igbo, Indonesian, Interlingua, Irish, Italian, Japanese, Kabyle, Kazakh, Kinyarwanda, Korean, Kurmanji Kurdish, Kyrgyz, Lao, Latvian, Lithuanian, Luganda, Macedonian, Malayalam, Maltese, Marathi, Meadow Mari, Moksha, Mongolian, Nepali, Norwegian Nynorsk, Occitan, Odia, Pashto, Persian, Polish, Portuguese, Punjabi, Quechua Chanka, Romanian, Romansh Sursilvan, Romansh Vallader, Russian, Sakha, Santali (Ol Chiki), Saraiki, Sardinian, Serbian, Slovak, Slovenian, Sorbian, Upper, Spanish, Swahili, Swedish, Taiwanese (Minnan), Tamazight, Tamil, Tatar, Thai, Tigre, Tigrinya, Toki Pona, Turkish, Turkmen, Twi, Ukrainian, Urdu, Uyghur, Uzbek, Vietnamese, Votic, Welsh, Yoruba ``` ## How to use The datasets library allows you to load and pre-process your dataset in pure Python, at scale. The dataset can be downloaded and prepared in one call to your local drive by using the load_dataset function. For example, to download the Portuguese config, simply specify the corresponding language config name (i.e., "pt" for Portuguese): ``` from datasets import load_dataset cv_15 = load_dataset("fsicoli/common_voice_15_0", "pt", split="train") ``` Using the datasets library, you can also stream the dataset on-the-fly by adding a streaming=True argument to the load_dataset function call. Loading a dataset in streaming mode loads individual samples of the dataset at a time, rather than downloading the entire dataset to disk. ``` from datasets import load_dataset cv_15 = load_dataset("fsicoli/common_voice_15_0", "pt", split="train", streaming=True) print(next(iter(cv_15))) ``` Bonus: create a PyTorch dataloader directly with your own datasets (local/streamed). ### Local ``` from datasets import load_dataset from torch.utils.data.sampler import BatchSampler, RandomSampler cv_15 = load_dataset("fsicoli/common_voice_15_0", "pt", split="train") batch_sampler = BatchSampler(RandomSampler(cv_15), batch_size=32, drop_last=False) dataloader = DataLoader(cv_15, batch_sampler=batch_sampler) ``` ### Streaming ``` from datasets import load_dataset from torch.utils.data import DataLoader cv_15 = load_dataset("fsicoli/common_voice_15_0", "pt", split="train") dataloader = DataLoader(cv_15, batch_size=32) ``` To find out more about loading and preparing audio datasets, head over to hf.co/blog/audio-datasets. ### Dataset Structure Data Instances A typical data point comprises the path to the audio file and its sentence. Additional fields include accent, age, client_id, up_votes, down_votes, gender, locale and segment. ### Licensing Information Public Domain, CC-0 ### Citation Information ``` @inproceedings{commonvoice:2020, author = {Ardila, R. and Branson, M. and Davis, K. and Henretty, M. and Kohler, M. and Meyer, J. and Morais, R. and Saunders, L. and Tyers, F. M. and Weber, G.}, title = {Common Voice: A Massively-Multilingual Speech Corpus}, booktitle = {Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020)}, pages = {4211--4215}, year = 2020 } ```
RogerQi/PH2D	RogerQi	"2025-03-31T09:27:25Z"	16,719	1	[ "task_categories:robotics", "license:mit", "arxiv:2503.13441", "region:us", "Human", "Humanoid", "Robot" ]	[ "robotics" ]	"2025-03-14T02:03:14Z"	--- license: mit task_categories: - robotics tags: - Human - Humanoid - Robot --- ## Dataset Description This dataset contains egocentric human-humanoid data that can be used to co-train manipulation policy for humanoid robot. For paper, visualization, and example code using this dataset, please refer to https://human-as-robot.github.io/ arXiv link: https://arxiv.org/abs/2503.13441 ## Task Descriptions We provide some example dataset config files that we used for our robots [here](https://github.com/RogerQi/human-policy/tree/main/hdt/configs/datasets). Data organizations - Each folder represents one task. Most HDF5 files contain ONE execution of the task specified by the language, but certain tasks, such as cup passing, contain multiple demonstrations in each HDF5. - Taskids start with `1` mean the data is a human demonstrations.
hssd/hssd-hab	hssd	"2025-02-14T02:19:58Z"	16,714	35	[ "language:en", "license:cc-by-nc-4.0", "region:us", "3D scenes", "Embodied AI" ]	null	"2023-06-04T18:59:50Z"	--- language: - en pretty_name: HSSD tags: - 3D scenes - Embodied AI license: cc-by-nc-4.0 extra_gated_heading: "Acknowledge license to accept the repository" extra_gated_prompt: "You agree to use this dataset under the [CC BY-NC 4.0 license](https://creativecommons.org/licenses/by-nc/4.0/) terms" viewer: false --- HSSD: Habitat Synthetic Scenes Dataset ================================== The [Habitat Synthetic Scenes Dataset (HSSD)](https://3dlg-hcvc.github.io/hssd/) is a human-authored 3D scene dataset that more closely mirrors real scenes than prior datasets. Our dataset represents real interiors and contains a diverse set of 211 scenes and more than 18000 models of real-world objects. <img src="https://i.imgur.com/XEkLxNs.png" width=50%> This repository provides a Habitat consumption-ready compressed version of HSSD. See [this repository](https://huggingface.co/datasets/hssd/hssd-models) for corresponding uncompressed assets. ## Dataset Structure ``` ├── objects │ ├── /.glb │ ├── /.collider.glb │ ├── /.filteredSupportSurface(.ply\|.glb) │ ├── /.object_config.json ├── stages │ ├── .glb │ ├── .stage_config.json ├── scenes │ ├── .scene_instance.json ├── scenes_uncluttered │ ├── .scene_instance.json ├── scenes_articulated │ ├── .scene_instance.json ├── scene_filter_files │ ├── .rec_filter.json ├── metadata │ ├── .csv │ ├── .json ├── semantics │ ├── hssd-hab_semantic_lexicon.json │ ├── scenes \| ├── .semantic_config.json ├── urdf │ ├── <model_name> \| ├── .glb \| ├── .urdf \| ├── .ao_config.json └── hssd-hab.scene_dataset_config.json └── hssd-hab-uncluttered.scene_dataset_config.json └── hssd-hab-articulated.scene_dataset_config.json ``` - `hssd-hab.scene_dataset_config.json`: This SceneDataset config file aggregates the assets and metadata necessary to fully describe the set of stages, objects, and scenes constituting the dataset. - `objects`: 3D models representing distinct objects that are used to compose scenes. Contains configuration files, render assets, collider assets, and Receptacle mesh assets. - `stages`: A stage in Habitat is the set of static mesh components which make up the backdrop of a scene (e.g. floor, walls, stairs, etc.). - `scenes`: A scene is a single 3D world composed of a static stage and a variable number of objects. - `scene_filter_files`: These .rec_filter.json files contain mappings of Receptacle instance unique_names to active or filtered sets based on their locations and accessibility within the scene. They also contain a "within_set" defining Receptacles which can only be accessed when the parent Furniture object's "default_link" is in the "open" state. - `metadata`: The metadata directory contains several csv and json files which provide semantic mappings for objects in the dataset as well as rational mappings from regions to the types of clutter objects typically found in them to support procedural generation. - `semantics`: Primarily defines instance semantics for the scenes. .semantic_config.json files contain the region annotations for each scene. - `urdf`: The urdf directory contains the articulated furniture assets, each contained in its own sub-directory named after the source asset. The .urdf files define the articulation properties. Each .glb file is either a render asset or Receptacle mesh connected to a rigid link. The .ao_config.json file contains habitat-specific metadata such as markersets and Receptacle definitions. ### Rearrange-ready assets: Supporting Habitat 3.0 embodied rearrangement tasks with updated colliders, adjusted and de-cluttered scene contents, receptacle meshes, and receptacle filter files. See [aihabitat.org/habitat3/](aihabitat.org/habitat3/) for more details. - `hssd-hab-uncluttered.scene_dataset_config.json`: This SceneDataset config file aggregates adds the adjusted and uncluttered scenes for rearrangement tasks. - `scenes_uncluttered`: Contains the adjusted scene instance configuration files. - `scene_filter_files`: A scene filter file organizes available Receptacle instances in a scene into active and inactive groups based on simualtion heuristics and manual edits. It is consumed by the RearrangeEpisodeGenerator to construct valid RearrangeEpisodeDatasets. ### Articulated scenes and assets: Introduced in `v0.3.0`, the `hssd-hab-articulated.scene_dataset_config.json` SceneDataset provides 202 fully articulated HSSD scenes ready for use within the AI Habitat simulation ecosystem. Note that only 161 are publicly available on this repo. The remainder and their unique assets are reserved as an internal test set. To enable more realistic indoor object manipulation, articulated 3D furniture models such as drawers, cabinets, and appliances were added to replace rigid assets. These models were converted from rigid source assets in HSSD and swapped into the scenes. Furniture is annotated with a set of Receptacles (surfaces which support small object placement such as shelves and drawers) and can be opened and closed by the agents. Receptacles are further filtered contextually in each scene to ensure that the active set is accessible to the agents. Additional annotations include point or marker sets for each furniture, region annotations, and semantic classification of objects. ## Getting Started To load HSSD scenes into the Habitat simulator, you can start by installing [habitat-sim](https://github.com/facebookresearch/habitat-sim) using instructions specified [here](https://github.com/facebookresearch/habitat-sim#installation). Once installed, you can run the interactive Habitat viewer to load a scene: ``` habitat-viewer --dataset /path/to/hssd-hab/hssd-hab.scene_dataset_config.json -- 102344280 # or ./build/viewer if compiling from source ``` You can find more information about using the interactive viewer [here](https://github.com/facebookresearch/habitat-sim#testing:~:text=path/to/data/-,Interactive%20testing,-%3A%20Use%20the%20interactive). Habitat-Sim is typically used with [Habitat-Lab](https://github.com/facebookresearch/habitat-lab), a modular high-level library for end-to-end experiments in embodied AI. To define embodied AI tasks (e.g. navigation, instruction following, question answering), train agents, and benchmark their performance using standard metrics, you can download habitat-lab using the instructions provided [here](https://github.com/facebookresearch/habitat-lab#installation). ## Changelog - `v0.3.0`: Articulated Scenes and PARTNR support* - This major version update adds a large set of changes to support the introduction of 202 articulated HSSD scenes and the [PARTNR benchmark](https://github.com/facebookresearch/partnr-planner). - Includes improvements to stage texture/geometry and object collision shapes and receptacles. - Adds: - 2000+ articulated assets in the urdf/ directory representing and replacing rigid furniture objects. Annotated with Receptacles and semantics. - 202 new articulated scenes with rigid objects replaced by AOs. These are uncluttered and often significantly altered from originals to accommodate the new assets. - Note that test scenes and assets are removed before migration to this repo. - Receptacle filter files for new scenes annotating accessible Receptacles and "within" Receptacles (those which require opening an articulated link for access). - Note that only one link per AO is configured with an active Receptacle. This is based on logic in PARTNR and habitat-lab (default_link). - Region volume semantic annotations to all scenes - Semantic lexicon file with updated classes - Metadata files mapping object semantics and common-sense object->region sets for PARTNR - `v0.2.5`: Rearrange-ready HSSD - Note: this is a checkpoint. Known issues exist and continued polish is ongoing. - Adds Receptacle meshes describing support surfaces for small objects (e.g. table or shelf surfaces). - Adds collider meshes (.collider.glb) for assets with Receptacle meshes to support simulation. - Adds new scenes 'scenes_uncluttered' and new SceneDataset 'hssd-hab-uncluttered' containing adjusted and de-cluttered versions of the scenes for use in embodied rearrangement tasks. - Adds 'scene_filter_files' which sort Receptacles in each scene into active and inactive groups for RearrangeEpisode generation. - `v0.2.4`: - Recompresses several object GLBs to preserve PBR material status. - Adds CSV with object metadata and semantic lexicon files for Habitat. - Adds train/val scene splits file. - `v0.2.3`: First release.
open-social-world/EgoNormia	open-social-world	"2025-03-04T19:44:49Z"	16,711	3	[ "task_categories:visual-question-answering", "task_categories:video-text-to-text", "task_categories:question-answering", "language:en", "license:cc-by-sa-4.0", "size_categories:1K<n<10K", "format:parquet", "modality:image", "modality:text", "modality:video", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "arxiv:2502.20490", "region:us", "visual-reasoning", "perception", "predictive", "spatial", "temporal", "causal" ]	[ "visual-question-answering", "video-text-to-text", "question-answering" ]	"2025-02-01T01:25:44Z"	--- language: - en license: cc-by-sa-4.0 size_categories: - 1K<n<10K task_categories: - visual-question-answering - video-text-to-text - question-answering pretty_name: EgoNormia tags: - visual-reasoning - perception - predictive - spatial - temporal - causal --- <h1 align='center' style="text-align:center; font-weight:bold; font-size:2.0em;letter-spacing:2.0px;"> EgoNormia: Benchmarking Physical Social Norm Understanding</h1> <p align='center' style="text-align:center;font-size:1.25em;"> <a href="https://mhrezaei.com" target="_blank" style="text-decoration: none;">MohammadHossein Rezaei</a>,  <a href="https://sofyc.github.io" target="_blank" style="text-decoration: none;">Yicheng Fu</a>,  <a href="https://scholar.google.com/citations?user=bDIUeu4AAAAJ&hl=en" target="_blank" style="text-decoration: none;">Phil Cuvin</a>,  <a href="https://calebziems.com" target="_blank" style="text-decoration: none;">Caleb Ziems</a>,  <a href="https://stevenyzzhang.github.io/website/" target="_blank" style="text-decoration: none;">Yanzhe Zhang</a>, <br/> <a href="https://zhuhao.me" target="_blank" style="text-decoration: none;">Hao Zhu</a>,  <a href="https://cs.stanford.edu/~diyiy/" target="_blank" style="text-decoration: none;">Diyi Yang</a>,  </p> <p align='center' style="text-align:center;font-size:1.25em;"> <a href="https://egonormia.org" title="Website" target="_blank" rel="nofollow" style="text-decoration: none;">🌎Website</a> \| <a href="https://huggingface.co/datasets/open-social-world/EgoNormia" title="Dataset" target="_blank" rel="nofollow" style="text-decoration: none;">🤗 Dataset</a> \| <a href="https://arxiv.org/abs/2502.20490" title="aXiv" target="_blank" rel="nofollow" style="text-decoration: none;">📄 arXiv</a> \| <a href="https://hf.co/papers/2502.20490" title="Paper" target="_blank" rel="nofollow" style="text-decoration: none;">📄 HF Paper</a> </p> ## EgoNormia EgoNormia is a challenging QA benchmark that tests VLMs' ability to reason over norms in context. The datset consists of 1,853* physically grounded egocentric interaction clips from [Ego4D](https://ego4d-data.org/) and corresponding five-way multiple-choice questions tasks for each. <br><br> EgoNormia spans 100 distinct settings across a wide range of activities, cultures, and interactions. Unlike other visually-grounded spatiotemporal, predictive, or causal reasoning benchmarks, EgoNormia evaluates models’ ability to reason about what should be done under social norms. EgoNormia highlights cases where these norm-related objectives conflict—the richest arena for evaluating normative decision-making. ## Example Data Point <img src="image/egonormia_teaser.jpg" alt="Teaser" width="800"/> ## EgoNormia Statistics Statistics \| Data Points \| Video Sources \| Scenarios \| Types of Actions --- \| --- \| --- \| --- \| --- \| Number \| 1853 \| 1077 \| 97 \| 93 <img src="image/activity_distribution.png" alt="Activity Distribution" width="400"/> ## Benchmarking Guide The supported method for benchmarking on EgoNormia is to download the github repo `git clone https://github.com/Open-Social-World/EgoNormia.git`, and then to follow the included guide for running model evaluation and benchmarking (which automatically downloads and uses this dataset). Alternatively, the HuggingFace datset can be directly downloaded and evaluated with custom code; however, this is not officially supported. ## Dataset Organization Below is a detailed explanation of the dataset's structure and its contents: ``` EgoNormia/ ├── images/ ├── videos/ # Images for dataset card │ └── {video_uid}/ │ ├── frame_all_during.jpg # Concatenated frames sampled at 1 FPS from video_during.mp4 │ ├── frame_all_prev.jpg # Concatenated frames sampled at 1 FPS from video_prev.mp4 │ ├── video_during.mp4 # Video clip capturing an action being performed │ └── video_prev.mp4 # Video clip capturing the five seconds before an action is performed └── final_data.json # JSON file with MCQs and descriptions for videos in EgoNormia ├── train-norm-updated.parquet # Parquet file for dataset visualization ├── .gitattributes # Git configuration └── README.md # README file ``` ### Annotation Format Each video includes metadata and an MCQ in the following format: ``` { "video_uid": { "id": "video_uid", "behaviors": list of str, "justifications": list of str, "correct": int, "sensibles": list of int, "taxonomy": { "0": list of string, "1": list of string, "2": list of string, "3": list of string, "4": list of string, }, "desc": str }, // Next video uid } ``` ## Limitations While multiple rounds of filtering are applied to ensure diversity in EgoNormis video clips, all video clips in EgoNormia are sourced exclusively from Ego4D, which may reflect inherent distribution biases within Ego4D. ## Contact - Yicheng Fu: [email protected] - Phil Cuvin: [email protected] - Hao Zhu: [email protected] ## Acknowledgement This research was supported in part by Other Transaction award HR00112490375 from the U.S. Defense Advanced Research Projects Agency (DARPA) Friction for Accountability in Conversational Transactions (FACT) program. We thank Google Cloud Platform and Modal Platform for their credits. We thank feedback from Yonatan Bisk and members of the SALT lab at Stanford University. The authors thank Leena Mathur and Su Li for their help in collecting out-of-domain robotics videos. ## Citation ```bibtex @misc{rezaei2025egonormiabenchmarkingphysicalsocial, title={EgoNormia: Benchmarking Physical Social Norm Understanding}, author={MohammadHossein Rezaei and Yicheng Fu and Phil Cuvin and Caleb Ziems and Yanzhe Zhang and Hao Zhu and Diyi Yang}, year={2025}, eprint={2502.20490}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2502.20490}, } ```
allenai/math_qa	allenai	"2024-01-18T11:08:38Z"	16,674	101	[ "task_categories:question-answering", "task_ids:multiple-choice-qa", "annotations_creators:crowdsourced", "language_creators:crowdsourced", "language_creators:expert-generated", "multilinguality:monolingual", "source_datasets:extended\|aqua_rat", "language:en", "license:apache-2.0", "size_categories:10K<n<100K", "region:us" ]	[ "question-answering" ]	"2022-03-02T23:29:22Z"	--- annotations_creators: - crowdsourced language: - en language_creators: - crowdsourced - expert-generated license: - apache-2.0 multilinguality: - monolingual pretty_name: MathQA size_categories: - 10K<n<100K source_datasets: - extended\|aqua_rat task_categories: - question-answering task_ids: - multiple-choice-qa paperswithcode_id: mathqa dataset_info: features: - name: Problem dtype: string - name: Rationale dtype: string - name: options dtype: string - name: correct dtype: string - name: annotated_formula dtype: string - name: linear_formula dtype: string - name: category dtype: string splits: - name: test num_bytes: 1844184 num_examples: 2985 - name: train num_bytes: 18368826 num_examples: 29837 - name: validation num_bytes: 2752969 num_examples: 4475 download_size: 7302821 dataset_size: 22965979 --- # Dataset Card for MathQA ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - Homepage: [https://math-qa.github.io/math-QA/](https://math-qa.github.io/math-QA/) - Repository: [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - Paper: [MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms](https://aclanthology.org/N19-1245/) - Point of Contact: [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - Size of downloaded dataset files: 7.30 MB - Size of the generated dataset: 22.96 MB - Total amount of disk used: 30.27 MB ### Dataset Summary We introduce a large-scale dataset of math word problems. Our dataset is gathered by using a new representation language to annotate over the AQuA-RAT dataset with fully-specified operational programs. AQuA-RAT has provided the questions, options, rationale, and the correct options. ### Supported Tasks and Leaderboards [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Languages [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Dataset Structure ### Data Instances #### default - Size of downloaded dataset files: 7.30 MB - Size of the generated dataset: 22.96 MB - Total amount of disk used: 30.27 MB An example of 'train' looks as follows. ``` { "Problem": "a multiple choice test consists of 4 questions , and each question has 5 answer choices . in how many r ways can the test be completed if every question is unanswered ?", "Rationale": "\"5 choices for each of the 4 questions , thus total r of 5 * 5 * 5 * 5 = 5 ^ 4 = 625 ways to answer all of them . answer : c .\"", "annotated_formula": "power(5, 4)", "category": "general", "correct": "c", "linear_formula": "power(n1,n0)\|", "options": "a ) 24 , b ) 120 , c ) 625 , d ) 720 , e ) 1024" } ``` ### Data Fields The data fields are the same among all splits. #### default - `Problem`: a `string` feature. - `Rationale`: a `string` feature. - `options`: a `string` feature. - `correct`: a `string` feature. - `annotated_formula`: a `string` feature. - `linear_formula`: a `string` feature. - `category`: a `string` feature. ### Data Splits \| name \|train\|validation\|test\| \|-------\|----:\|---------:\|---:\| \|default\|29837\| 4475\|2985\| ## Dataset Creation ### Curation Rationale [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Source Data #### Initial Data Collection and Normalization [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the source language producers? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Annotations #### Annotation process [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the annotators? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Personal and Sensitive Information [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Discussion of Biases [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Other Known Limitations [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Additional Information ### Dataset Curators [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Licensing Information The dataset is licensed under the [Apache License, Version 2.0](http://www.apache.org/licenses/LICENSE-2.0). ### Citation Information ``` @inproceedings{amini-etal-2019-mathqa, title = "{M}ath{QA}: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms", author = "Amini, Aida and Gabriel, Saadia and Lin, Shanchuan and Koncel-Kedziorski, Rik and Choi, Yejin and Hajishirzi, Hannaneh", booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)", month = jun, year = "2019", address = "Minneapolis, Minnesota", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/N19-1245", doi = "10.18653/v1/N19-1245", pages = "2357--2367", } ``` ### Contributions Thanks to [@thomwolf](https://github.com/thomwolf), [@lewtun](https://github.com/lewtun), [@patrickvonplaten](https://github.com/patrickvonplaten) for adding this dataset.
awettig/RedPajama-combined-15B-8k-llama	awettig	"2023-11-30T07:16:59Z"	16,408	0	[ "size_categories:1M<n<10M", "format:parquet", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]	null	"2023-11-29T05:26:03Z"	--- dataset_info: features: - name: input_ids sequence: int32 - name: attention_mask sequence: int8 - name: labels sequence: int64 splits: - name: test num_bytes: 3181819992 num_examples: 29874 - name: train num_bytes: 188533325564 num_examples: 1770133 download_size: 0 dataset_size: 191715145556 --- # Dataset Card for "RedPajama-combined-15B-8K-llama" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
gigant/tib_slides_wip	gigant	"2023-03-26T16:22:49Z"	16,368	0	[ "size_categories:100K<n<1M", "format:parquet", "modality:image", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]	null	"2023-03-26T00:20:40Z"	--- dataset_info: features: - name: Image dtype: image - name: file_name dtype: string splits: - name: train num_bytes: 161850916866.84 num_examples: 595458 download_size: 29396407498 dataset_size: 161850916866.84 --- # Dataset Card for "tib_slides_wip" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
JonasLange/DBD-research-group	JonasLange	"2023-06-27T11:26:14Z"	16,218	0	[ "size_categories:10K<n<100K", "format:parquet", "modality:audio", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]	null	"2023-06-27T08:44:41Z"	--- dataset_info: features: - name: ID dtype: string - name: Audio dtype: audio - name: Start Time (s) dtype: string - name: End Time (s) dtype: string - name: Low Freq (Hz) dtype: string - name: High Freq (Hz) dtype: string - name: Species eBird Code dtype: string - name: Call Type dtype: 'null' - name: Sex dtype: 'null' - name: Latitude dtype: float64 - name: Longitude dtype: float64 - name: Uncertainty dtype: 'null' - name: Microphone dtype: string - name: License dtype: string - name: Source dtype: string - name: BirdNet Training Data dtype: bool splits: - name: train num_bytes: 156231869250.216 num_examples: 10976 download_size: 538872707 dataset_size: 156231869250.216 --- # Dataset Card for "DBD-research-group" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
lmqg/qg_koquad	lmqg	"2022-12-02T18:53:42Z"	16,168	8	[ "task_categories:text-generation", "task_ids:language-modeling", "multilinguality:monolingual", "source_datasets:squad_es", "language:ko", "license:cc-by-4.0", "size_categories:10K<n<100K", "modality:text", "library:datasets", "library:mlcroissant", "arxiv:2210.03992", "region:us", "question-generation" ]	[ "text-generation" ]	"2022-06-02T23:42:21Z"	--- license: cc-by-4.0 pretty_name: KorQuAD for question generation language: ko multilinguality: monolingual size_categories: 10K<n<100K source_datasets: squad_es task_categories: - text-generation task_ids: - language-modeling tags: - question-generation --- # Dataset Card for "lmqg/qg_korquad" ## Dataset Description - Repository: [https://github.com/asahi417/lm-question-generation](https://github.com/asahi417/lm-question-generation) - Paper: [https://arxiv.org/abs/2210.03992](https://arxiv.org/abs/2210.03992) - Point of Contact: [Asahi Ushio](http://asahiushio.com/) ### Dataset Summary This is a subset of [QG-Bench](https://github.com/asahi417/lm-question-generation/blob/master/QG_BENCH.md#datasets), a unified question generation benchmark proposed in ["Generative Language Models for Paragraph-Level Question Generation: A Unified Benchmark and Evaluation, EMNLP 2022 main conference"](https://arxiv.org/abs/2210.03992). This is a modified version of [KorQuAD](https://huggingface.co/datasets/squad_kor_v1) for question generation (QG) task. Since the original dataset only contains training/validation set, we manually sample test set from training set, which has no overlap in terms of the paragraph with the training set. ### Supported Tasks and Leaderboards * `question-generation`: The dataset is assumed to be used to train a model for question generation. Success on this task is typically measured by achieving a high BLEU4/METEOR/ROUGE-L/BERTScore/MoverScore (see our paper for more in detail). ### Languages Korean (ko) ## Dataset Structure An example of 'train' looks as follows. ``` { "question": "함수해석학이 주목하는 탐구는?", "paragraph": "변화에 대한 이해와 묘사는 자연과학에 있어서 일반적인 주제이며, 미적분학은 변화를 탐구하는 강력한 도구로서 발전되었다. 함수는 변화하는 양을 묘사함에 있어서 중추적인 개념으로써 떠오르게 된다. 실수와 실변수로 구성된 함수의 엄밀한 탐구가 실해석학이라는 분야로 알려지게 되었고, 복소수에 대한 이와 같은 탐구분야는 복소해석학이라고 한다. 함수해석학은 함수의 공간(특히 무한차원)의 탐구에 주목한다. 함수해석학의 많은 응용분야 중 하나가 양자역학이다. 많은 문제들이 자연스럽게 양과 그 양의 변화율의 관계로 귀착되고, 이러한 문제들이 미분방정식으로 다루어진다. 자연의 많은 현상들이 동역학계로 기술될 수 있다. 혼돈 이론은 이러한 예측 불가능한 현상을 탐구하는 데 상당한 기여를 한다.", "answer": "함수의 공간(특히 무한차원)의 탐구", "sentence": "함수해석학은 함수의 공간(특히 무한차원)의 탐구 에 주목한다.", "paragraph_sentence": '변화에 대한 이해와 묘사는 자연과학에 있어서 일반적인 주제이며, 미적분학은 변화를 탐구하는 강력한 도구로서 발전되었다. 함수는 변화하는 양을 묘사함에 있어서 중추적인 개념으로써 떠오르게 된다. 실수와 실변수로 구성된 함수의 엄밀한 탐구가 실해석학이라는 분야로 알려지게 되었고, 복소수에 대한 이와 같은 탐구 분야는 복소해석학이라고 한다. <hl> 함수해석학은 함수의 공간(특히 무한차원)의 탐구 에 주목한다. <hl> 함수해석학의 많은 응용분야 중 하나가 양자역학이다. 많은 문제들이 자연스럽게 양과 그 양의 변화율의 관계로 귀착되고, 이러한 문제들이 미분방정식으로 다루어진다. 자연의 많은 현상들이 동역학계로 기술될 수 있다. 혼돈 이론은 이러한 예측 불가능한 현상을 탐구하는 데 상당한 기여를 한다.', "paragraph_answer": '변화에 대한 이해와 묘사는 자연과학에 있어서 일반적인 주제이며, 미적분학은 변화를 탐구하는 강력한 도구로서 발전되었다. 함수는 변화하는 양을 묘사함에 있어서 중추적인 개념으로써 떠오르게 된다. 실수와 실변수로 구성된 함수의 엄밀한 탐구가 실해석학이라는 분야로 알려지게 되었고, 복소수에 대한 이와 같은 탐구 분야는 복소해석학이라고 한다. 함수해석학은 <hl> 함수의 공간(특히 무한차원)의 탐구 <hl>에 주목한다. 함수해석학의 많은 응용분야 중 하나가 양자역학이다. 많은 문제들이 자연스럽게 양과 그 양의 변화율의 관계로 귀착되고, 이러한 문제들이 미분방정식으로 다루어진다. 자연의 많은 현상들이 동역학계로 기술될 수 있다. 혼돈 이론은 이러한 예측 불가능한 현상을 탐구하는 데 상당한 기여를 한다.', "sentence_answer": "함수해석학은 <hl> 함수의 공간(특히 무한차원)의 탐구 <hl> 에 주목한다." } ``` The data fields are the same among all splits. - `question`: a `string` feature. - `paragraph`: a `string` feature. - `answer`: a `string` feature. - `sentence`: a `string` feature. - `paragraph_answer`: a `string` feature, which is same as the paragraph but the answer is highlighted by a special token `<hl>`. - `paragraph_sentence`: a `string` feature, which is same as the paragraph but a sentence containing the answer is highlighted by a special token `<hl>`. - `sentence_answer`: a `string` feature, which is same as the sentence but the answer is highlighted by a special token `<hl>`. Each of `paragraph_answer`, `paragraph_sentence`, and `sentence_answer` feature is assumed to be used to train a question generation model, but with different information. The `paragraph_answer` and `sentence_answer` features are for answer-aware question generation and `paragraph_sentence` feature is for sentence-aware question generation. ## Data Splits \|train\|validation\|test \| \|----:\|---------:\|----:\| \|54556\| 5766 \|5766 \| ## Citation Information ``` @inproceedings{ushio-etal-2022-generative, title = "{G}enerative {L}anguage {M}odels for {P}aragraph-{L}evel {Q}uestion {G}eneration: {A} {U}nified {B}enchmark and {E}valuation", author = "Ushio, Asahi and Alva-Manchego, Fernando and Camacho-Collados, Jose", booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing", month = dec, year = "2022", address = "Abu Dhabi, U.A.E.", publisher = "Association for Computational Linguistics", } ```
fxmarty/transformers-regressions	fxmarty	"2023-09-27T13:33:28Z"	16,131	0	[ "license:mit", "region:us" ]	null	"2023-08-08T14:18:24Z"	--- license: mit ---
nyu-mll/blimp	nyu-mll	"2024-01-23T09:58:08Z"	16,130	37	[ "task_categories:text-classification", "task_ids:acceptability-classification", "annotations_creators:crowdsourced", "language_creators:machine-generated", "multilinguality:monolingual", "source_datasets:original", "language:en", "license:cc-by-4.0", "size_categories:10K<n<100K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "arxiv:1912.00582", "region:us" ]	[ "text-classification" ]	"2022-03-02T23:29:22Z"	--- annotations_creators: - crowdsourced language_creators: - machine-generated language: - en license: - cc-by-4.0 multilinguality: - monolingual size_categories: - 10K<n<100K source_datasets: - original task_categories: - text-classification task_ids: - acceptability-classification paperswithcode_id: blimp pretty_name: BLiMP dataset_info: - config_name: adjunct_island features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 165894 num_examples: 1000 download_size: 62231 dataset_size: 165894 - config_name: anaphor_gender_agreement features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 130918 num_examples: 1000 download_size: 39201 dataset_size: 130918 - config_name: anaphor_number_agreement features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 139879 num_examples: 1000 download_size: 41547 dataset_size: 139879 - config_name: animate_subject_passive features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 144423 num_examples: 1000 download_size: 47282 dataset_size: 144423 - config_name: animate_subject_trans features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 127798 num_examples: 1000 download_size: 49651 dataset_size: 127798 - config_name: causative features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 122772 num_examples: 1000 download_size: 48963 dataset_size: 122772 - config_name: complex_NP_island features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 198972 num_examples: 1000 download_size: 78211 dataset_size: 198972 - config_name: coordinate_structure_constraint_complex_left_branch features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 210912 num_examples: 1000 download_size: 67908 dataset_size: 210912 - config_name: coordinate_structure_constraint_object_extraction features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 171655 num_examples: 1000 download_size: 51584 dataset_size: 171655 - config_name: determiner_noun_agreement_1 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 156120 num_examples: 1000 download_size: 49893 dataset_size: 156120 - config_name: determiner_noun_agreement_2 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 156204 num_examples: 1000 download_size: 49527 dataset_size: 156204 - config_name: determiner_noun_agreement_irregular_1 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 164473 num_examples: 1000 download_size: 47274 dataset_size: 164473 - config_name: determiner_noun_agreement_irregular_2 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 161074 num_examples: 1000 download_size: 47422 dataset_size: 161074 - config_name: determiner_noun_agreement_with_adj_2 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 179666 num_examples: 1000 download_size: 56346 dataset_size: 179666 - config_name: determiner_noun_agreement_with_adj_irregular_1 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 184529 num_examples: 1000 download_size: 54405 dataset_size: 184529 - config_name: determiner_noun_agreement_with_adj_irregular_2 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 184396 num_examples: 1000 download_size: 54064 dataset_size: 184396 - config_name: determiner_noun_agreement_with_adjective_1 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 185126 num_examples: 1000 download_size: 55682 dataset_size: 185126 - config_name: distractor_agreement_relational_noun features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 191473 num_examples: 1000 download_size: 59641 dataset_size: 191473 - config_name: distractor_agreement_relative_clause features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 216756 num_examples: 1000 download_size: 77897 dataset_size: 216756 - config_name: drop_argument features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 109806 num_examples: 1000 download_size: 39961 dataset_size: 109806 - config_name: ellipsis_n_bar_1 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 217590 num_examples: 1000 download_size: 92776 dataset_size: 217590 - config_name: ellipsis_n_bar_2 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 233161 num_examples: 1000 download_size: 98882 dataset_size: 233161 - config_name: existential_there_object_raising features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 223741 num_examples: 1000 download_size: 76641 dataset_size: 223741 - config_name: existential_there_quantifiers_1 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 162931 num_examples: 1000 download_size: 51576 dataset_size: 162931 - config_name: existential_there_quantifiers_2 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 164826 num_examples: 1000 download_size: 52092 dataset_size: 164826 - config_name: existential_there_subject_raising features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 200063 num_examples: 1000 download_size: 59519 dataset_size: 200063 - config_name: expletive_it_object_raising features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 238615 num_examples: 1000 download_size: 88607 dataset_size: 238615 - config_name: inchoative features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 104319 num_examples: 1000 download_size: 39842 dataset_size: 104319 - config_name: intransitive features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 111097 num_examples: 1000 download_size: 42387 dataset_size: 111097 - config_name: irregular_past_participle_adjectives features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 144661 num_examples: 1000 download_size: 36654 dataset_size: 144661 - config_name: irregular_past_participle_verbs features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 125692 num_examples: 1000 download_size: 37297 dataset_size: 125692 - config_name: irregular_plural_subject_verb_agreement_1 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 165584 num_examples: 1000 download_size: 50725 dataset_size: 165584 - config_name: irregular_plural_subject_verb_agreement_2 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 153843 num_examples: 1000 download_size: 42707 dataset_size: 153843 - config_name: left_branch_island_echo_question features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 147840 num_examples: 1000 download_size: 50481 dataset_size: 147840 - config_name: left_branch_island_simple_question features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 150060 num_examples: 1000 download_size: 50293 dataset_size: 150060 - config_name: matrix_question_npi_licensor_present features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 153262 num_examples: 1000 download_size: 51899 dataset_size: 153262 - config_name: npi_present_1 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 138465 num_examples: 1000 download_size: 51981 dataset_size: 138465 - config_name: npi_present_2 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 127636 num_examples: 1000 download_size: 51661 dataset_size: 127636 - config_name: only_npi_licensor_present features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 148516 num_examples: 1000 download_size: 51361 dataset_size: 148516 - config_name: only_npi_scope features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 208902 num_examples: 1000 download_size: 84970 dataset_size: 208902 - config_name: passive_1 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 145882 num_examples: 1000 download_size: 53931 dataset_size: 145882 - config_name: passive_2 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 113960 num_examples: 1000 download_size: 40499 dataset_size: 113960 - config_name: principle_A_c_command features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 188490 num_examples: 1000 download_size: 67867 dataset_size: 188490 - config_name: principle_A_case_1 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 170398 num_examples: 1000 download_size: 61092 dataset_size: 170398 - config_name: principle_A_case_2 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 170412 num_examples: 1000 download_size: 56430 dataset_size: 170412 - config_name: principle_A_domain_1 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 171170 num_examples: 1000 download_size: 59120 dataset_size: 171170 - config_name: principle_A_domain_2 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 165333 num_examples: 1000 download_size: 58464 dataset_size: 165333 - config_name: principle_A_domain_3 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 158998 num_examples: 1000 download_size: 52859 dataset_size: 158998 - config_name: principle_A_reconstruction features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 152104 num_examples: 1000 download_size: 44480 dataset_size: 152104 - config_name: regular_plural_subject_verb_agreement_1 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 158819 num_examples: 1000 download_size: 49466 dataset_size: 158819 - config_name: regular_plural_subject_verb_agreement_2 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 153609 num_examples: 1000 download_size: 43365 dataset_size: 153609 - config_name: sentential_negation_npi_licensor_present features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 171864 num_examples: 1000 download_size: 54830 dataset_size: 171864 - config_name: sentential_negation_npi_scope features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 232098 num_examples: 1000 download_size: 90157 dataset_size: 232098 - config_name: sentential_subject_island features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 172432 num_examples: 1000 download_size: 56666 dataset_size: 172432 - config_name: superlative_quantifiers_1 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 159290 num_examples: 1000 download_size: 48453 dataset_size: 159290 - config_name: superlative_quantifiers_2 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 159340 num_examples: 1000 download_size: 50480 dataset_size: 159340 - config_name: tough_vs_raising_1 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 148636 num_examples: 1000 download_size: 44779 dataset_size: 148636 - config_name: tough_vs_raising_2 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 169684 num_examples: 1000 download_size: 61465 dataset_size: 169684 - config_name: transitive features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 133104 num_examples: 1000 download_size: 55090 dataset_size: 133104 - config_name: wh_island features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 142340 num_examples: 1000 download_size: 52808 dataset_size: 142340 - config_name: wh_questions_object_gap features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 193045 num_examples: 1000 download_size: 70049 dataset_size: 193045 - config_name: wh_questions_subject_gap features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 195593 num_examples: 1000 download_size: 71632 dataset_size: 195593 - config_name: wh_questions_subject_gap_long_distance features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 268270 num_examples: 1000 download_size: 98913 dataset_size: 268270 - config_name: wh_vs_that_no_gap features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 188872 num_examples: 1000 download_size: 71710 dataset_size: 188872 - config_name: wh_vs_that_no_gap_long_distance features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 247039 num_examples: 1000 download_size: 95504 dataset_size: 247039 - config_name: wh_vs_that_with_gap features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 173386 num_examples: 1000 download_size: 60291 dataset_size: 173386 - config_name: wh_vs_that_with_gap_long_distance features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 231595 num_examples: 1000 download_size: 84147 dataset_size: 231595 configs: - config_name: adjunct_island data_files: - split: train path: adjunct_island/train-* - config_name: anaphor_gender_agreement data_files: - split: train path: anaphor_gender_agreement/train-* - config_name: anaphor_number_agreement data_files: - split: train path: anaphor_number_agreement/train-* - config_name: animate_subject_passive data_files: - split: train path: animate_subject_passive/train-* - config_name: animate_subject_trans data_files: - split: train path: animate_subject_trans/train-* - config_name: causative data_files: - split: train path: causative/train-* - config_name: complex_NP_island data_files: - split: train path: complex_NP_island/train-* - config_name: coordinate_structure_constraint_complex_left_branch data_files: - split: train path: coordinate_structure_constraint_complex_left_branch/train-* - config_name: coordinate_structure_constraint_object_extraction data_files: - split: train path: coordinate_structure_constraint_object_extraction/train-* - config_name: determiner_noun_agreement_1 data_files: - split: train path: determiner_noun_agreement_1/train-* - config_name: determiner_noun_agreement_2 data_files: - split: train path: determiner_noun_agreement_2/train-* - config_name: determiner_noun_agreement_irregular_1 data_files: - split: train path: determiner_noun_agreement_irregular_1/train-* - config_name: determiner_noun_agreement_irregular_2 data_files: - split: train path: determiner_noun_agreement_irregular_2/train-* - config_name: determiner_noun_agreement_with_adj_2 data_files: - split: train path: determiner_noun_agreement_with_adj_2/train-* - config_name: determiner_noun_agreement_with_adj_irregular_1 data_files: - split: train path: determiner_noun_agreement_with_adj_irregular_1/train-* - config_name: determiner_noun_agreement_with_adj_irregular_2 data_files: - split: train path: determiner_noun_agreement_with_adj_irregular_2/train-* - config_name: determiner_noun_agreement_with_adjective_1 data_files: - split: train path: determiner_noun_agreement_with_adjective_1/train-* - config_name: distractor_agreement_relational_noun data_files: - split: train path: distractor_agreement_relational_noun/train-* - config_name: distractor_agreement_relative_clause data_files: - split: train path: distractor_agreement_relative_clause/train-* - config_name: drop_argument data_files: - split: train path: drop_argument/train-* - config_name: ellipsis_n_bar_1 data_files: - split: train path: ellipsis_n_bar_1/train-* - config_name: ellipsis_n_bar_2 data_files: - split: train path: ellipsis_n_bar_2/train-* - config_name: existential_there_object_raising data_files: - split: train path: existential_there_object_raising/train-* - config_name: existential_there_quantifiers_1 data_files: - split: train path: existential_there_quantifiers_1/train-* - config_name: existential_there_quantifiers_2 data_files: - split: train path: existential_there_quantifiers_2/train-* - config_name: existential_there_subject_raising data_files: - split: train path: existential_there_subject_raising/train-* - config_name: expletive_it_object_raising data_files: - split: train path: expletive_it_object_raising/train-* - config_name: inchoative data_files: - split: train path: inchoative/train-* - config_name: intransitive data_files: - split: train path: intransitive/train-* - config_name: irregular_past_participle_adjectives data_files: - split: train path: irregular_past_participle_adjectives/train-* - config_name: irregular_past_participle_verbs data_files: - split: train path: irregular_past_participle_verbs/train-* - config_name: irregular_plural_subject_verb_agreement_1 data_files: - split: train path: irregular_plural_subject_verb_agreement_1/train-* - config_name: irregular_plural_subject_verb_agreement_2 data_files: - split: train path: irregular_plural_subject_verb_agreement_2/train-* - config_name: left_branch_island_echo_question data_files: - split: train path: left_branch_island_echo_question/train-* - config_name: left_branch_island_simple_question data_files: - split: train path: left_branch_island_simple_question/train-* - config_name: matrix_question_npi_licensor_present data_files: - split: train path: matrix_question_npi_licensor_present/train-* - config_name: npi_present_1 data_files: - split: train path: npi_present_1/train-* - config_name: npi_present_2 data_files: - split: train path: npi_present_2/train-* - config_name: only_npi_licensor_present data_files: - split: train path: only_npi_licensor_present/train-* - config_name: only_npi_scope data_files: - split: train path: only_npi_scope/train-* - config_name: passive_1 data_files: - split: train path: passive_1/train-* - config_name: passive_2 data_files: - split: train path: passive_2/train-* - config_name: principle_A_c_command data_files: - split: train path: principle_A_c_command/train-* - config_name: principle_A_case_1 data_files: - split: train path: principle_A_case_1/train-* - config_name: principle_A_case_2 data_files: - split: train path: principle_A_case_2/train-* - config_name: principle_A_domain_1 data_files: - split: train path: principle_A_domain_1/train-* - config_name: principle_A_domain_2 data_files: - split: train path: principle_A_domain_2/train-* - config_name: principle_A_domain_3 data_files: - split: train path: principle_A_domain_3/train-* - config_name: principle_A_reconstruction data_files: - split: train path: principle_A_reconstruction/train-* - config_name: regular_plural_subject_verb_agreement_1 data_files: - split: train path: regular_plural_subject_verb_agreement_1/train-* - config_name: regular_plural_subject_verb_agreement_2 data_files: - split: train path: regular_plural_subject_verb_agreement_2/train-* - config_name: sentential_negation_npi_licensor_present data_files: - split: train path: sentential_negation_npi_licensor_present/train-* - config_name: sentential_negation_npi_scope data_files: - split: train path: sentential_negation_npi_scope/train-* - config_name: sentential_subject_island data_files: - split: train path: sentential_subject_island/train-* - config_name: superlative_quantifiers_1 data_files: - split: train path: superlative_quantifiers_1/train-* - config_name: superlative_quantifiers_2 data_files: - split: train path: superlative_quantifiers_2/train-* - config_name: tough_vs_raising_1 data_files: - split: train path: tough_vs_raising_1/train-* - config_name: tough_vs_raising_2 data_files: - split: train path: tough_vs_raising_2/train-* - config_name: transitive data_files: - split: train path: transitive/train-* - config_name: wh_island data_files: - split: train path: wh_island/train-* - config_name: wh_questions_object_gap data_files: - split: train path: wh_questions_object_gap/train-* - config_name: wh_questions_subject_gap data_files: - split: train path: wh_questions_subject_gap/train-* - config_name: wh_questions_subject_gap_long_distance data_files: - split: train path: wh_questions_subject_gap_long_distance/train-* - config_name: wh_vs_that_no_gap data_files: - split: train path: wh_vs_that_no_gap/train-* - config_name: wh_vs_that_no_gap_long_distance data_files: - split: train path: wh_vs_that_no_gap_long_distance/train-* - config_name: wh_vs_that_with_gap data_files: - split: train path: wh_vs_that_with_gap/train-* - config_name: wh_vs_that_with_gap_long_distance data_files: - split: train path: wh_vs_that_with_gap_long_distance/train-* --- # Dataset Card for "blimp" ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - Homepage: - Repository: https://github.com/alexwarstadt/blimp - Paper: [BLiMP: The Benchmark of Linguistic Minimal Pairs for English](https://doi.org/10.1162/tacl_a_00321) - Paper: https://arxiv.org/abs/1912.00582 - Point of Contact: [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - Size of downloaded dataset files: 29.58 MB - Size of the generated dataset: 11.45 MB - Total amount of disk used: 41.03 MB ### Dataset Summary BLiMP is a challenge set for evaluating what language models (LMs) know about major grammatical phenomena in English. BLiMP consists of 67 sub-datasets, each containing 1000 minimal pairs isolating specific contrasts in syntax, morphology, or semantics. The data is automatically generated according to expert-crafted grammars. ### Supported Tasks and Leaderboards [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Languages [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Dataset Structure ### Data Instances #### adjunct_island - Size of downloaded dataset files: 0.36 MB - Size of the generated dataset: 0.17 MB - Total amount of disk used: 0.52 MB An example of 'train' looks as follows. ``` { "UID": "tough_vs_raising_1", "field": "syntax_semantics", "lexically_identical": false, "linguistics_term": "control_raising", "one_prefix_method": false, "pair_id": 2, "sentence_bad": "Benjamin's tutor was certain to boast about.", "sentence_good": "Benjamin's tutor was easy to boast about.", "simple_LM_method": true, "two_prefix_method": false } ``` #### anaphor_gender_agreement - Size of downloaded dataset files: 0.44 MB - Size of the generated dataset: 0.14 MB - Total amount of disk used: 0.57 MB An example of 'train' looks as follows. ``` { "UID": "tough_vs_raising_1", "field": "syntax_semantics", "lexically_identical": false, "linguistics_term": "control_raising", "one_prefix_method": false, "pair_id": 2, "sentence_bad": "Benjamin's tutor was certain to boast about.", "sentence_good": "Benjamin's tutor was easy to boast about.", "simple_LM_method": true, "two_prefix_method": false } ``` #### anaphor_number_agreement - Size of downloaded dataset files: 0.45 MB - Size of the generated dataset: 0.14 MB - Total amount of disk used: 0.59 MB An example of 'train' looks as follows. ``` { "UID": "tough_vs_raising_1", "field": "syntax_semantics", "lexically_identical": false, "linguistics_term": "control_raising", "one_prefix_method": false, "pair_id": 2, "sentence_bad": "Benjamin's tutor was certain to boast about.", "sentence_good": "Benjamin's tutor was easy to boast about.", "simple_LM_method": true, "two_prefix_method": false } ``` #### animate_subject_passive - Size of downloaded dataset files: 0.46 MB - Size of the generated dataset: 0.15 MB - Total amount of disk used: 0.61 MB An example of 'train' looks as follows. ``` { "UID": "tough_vs_raising_1", "field": "syntax_semantics", "lexically_identical": false, "linguistics_term": "control_raising", "one_prefix_method": false, "pair_id": 2, "sentence_bad": "Benjamin's tutor was certain to boast about.", "sentence_good": "Benjamin's tutor was easy to boast about.", "simple_LM_method": true, "two_prefix_method": false } ``` #### animate_subject_trans - Size of downloaded dataset files: 0.43 MB - Size of the generated dataset: 0.13 MB - Total amount of disk used: 0.57 MB An example of 'train' looks as follows. ``` { "UID": "tough_vs_raising_1", "field": "syntax_semantics", "lexically_identical": false, "linguistics_term": "control_raising", "one_prefix_method": false, "pair_id": 2, "sentence_bad": "Benjamin's tutor was certain to boast about.", "sentence_good": "Benjamin's tutor was easy to boast about.", "simple_LM_method": true, "two_prefix_method": false } ``` ### Data Fields The data fields are the same among all splits. #### adjunct_island - `sentence_good`: a `string` feature. - `sentence_bad`: a `string` feature. - `field`: a `string` feature. - `linguistics_term`: a `string` feature. - `UID`: a `string` feature. - `simple_LM_method`: a `bool` feature. - `one_prefix_method`: a `bool` feature. - `two_prefix_method`: a `bool` feature. - `lexically_identical`: a `bool` feature. - `pair_id`: a `int32` feature. #### anaphor_gender_agreement - `sentence_good`: a `string` feature. - `sentence_bad`: a `string` feature. - `field`: a `string` feature. - `linguistics_term`: a `string` feature. - `UID`: a `string` feature. - `simple_LM_method`: a `bool` feature. - `one_prefix_method`: a `bool` feature. - `two_prefix_method`: a `bool` feature. - `lexically_identical`: a `bool` feature. - `pair_id`: a `int32` feature. #### anaphor_number_agreement - `sentence_good`: a `string` feature. - `sentence_bad`: a `string` feature. - `field`: a `string` feature. - `linguistics_term`: a `string` feature. - `UID`: a `string` feature. - `simple_LM_method`: a `bool` feature. - `one_prefix_method`: a `bool` feature. - `two_prefix_method`: a `bool` feature. - `lexically_identical`: a `bool` feature. - `pair_id`: a `int32` feature. #### animate_subject_passive - `sentence_good`: a `string` feature. - `sentence_bad`: a `string` feature. - `field`: a `string` feature. - `linguistics_term`: a `string` feature. - `UID`: a `string` feature. - `simple_LM_method`: a `bool` feature. - `one_prefix_method`: a `bool` feature. - `two_prefix_method`: a `bool` feature. - `lexically_identical`: a `bool` feature. - `pair_id`: a `int32` feature. #### animate_subject_trans - `sentence_good`: a `string` feature. - `sentence_bad`: a `string` feature. - `field`: a `string` feature. - `linguistics_term`: a `string` feature. - `UID`: a `string` feature. - `simple_LM_method`: a `bool` feature. - `one_prefix_method`: a `bool` feature. - `two_prefix_method`: a `bool` feature. - `lexically_identical`: a `bool` feature. - `pair_id`: a `int32` feature. ### Data Splits \| name \|train\| \|------------------------\|----:\| \|adjunct_island \| 1000\| \|anaphor_gender_agreement\| 1000\| \|anaphor_number_agreement\| 1000\| \|animate_subject_passive \| 1000\| \|animate_subject_trans \| 1000\| ## Dataset Creation ### Curation Rationale [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Source Data #### Initial Data Collection and Normalization [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the source language producers? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Annotations #### Annotation process [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the annotators? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Personal and Sensitive Information [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Discussion of Biases [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Other Known Limitations [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Additional Information ### Dataset Curators [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Licensing Information BLiMP is distributed under a [CC-BY](https://creativecommons.org/licenses/by/4.0/) license. Source: https://github.com/alexwarstadt/blimp#license ### Citation Information ``` @article{warstadt2020blimp, author = {Warstadt, Alex and Parrish, Alicia and Liu, Haokun and Mohananey, Anhad and Peng, Wei and Wang, Sheng-Fu and Bowman, Samuel R.}, title = {BLiMP: The Benchmark of Linguistic Minimal Pairs for English}, journal = {Transactions of the Association for Computational Linguistics}, volume = {8}, number = {}, pages = {377-392}, year = {2020}, doi = {10.1162/tacl\_a\_00321}, URL = {https://doi.org/10.1162/tacl_a_00321}, eprint = {https://doi.org/10.1162/tacl_a_00321}, abstract = { We introduce The Benchmark of Linguistic Minimal Pairs (BLiMP),1 a challenge set for evaluating the linguistic knowledge of language models (LMs) on major grammatical phenomena in English. BLiMP consists of 67 individual datasets, each containing 1,000 minimal pairs—that is, pairs of minimally different sentences that contrast in grammatical acceptability and isolate specific phenomenon in syntax, morphology, or semantics. We generate the data according to linguist-crafted grammar templates, and human aggregate agreement with the labels is 96.4\%. We evaluate n-gram, LSTM, and Transformer (GPT-2 and Transformer-XL) LMs by observing whether they assign a higher probability to the acceptable sentence in each minimal pair. We find that state-of-the-art models identify morphological contrasts related to agreement reliably, but they struggle with some subtle semantic and syntactic phenomena, such as negative polarity items and extraction islands. } } ``` #### Errata Some results were misreported in the published TACL version. Please refer to the corrected version on arXiv: https://arxiv.org/abs/1912.00582 ### Contributions Thanks to [@lhoestq](https://github.com/lhoestq), [@patrickvonplaten](https://github.com/patrickvonplaten), [@thomwolf](https://github.com/thomwolf) for adding this dataset.
alvations/c4p0-x1-en-ja	alvations	"2024-03-24T03:55:23Z"	15,951	0	[ "size_categories:n<1K", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]	null	"2024-03-23T09:54:37Z"	--- dataset_info: features: - name: source dtype: string - name: target dtype: string - name: target_backto_source dtype: string - name: raw_target list: - name: generated_text dtype: string - name: raw_target_backto_source list: - name: generated_text dtype: string - name: prompt dtype: string - name: reverse_prompt dtype: string - name: source_langid dtype: string - name: target_langid dtype: string - name: target_backto_source_langid dtype: string - name: doc_id dtype: int64 - name: sent_id dtype: int64 - name: timestamp dtype: string - name: url dtype: string - name: doc_hash dtype: string splits: - name: train num_bytes: 49764 num_examples: 42 download_size: 37636 dataset_size: 49764 configs: - config_name: default data_files: - split: train path: 66034f82c5c65ae4/train-* ---
DTU54DL/librispeech-augmentated-train-prepared	DTU54DL	"2022-12-05T14:21:47Z"	15,940	0	[ "size_categories:1K<n<10K", "format:parquet", "modality:audio", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]	null	"2022-11-26T21:55:59Z"	--- dataset_info: features: - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: text dtype: string - name: speaker_id dtype: int64 - name: chapter_id dtype: int64 - name: id dtype: string - name: input_features sequence: sequence: float32 - name: labels sequence: int64 splits: - name: train.360 num_bytes: 6796928865.0 num_examples: 5000 download_size: 3988873165 dataset_size: 6796928865.0 --- # Dataset Card for "librispeech-augmentated-train-prepared" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
shenyunhang/VoiceAssistant-400K	shenyunhang	"2025-03-23T08:36:31Z"	15,853	0	[ "license:apache-2.0", "region:us" ]	null	"2025-03-19T02:01:25Z"	--- license: apache-2.0 --- --- Data source: https://huggingface.co/datasets/gpt-omni/VoiceAssistant-400K 1. Question and answer audios are extracted, which results in `940,108` audio files. 2. Raw conversations are formed as multi-round chat format in `data.jsonl`, which has in total of `251,223` samples. ``` [ ... { "messages": [ { "role": "user", "content": "...<\|audio\|>" }, { "role": "assistant", "content": "...<\|audio\|>" } { "role": "user", "content": "...<\|audio\|>" }, { "role": "assistant", "content": "...<\|audio\|>" }, ... ], "audios": ["path/to/first/audio", "path/to/second/audio", "path/to/third/audio", "path/to/forth/audio", ...], }, ... ] ``` ---
lmms-lab/MMMU	lmms-lab	"2024-03-08T05:09:42Z"	15,840	4	[ "size_categories:10K<n<100K", "format:parquet", "modality:image", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]	null	"2024-01-15T06:32:16Z"	--- dataset_info: features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 57719107.0 num_examples: 150 - name: validation num_bytes: 347519954.0 num_examples: 900 - name: test num_bytes: 3271046267.0 num_examples: 10500 download_size: 3377778136 dataset_size: 3676285328.0 configs: - config_name: default data_files: - split: dev path: data/dev-* - split: validation path: data/validation-* - split: test path: data/test-* --- This is a merged version of [MMMU/MMMU](https://huggingface.co/datasets/MMMU/MMMU) with all subsets concatenated. <p align="center" width="100%"> <img src="https://i.postimg.cc/g0QRgMVv/WX20240228-113337-2x.png" width="100%" height="80%"> </p> # Large-scale Multi-modality Models Evaluation Suite > Accelerating the development of large-scale multi-modality models (LMMs) with `lmms-eval` 🏠 [Homepage](https://lmms-lab.github.io/) \| 📚 [Documentation](docs/README.md) \| 🤗 [Huggingface Datasets](https://huggingface.co/lmms-lab) # This Dataset This is a formatted version of [MMMU](https://github.com/MMMU-Benchmark/MMMU). It is used in our `lmms-eval` pipeline to allow for one-click evaluations of large multi-modality models. ``` @article{yue2023mmmu, title={Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi}, author={Yue, Xiang and Ni, Yuansheng and Zhang, Kai and Zheng, Tianyu and Liu, Ruoqi and Zhang, Ge and Stevens, Samuel and Jiang, Dongfu and Ren, Weiming and Sun, Yuxuan and others}, journal={arXiv preprint arXiv:2311.16502}, year={2023} } ```
pixparse/cc12m-wds	pixparse	"2023-12-15T04:50:41Z"	15,829	27	[ "task_categories:image-to-text", "license:other", "size_categories:10M<n<100M", "format:webdataset", "modality:image", "modality:text", "library:datasets", "library:webdataset", "library:mlcroissant", "arxiv:2102.08981", "region:us" ]	[ "image-to-text" ]	"2023-12-12T23:59:59Z"	--- license: other license_name: conceptual-12m license_link: LICENSE task_categories: - image-to-text size_categories: - 10M<n<100M --- # Dataset Card for Conceptual Captions 12M (CC12M) ## Dataset Description - Repository: [Conceptual 12M repository](https://github.com/google-research-datasets/conceptual-12m) - Paper: [Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts](https://arxiv.org/abs/2102.08981) - Point of Contact: [Conceptual Captions e-mail](mailto:[email protected]) ### Dataset Summary Conceptual 12M (CC12M) is a dataset with 12 million image-text pairs specifically meant to be used for visionand-language pre-training. Its data collection pipeline is a relaxed version of the one used in Conceptual Captions 3M (CC3M). ### Usage This instance of Conceptual Captions is in [webdataset](https://github.com/webdataset/webdataset/commits/main) .tar format. It can be used with webdataset library or upcoming releases of Hugging Face `datasets`. ...More Detail TBD ### Data Splits This dataset was downloaded using img2dataset. Images resized on download if shortest edge > 512 to shortest edge = 512. #### Train * `cc12m-train-.tar` Downloaded on 2021/18/22 * 2176 shards, 10968539 samples ## Additional Information ### Dataset Curators Soravit Changpinyo, Piyush Sharma, Nan Ding and Radu Soricut. ### Licensing Information The dataset may be freely used for any purpose, although acknowledgement of Google LLC ("Google") as the data source would be appreciated. The dataset is provided "AS IS" without any warranty, express or implied. Google disclaims all liability for any damages, direct or indirect, resulting from the use of the dataset. ### Citation Information ```bibtex @inproceedings{changpinyo2021cc12m, title = {{Conceptual 12M}: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts}, author = {Changpinyo, Soravit and Sharma, Piyush and Ding, Nan and Soricut, Radu}, booktitle = {CVPR}, year = {2021}, } ```
alvarobartt/mmlu-okapi-eval-es	alvarobartt	"2024-02-29T17:57:41Z"	15,789	1	[ "task_categories:multiple-choice", "task_categories:question-answering", "task_ids:multiple-choice-qa", "task_ids:open-domain-qa", "language:es", "license:cc-by-nc-4.0", "size_categories:10K<n<100K", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "arxiv:2009.03300", "arxiv:2307.16039", "region:us", "chatgpt-translated" ]	[ "multiple-choice", "question-answering" ]	"2024-02-29T12:55:40Z"	--- language: - es license: cc-by-nc-4.0 size_categories: - 10K<n<100K task_categories: - multiple-choice - question-answering task_ids: - multiple-choice-qa - open-domain-qa tags: - chatgpt-translated dataset_info: - config_name: abstract_algebra features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 1760 num_examples: 5 - name: validation num_bytes: 4246 num_examples: 11 - name: test num_bytes: 40783 num_examples: 100 download_size: 31838 dataset_size: 46789 - config_name: anatomy features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 2024 num_examples: 5 - name: validation num_bytes: 6533 num_examples: 14 - name: test num_bytes: 68781 num_examples: 134 download_size: 55543 dataset_size: 77338 - config_name: astronomy features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 4476 num_examples: 5 - name: validation num_bytes: 10713 num_examples: 16 - name: test num_bytes: 100179 num_examples: 152 download_size: 78498 dataset_size: 115368 - config_name: business_ethics features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 4608 num_examples: 5 - name: validation num_bytes: 6415 num_examples: 11 - name: test num_bytes: 69628 num_examples: 98 download_size: 62408 dataset_size: 80651 - config_name: clinical_knowledge features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 2594 num_examples: 5 - name: validation num_bytes: 14438 num_examples: 29 - name: test num_bytes: 135086 num_examples: 263 download_size: 103601 dataset_size: 152118 - config_name: college_biology features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 3177 num_examples: 5 - name: validation num_bytes: 10330 num_examples: 16 - name: test num_bytes: 103413 num_examples: 143 download_size: 87080 dataset_size: 116920 - config_name: college_chemistry features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 2779 num_examples: 5 - name: validation num_bytes: 4874 num_examples: 8 - name: test num_bytes: 52123 num_examples: 100 download_size: 51328 dataset_size: 59776 - config_name: college_computer_science features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 5805 num_examples: 5 - name: validation num_bytes: 9920 num_examples: 11 - name: test num_bytes: 89185 num_examples: 98 download_size: 82341 dataset_size: 104910 - config_name: college_mathematics features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 3089 num_examples: 5 - name: validation num_bytes: 5484 num_examples: 11 - name: test num_bytes: 50044 num_examples: 97 download_size: 51658 dataset_size: 58617 - config_name: college_medicine features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 3649 num_examples: 5 - name: validation num_bytes: 16728 num_examples: 22 - name: test num_bytes: 171553 num_examples: 171 download_size: 115167 dataset_size: 191930 - config_name: college_physics features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 2898 num_examples: 5 - name: validation num_bytes: 7335 num_examples: 11 - name: test num_bytes: 62094 num_examples: 100 download_size: 57235 dataset_size: 72327 - config_name: computer_security features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 1733 num_examples: 4 - name: validation num_bytes: 9678 num_examples: 11 - name: test num_bytes: 58507 num_examples: 100 download_size: 57512 dataset_size: 69918 - config_name: conceptual_physics features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 1965 num_examples: 5 - name: validation num_bytes: 9503 num_examples: 26 - name: test num_bytes: 86744 num_examples: 235 download_size: 69227 dataset_size: 98212 - config_name: econometrics features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 3459 num_examples: 5 - name: validation num_bytes: 10475 num_examples: 12 - name: test num_bytes: 94779 num_examples: 110 download_size: 71152 dataset_size: 108713 - config_name: electrical_engineering features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 2046 num_examples: 5 - name: validation num_bytes: 6173 num_examples: 16 - name: test num_bytes: 54302 num_examples: 145 download_size: 51393 dataset_size: 62521 - config_name: elementary_mathematics features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 2726 num_examples: 4 - name: validation num_bytes: 18444 num_examples: 40 - name: test num_bytes: 144531 num_examples: 369 download_size: 109491 dataset_size: 165701 - config_name: formal_logic features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 3619 num_examples: 5 - name: validation num_bytes: 12939 num_examples: 14 - name: test num_bytes: 96569 num_examples: 118 download_size: 63090 dataset_size: 113127 - config_name: global_facts features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 2553 num_examples: 5 - name: validation num_bytes: 3941 num_examples: 10 - name: test num_bytes: 39400 num_examples: 100 download_size: 37322 dataset_size: 45894 - config_name: high_school_biology features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 3476 num_examples: 5 - name: validation num_bytes: 23395 num_examples: 32 - name: test num_bytes: 232885 num_examples: 309 download_size: 158998 dataset_size: 259756 - config_name: high_school_chemistry features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 2507 num_examples: 5 - name: validation num_bytes: 14839 num_examples: 22 - name: test num_bytes: 120079 num_examples: 200 download_size: 90031 dataset_size: 137425 - config_name: high_school_computer_science features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 6121 num_examples: 5 - name: validation num_bytes: 6988 num_examples: 8 - name: test num_bytes: 93799 num_examples: 97 download_size: 75958 dataset_size: 106908 - config_name: high_school_european_history features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 14265 num_examples: 3 - name: validation num_bytes: 57480 num_examples: 17 - name: test num_bytes: 479646 num_examples: 148 download_size: 359755 dataset_size: 551391 - config_name: high_school_geography features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 3101 num_examples: 5 - name: validation num_bytes: 9160 num_examples: 22 - name: test num_bytes: 87342 num_examples: 192 download_size: 75260 dataset_size: 99603 - config_name: high_school_government_and_politics features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 3772 num_examples: 5 - name: validation num_bytes: 14984 num_examples: 21 - name: test num_bytes: 141849 num_examples: 193 download_size: 106607 dataset_size: 160605 - config_name: high_school_macroeconomics features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 2933 num_examples: 5 - name: validation num_bytes: 27945 num_examples: 43 - name: test num_bytes: 249710 num_examples: 387 download_size: 141531 dataset_size: 280588 - config_name: high_school_mathematics features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 2617 num_examples: 5 - name: validation num_bytes: 11798 num_examples: 28 - name: test num_bytes: 112551 num_examples: 266 download_size: 89117 dataset_size: 126966 - config_name: high_school_microeconomics features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 2710 num_examples: 5 - name: validation num_bytes: 16309 num_examples: 26 - name: test num_bytes: 160145 num_examples: 234 download_size: 98676 dataset_size: 179164 - config_name: high_school_physics features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 3173 num_examples: 5 - name: validation num_bytes: 14127 num_examples: 17 - name: test num_bytes: 123938 num_examples: 149 download_size: 90127 dataset_size: 141238 - config_name: high_school_psychology features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 3883 num_examples: 5 - name: validation num_bytes: 36566 num_examples: 60 - name: test num_bytes: 318886 num_examples: 513 download_size: 221819 dataset_size: 359335 - config_name: high_school_statistics features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 5264 num_examples: 5 - name: validation num_bytes: 21199 num_examples: 23 - name: test num_bytes: 234094 num_examples: 215 download_size: 150556 dataset_size: 260557 - config_name: high_school_us_history features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 10940 num_examples: 3 - name: validation num_bytes: 57373 num_examples: 19 - name: test num_bytes: 415443 num_examples: 149 download_size: 309982 dataset_size: 483756 - config_name: high_school_world_history features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 10120 num_examples: 5 - name: validation num_bytes: 70014 num_examples: 21 - name: test num_bytes: 629850 num_examples: 201 download_size: 441428 dataset_size: 709984 - config_name: human_aging features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 2066 num_examples: 5 - name: validation num_bytes: 10131 num_examples: 23 - name: test num_bytes: 96475 num_examples: 219 download_size: 81152 dataset_size: 108672 - config_name: human_sexuality features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 1251 num_examples: 3 - name: validation num_bytes: 5129 num_examples: 12 - name: test num_bytes: 53324 num_examples: 110 download_size: 53146 dataset_size: 59704 - config_name: international_law features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 5118 num_examples: 5 - name: validation num_bytes: 13609 num_examples: 13 - name: test num_bytes: 114851 num_examples: 121 download_size: 83492 dataset_size: 133578 - config_name: jurisprudence features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 2642 num_examples: 5 - name: validation num_bytes: 7940 num_examples: 11 - name: test num_bytes: 71653 num_examples: 108 download_size: 66964 dataset_size: 82235 - config_name: logical_fallacies features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 3160 num_examples: 5 - name: validation num_bytes: 10588 num_examples: 18 - name: test num_bytes: 103636 num_examples: 161 download_size: 66840 dataset_size: 117384 - config_name: machine_learning features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 5036 num_examples: 5 - name: validation num_bytes: 6891 num_examples: 11 - name: test num_bytes: 73135 num_examples: 112 download_size: 60833 dataset_size: 85062 - config_name: management features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 1872 num_examples: 5 - name: validation num_bytes: 3799 num_examples: 11 - name: test num_bytes: 42556 num_examples: 103 download_size: 43017 dataset_size: 48227 - config_name: marketing features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 3239 num_examples: 5 - name: validation num_bytes: 15704 num_examples: 25 - name: test num_bytes: 132425 num_examples: 231 download_size: 98948 dataset_size: 151368 - config_name: medical_genetics features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 2284 num_examples: 5 - name: validation num_bytes: 6400 num_examples: 11 - name: test num_bytes: 44372 num_examples: 100 download_size: 48735 dataset_size: 53056 - config_name: miscellaneous features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 1437 num_examples: 5 - name: validation num_bytes: 30333 num_examples: 86 - name: test num_bytes: 304980 num_examples: 760 download_size: 231606 dataset_size: 336750 - config_name: moral_disputes features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 3671 num_examples: 5 - name: validation num_bytes: 25869 num_examples: 38 - name: test num_bytes: 214143 num_examples: 327 download_size: 147774 dataset_size: 243683 - config_name: moral_scenarios features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 2657 num_examples: 3 - name: validation num_bytes: 71335 num_examples: 78 - name: test num_bytes: 683382 num_examples: 752 download_size: 213484 dataset_size: 757374 - config_name: nutrition features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 4523 num_examples: 5 - name: validation num_bytes: 17721 num_examples: 32 - name: test num_bytes: 199634 num_examples: 305 download_size: 138805 dataset_size: 221878 - config_name: philosophy features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 2058 num_examples: 5 - name: validation num_bytes: 19167 num_examples: 34 - name: test num_bytes: 161737 num_examples: 302 download_size: 121059 dataset_size: 182962 - config_name: prehistory features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 3992 num_examples: 5 - name: validation num_bytes: 21214 num_examples: 34 - name: test num_bytes: 181683 num_examples: 314 download_size: 136059 dataset_size: 206889 - config_name: professional_accounting features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 4568 num_examples: 5 - name: validation num_bytes: 29165 num_examples: 30 - name: test num_bytes: 266225 num_examples: 282 download_size: 181436 dataset_size: 299958 - config_name: professional_law features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 9431 num_examples: 4 - name: validation num_bytes: 363635 num_examples: 145 - name: test num_bytes: 3285957 num_examples: 1292 download_size: 1993775 dataset_size: 3659023 - config_name: professional_medicine features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 7060 num_examples: 4 - name: validation num_bytes: 47479 num_examples: 30 - name: test num_bytes: 446995 num_examples: 265 download_size: 311538 dataset_size: 501534 - config_name: professional_psychology features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 4597 num_examples: 5 - name: validation num_bytes: 60499 num_examples: 68 - name: test num_bytes: 471519 num_examples: 604 download_size: 325283 dataset_size: 536615 - config_name: public_relations features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 3165 num_examples: 5 - name: validation num_bytes: 9669 num_examples: 12 - name: test num_bytes: 60281 num_examples: 109 download_size: 61213 dataset_size: 73115 - config_name: security_studies features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 11199 num_examples: 5 - name: validation num_bytes: 47992 num_examples: 27 - name: test num_bytes: 427743 num_examples: 240 download_size: 282999 dataset_size: 486934 - config_name: sociology features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 3456 num_examples: 5 - name: validation num_bytes: 14660 num_examples: 21 - name: test num_bytes: 138231 num_examples: 196 download_size: 111807 dataset_size: 156347 - config_name: us_foreign_policy features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 3440 num_examples: 5 - name: validation num_bytes: 6883 num_examples: 11 - name: test num_bytes: 60635 num_examples: 99 download_size: 56816 dataset_size: 70958 - config_name: virology features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 1836 num_examples: 4 - name: validation num_bytes: 10140 num_examples: 17 - name: test num_bytes: 82841 num_examples: 165 download_size: 73952 dataset_size: 94817 - config_name: world_religions features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 1357 num_examples: 5 - name: validation num_bytes: 5669 num_examples: 19 - name: test num_bytes: 51954 num_examples: 171 download_size: 51989 dataset_size: 58980 configs: - config_name: abstract_algebra data_files: - split: dev path: abstract_algebra/dev-* - split: validation path: abstract_algebra/validation-* - split: test path: abstract_algebra/test-* - config_name: anatomy data_files: - split: dev path: anatomy/dev-* - split: validation path: anatomy/validation-* - split: test path: anatomy/test-* - config_name: astronomy data_files: - split: dev path: astronomy/dev-* - split: validation path: astronomy/validation-* - split: test path: astronomy/test-* - config_name: business_ethics data_files: - split: dev path: business_ethics/dev-* - split: validation path: business_ethics/validation-* - split: test path: business_ethics/test-* - config_name: clinical_knowledge data_files: - split: dev path: clinical_knowledge/dev-* - split: validation path: clinical_knowledge/validation-* - split: test path: clinical_knowledge/test-* - config_name: college_biology data_files: - split: dev path: college_biology/dev-* - split: validation path: college_biology/validation-* - split: test path: college_biology/test-* - config_name: college_chemistry data_files: - split: dev path: college_chemistry/dev-* - split: validation path: college_chemistry/validation-* - split: test path: college_chemistry/test-* - config_name: college_computer_science data_files: - split: dev path: college_computer_science/dev-* - split: validation path: college_computer_science/validation-* - split: test path: college_computer_science/test-* - config_name: college_mathematics data_files: - split: dev path: college_mathematics/dev-* - split: validation path: college_mathematics/validation-* - split: test path: college_mathematics/test-* - config_name: college_medicine data_files: - split: dev path: college_medicine/dev-* - split: validation path: college_medicine/validation-* - split: test path: college_medicine/test-* - config_name: college_physics data_files: - split: dev path: college_physics/dev-* - split: validation path: college_physics/validation-* - split: test path: college_physics/test-* - config_name: computer_security data_files: - split: dev path: computer_security/dev-* - split: validation path: computer_security/validation-* - split: test path: computer_security/test-* - config_name: conceptual_physics data_files: - split: dev path: conceptual_physics/dev-* - split: validation path: conceptual_physics/validation-* - split: test path: conceptual_physics/test-* - config_name: econometrics data_files: - split: dev path: econometrics/dev-* - split: validation path: econometrics/validation-* - split: test path: econometrics/test-* - config_name: electrical_engineering data_files: - split: dev path: electrical_engineering/dev-* - split: validation path: electrical_engineering/validation-* - split: test path: electrical_engineering/test-* - config_name: elementary_mathematics data_files: - split: dev path: elementary_mathematics/dev-* - split: validation path: elementary_mathematics/validation-* - split: test path: elementary_mathematics/test-* - config_name: formal_logic data_files: - split: dev path: formal_logic/dev-* - split: validation path: formal_logic/validation-* - split: test path: formal_logic/test-* - config_name: global_facts data_files: - split: dev path: global_facts/dev-* - split: validation path: global_facts/validation-* - split: test path: global_facts/test-* - config_name: high_school_biology data_files: - split: dev path: high_school_biology/dev-* - split: validation path: high_school_biology/validation-* - split: test path: high_school_biology/test-* - config_name: high_school_chemistry data_files: - split: dev path: high_school_chemistry/dev-* - split: validation path: high_school_chemistry/validation-* - split: test path: high_school_chemistry/test-* - config_name: high_school_computer_science data_files: - split: dev path: high_school_computer_science/dev-* - split: validation path: high_school_computer_science/validation-* - split: test path: high_school_computer_science/test-* - config_name: high_school_european_history data_files: - split: dev path: high_school_european_history/dev-* - split: validation path: high_school_european_history/validation-* - split: test path: high_school_european_history/test-* - config_name: high_school_geography data_files: - split: dev path: high_school_geography/dev-* - split: validation path: high_school_geography/validation-* - split: test path: high_school_geography/test-* - config_name: high_school_government_and_politics data_files: - split: dev path: high_school_government_and_politics/dev-* - split: validation path: high_school_government_and_politics/validation-* - split: test path: high_school_government_and_politics/test-* - config_name: high_school_macroeconomics data_files: - split: dev path: high_school_macroeconomics/dev-* - split: validation path: high_school_macroeconomics/validation-* - split: test path: high_school_macroeconomics/test-* - config_name: high_school_mathematics data_files: - split: dev path: high_school_mathematics/dev-* - split: validation path: high_school_mathematics/validation-* - split: test path: high_school_mathematics/test-* - config_name: high_school_microeconomics data_files: - split: dev path: high_school_microeconomics/dev-* - split: validation path: high_school_microeconomics/validation-* - split: test path: high_school_microeconomics/test-* - config_name: high_school_physics data_files: - split: dev path: high_school_physics/dev-* - split: validation path: high_school_physics/validation-* - split: test path: high_school_physics/test-* - config_name: high_school_psychology data_files: - split: dev path: high_school_psychology/dev-* - split: validation path: high_school_psychology/validation-* - split: test path: high_school_psychology/test-* - config_name: high_school_statistics data_files: - split: dev path: high_school_statistics/dev-* - split: validation path: high_school_statistics/validation-* - split: test path: high_school_statistics/test-* - config_name: high_school_us_history data_files: - split: dev path: high_school_us_history/dev-* - split: validation path: high_school_us_history/validation-* - split: test path: high_school_us_history/test-* - config_name: high_school_world_history data_files: - split: dev path: high_school_world_history/dev-* - split: validation path: high_school_world_history/validation-* - split: test path: high_school_world_history/test-* - config_name: human_aging data_files: - split: dev path: human_aging/dev-* - split: validation path: human_aging/validation-* - split: test path: human_aging/test-* - config_name: human_sexuality data_files: - split: dev path: human_sexuality/dev-* - split: validation path: human_sexuality/validation-* - split: test path: human_sexuality/test-* - config_name: international_law data_files: - split: dev path: international_law/dev-* - split: validation path: international_law/validation-* - split: test path: international_law/test-* - config_name: jurisprudence data_files: - split: dev path: jurisprudence/dev-* - split: validation path: jurisprudence/validation-* - split: test path: jurisprudence/test-* - config_name: logical_fallacies data_files: - split: dev path: logical_fallacies/dev-* - split: validation path: logical_fallacies/validation-* - split: test path: logical_fallacies/test-* - config_name: machine_learning data_files: - split: dev path: machine_learning/dev-* - split: validation path: machine_learning/validation-* - split: test path: machine_learning/test-* - config_name: management data_files: - split: dev path: management/dev-* - split: validation path: management/validation-* - split: test path: management/test-* - config_name: marketing data_files: - split: dev path: marketing/dev-* - split: validation path: marketing/validation-* - split: test path: marketing/test-* - config_name: medical_genetics data_files: - split: dev path: medical_genetics/dev-* - split: validation path: medical_genetics/validation-* - split: test path: medical_genetics/test-* - config_name: miscellaneous data_files: - split: dev path: miscellaneous/dev-* - split: validation path: miscellaneous/validation-* - split: test path: miscellaneous/test-* - config_name: moral_disputes data_files: - split: dev path: moral_disputes/dev-* - split: validation path: moral_disputes/validation-* - split: test path: moral_disputes/test-* - config_name: moral_scenarios data_files: - split: dev path: moral_scenarios/dev-* - split: validation path: moral_scenarios/validation-* - split: test path: moral_scenarios/test-* - config_name: nutrition data_files: - split: dev path: nutrition/dev-* - split: validation path: nutrition/validation-* - split: test path: nutrition/test-* - config_name: philosophy data_files: - split: dev path: philosophy/dev-* - split: validation path: philosophy/validation-* - split: test path: philosophy/test-* - config_name: prehistory data_files: - split: dev path: prehistory/dev-* - split: validation path: prehistory/validation-* - split: test path: prehistory/test-* - config_name: professional_accounting data_files: - split: dev path: professional_accounting/dev-* - split: validation path: professional_accounting/validation-* - split: test path: professional_accounting/test-* - config_name: professional_law data_files: - split: dev path: professional_law/dev-* - split: validation path: professional_law/validation-* - split: test path: professional_law/test-* - config_name: professional_medicine data_files: - split: dev path: professional_medicine/dev-* - split: validation path: professional_medicine/validation-* - split: test path: professional_medicine/test-* - config_name: professional_psychology data_files: - split: dev path: professional_psychology/dev-* - split: validation path: professional_psychology/validation-* - split: test path: professional_psychology/test-* - config_name: public_relations data_files: - split: dev path: public_relations/dev-* - split: validation path: public_relations/validation-* - split: test path: public_relations/test-* - config_name: security_studies data_files: - split: dev path: security_studies/dev-* - split: validation path: security_studies/validation-* - split: test path: security_studies/test-* - config_name: sociology data_files: - split: dev path: sociology/dev-* - split: validation path: sociology/validation-* - split: test path: sociology/test-* - config_name: us_foreign_policy data_files: - split: dev path: us_foreign_policy/dev-* - split: validation path: us_foreign_policy/validation-* - split: test path: us_foreign_policy/test-* - config_name: virology data_files: - split: dev path: virology/dev-* - split: validation path: virology/validation-* - split: test path: virology/test-* - config_name: world_religions data_files: - split: dev path: world_religions/dev-* - split: validation path: world_religions/validation-* - split: test path: world_religions/test-* --- # MMLU translated to Spanish This dataset was generated by the Natural Language Processing Group of the University of Oregon, where they used the original MMLU dataset in English and translated it into different languages using ChatGPT. This dataset only contains the Spanish translation, but the following languages are also covered within the original subsets posted by the University of Oregon at http://nlp.uoregon.edu/download/okapi-eval/datasets/. ## Disclaimer All the credits for this dataset go to the original authors of MMLU (licensed as MIT), and to the authors of this translation via ChatGPT (licensed as CC BY NC 4.0, allowing only non-commercial use). ## References * [Measuring Massive Multitask Language Understanding](https://arxiv.org/abs/2009.03300) * [Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback](https://arxiv.org/abs/2307.16039)
openbmb/DCAD-2000	openbmb	"2025-04-04T09:51:21Z"	15,764	4	[ "multilinguality:multilingual", "language:eng", "language:rus", "language:cmn", "language:deu", "language:spa", "language:fra", "language:jpn", "language:ita", "language:por", "language:pol", "language:nld", "language:ind", "language:tur", "language:vie", "language:fas", "language:kor", "language:swe", "language:hun", "language:ell", "language:ukr", "language:tha", "language:aze", "language:arb", "language:slv", "language:cat", "language:fin", "language:hbs", "language:ces", "language:fil", "language:guj", "language:nob", "language:mal", "language:bul", "language:kan", "language:hin", "language:tam", "language:ara", "language:kaz", "language:sqi", "language:pan", "language:est", "language:srp", "language:heb", "language:isl", "language:mlt", "language:mkd", "language:bos", "language:lit", "language:kat", "language:hrv", "language:ben", "language:glg", "language:ceb", "language:ron", "language:msa", "language:hye", "language:tgk", "language:mar", "language:bel", "language:nep", "language:urd", "language:slk", "language:mon", "language:swa", "language:dan", "language:eus", "language:azj", "language:sin", "language:lat", "language:als", "language:tel", "language:afr", "language:ekk", "language:ltz", "language:zsm", "language:som", "language:cym", "language:und", "language:kir", "language:nor", "language:uzb", "language:mya", "language:epo", "language:hau", "language:ary", "language:gle", "language:lvs", "language:nno", "language:ory", "language:amh", "language:tat", "language:khm", "language:arz", "language:pus", "language:lav", "language:war", "language:mlg", "language:uzn", "language:hat", "language:zul", "language:kur", "language:tgl", "language:div", "language:fry", "language:sna", "language:fao", "language:sun", "language:snd", "language:cos", "language:bak", "language:ckb", "language:asm", "language:ast", "language:ibo", "language:mri", "language:ars", "language:anp", "language:khk", "language:lao", "language:ori", "language:yid", "language:hmn", "language:jav", "language:nya", "language:tir", "language:uig", "language:wln", "language:yor", "language:swh", "language:gla", "language:xho", "language:bre", "language:sot", "language:che", "language:nan", "language:bew", "language:glk", "language:smo", "language:orm", "language:zho", "language:haw", "language:pnb", "language:oci", "language:chv", "language:kin", "language:pcm", "language:kaa", "language:lug", "language:pbt", "language:gsw", "language:min", "language:tuk", "language:lim", "language:kmr", "language:roh", "language:vec", "language:san", "language:gmh", "language:nds", "language:sco", "language:azb", "language:tsn", "language:sah", "language:pri", "language:pap", "language:plt", "language:lmo", "language:bod", "language:yue", "language:bar", "language:hif", "language:arg", "language:pms", "language:nrm", "language:vol", "language:aeb", "language:ido", "language:pam", "language:kal", "language:lus", "language:new", "language:sme", "language:nso", "language:lld", "language:ina", "language:scn", "language:hyw", "language:abk", "language:bpy", "language:lin", "language:oss", "language:que", "language:szl", "language:sdh", "language:mww", "language:mhr", "language:rmy", "language:diq", "language:srd", "language:ydd", "language:run", "language:hsb", "language:wol", "language:kiu", "language:ilo", "language:cak", "language:acm", "language:grc", "language:xmf", "language:vls", "language:tso", "language:crh", "language:nav", "language:mwl", "language:grn", "language:mui", "language:mvf", "language:udm", "language:mzn", "language:bcl", "language:ban", "language:afb", "language:cnh", "language:cbk", "language:tyv", "language:ful", "language:zea", "language:frp", "language:frr", "language:pfl", "language:lij", "language:apc", "language:mai", "language:pon", "language:eml", "language:uzs", "language:nde", "language:hil", "language:mam", "language:gom", "language:dag", "language:nap", "language:bjn", "language:hbo", "language:tet", "language:inh", "language:ven", "language:gaz", "language:tpi", "language:ajp", "language:sat", "language:wuu", "language:bam", "language:vep", "language:glv", "language:tzo", "language:bik", "language:acr", "language:twi", "language:myv", "language:ewe", "language:poh", "language:ile", "language:rue", "language:ace", "language:kha", "language:ksh", "language:hui", "language:gor", "language:krc", "language:lfn", "language:tls", "language:fur", "language:gag", "language:chk", "language:hmo", "language:kek", "language:fon", "language:ssw", "language:quh", "language:meu", "language:csb", "language:ksd", "language:ext", "language:rop", "language:aln", "language:kab", "language:shn", "language:tbz", "language:knv", "language:bqc", "language:npi", "language:rug", "language:kom", "language:kpg", "language:kbd", "language:dzo", "language:wal", "language:zlm", "language:mzh", "language:hac", "language:tum", "language:sgs", "language:fij", "language:tuc", "language:jbo", "language:iba", "language:pcd", "language:kjh", "language:ixl", "language:ndo", "language:suz", "language:mfe", "language:bxr", "language:ava", "language:bho", "language:brh", "language:ctd", "language:aym", "language:ady", "language:nbl", "language:hus", "language:gug", "language:bat", "language:hne", "language:srn", "language:ctu", "language:ton", "language:bug", "language:aoj", "language:jam", "language:lez", "language:xav", "language:luo", "language:ltg", "language:bih", "language:mrj", "language:avk", "language:kos", "language:kbp", "language:alt", "language:cfm", "language:goh", "language:lad", "language:cor", "language:quc", "language:kpv", "language:aka", "language:hak", "language:rmn", "language:pls", "language:sag", "language:rcf", "language:gym", "language:kik", "language:pag", "language:arn", "language:ngu", "language:dsb", "language:tca", "language:mni", "language:naq", "language:pdc", "language:mps", "language:olo", "language:fro", "language:fit", "language:cdo", "language:kac", "language:mdf", "language:mad", "language:cab", "language:srm", "language:toj", "language:zai", "language:guc", "language:smn", "language:ote", "language:nch", "language:prs", "language:bis", "language:cuk", "language:bzj", "language:map", "language:djk", "language:ncj", "language:mco", "language:shp", "language:ang", "language:seh", "language:ikk", "language:qvi", "language:yom", "language:top", "language:awa", "language:ike", "language:mau", "language:kum", "language:mos", "language:tly", "language:ayr", "language:tdt", "language:yap", "language:evn", "language:tah", "language:xal", "language:szy", "language:quw", "language:stq", "language:tlh", "language:otq", "language:nov", "language:skr", "language:yua", "language:raw", "language:fiu", "language:enm", "language:bbc", "language:non", "language:ber", "language:kea", "language:bua", "language:kua", "language:zza", "language:csy", "language:mnw", "language:dtp", "language:nah", "language:yao", "language:nog", "language:abt", "language:meo", "language:ame", "language:mbf", "language:chm", "language:kas", "language:crs", "language:tcy", "language:lbe", "language:cni", "language:rom", "language:zom", "language:blk", "language:efi", "language:ada", "language:koi", "language:bbj", "language:trv", "language:ach", "language:mgh", "language:gcr", "language:krl", "language:iso", "language:lki", "language:atj", "language:cmo", "language:chu", "language:gur", "language:iku", "language:sma", "language:lrc", "language:gos", "language:dty", "language:nzi", "language:btx", "language:brx", "language:bts", "language:nyu", "language:ckt", "language:guw", "language:pck", "language:quy", "language:gcf", "language:ksw", "language:nia", "language:bal", "language:nhe", "language:hwc", "language:mup", "language:dyu", "language:ami", "language:tay", "language:gaa", "language:loz", "language:abq", "language:pnt", "language:ium", "language:abs", "language:cmr", "language:shi", "language:tzm", "language:gil", "language:ewo", "language:kon", "language:sms", "language:ape", "language:tzh", "language:bci", "language:acd", "language:tab", "language:fuv", "language:swc", "language:tcz", "language:sgc", "language:aaz", "language:tvl", "language:zha", "language:pib", "language:pli", "language:bru", "language:quz", "language:cha", "language:aeu", "language:nqo", "language:mer", "language:acf", "language:rmc", "language:msi", "language:smj", "language:kng", "language:dhv", "language:doi", "language:zap", "language:hla", "language:cac", "language:pdt", "language:mbt", "language:taq", "language:bgp", "language:tyz", "language:aau", "language:mah", "language:nak", "language:kmb", "language:mjw", "language:fuf", "language:bba", "language:amu", "language:alz", "language:cop", "language:rar", "language:emp", "language:arc", "language:nyn", "language:rut", "language:lub", "language:tzj", "language:fat", "language:lzh", "language:aak", "language:nnb", "language:lhu", "language:bjv", "language:bum", "language:maq", "language:roa", "language:bvr", "language:kcg", "language:tok", "language:yrk", "language:khs", "language:rup", "language:qub", "language:jac", "language:hmr", "language:sid", "language:chr", "language:amp", "language:qug", "language:mas", "language:fkv", "language:bem", "language:cav", "language:her", "language:kwn", "language:ify", "language:gpe", "language:zpa", "language:agu", "language:ppk", "language:tiv", "language:ahk", "language:pis", "language:hns", "language:sus", "language:bon", "language:sja", "language:kri", "language:dik", "language:wrk", "language:got", "language:dar", "language:gui", "language:mak", "language:jiv", "language:kjb", "language:maz", "language:bsn", "language:dov", "language:cok", "language:rwo", "language:mag", "language:hnj", "language:krj", "language:teo", "language:enq", "language:aom", "language:ffm", "language:din", "language:ubu", "language:pwn", "language:gum", "language:sny", "language:twu", "language:med", "language:acn", "language:rme", "language:cbs", "language:abx", "language:ndc", "language:ibb", "language:pih", "language:zty", "language:rad", "language:aby", "language:zne", "language:cui", "language:lua", "language:yby", "language:bno", "language:niu", "language:agd", "language:nij", "language:agg", "language:yre", "language:fip", "language:qve", "language:tsg", "language:skg", "language:adj", "language:mfq", "language:agx", "language:kmg", "language:umb", "language:cnk", "language:nhw", "language:maa", "language:kwy", "language:jra", "language:syr", "language:inb", "language:pau", "language:xsm", "language:vap", "language:alp", "language:des", "language:syl", "language:mkn", "language:gan", "language:qwh", "language:jvn", "language:bib", "language:mpx", "language:bin", "language:klv", "language:xon", "language:jbu", "language:bdh", "language:knj", "language:ptu", "language:mmn", "language:mwq", "language:sop", "language:cgc", "language:dop", "language:mgr", "language:rmo", "language:tbc", "language:kyq", "language:zpu", "language:kkc", "language:acu", "language:ata", "language:mif", "language:tsz", "language:mbi", "language:imo", "language:fuh", "language:zyp", "language:apr", "language:att", "language:bus", "language:kqp", "language:koo", "language:bas", "language:urh", "language:bbr", "language:msy", "language:mdy", "language:nas", "language:lee", "language:mcu", "language:dig", "language:izr", "language:nfr", "language:hto", "language:mzw", "language:qxh", "language:chz", "language:guh", "language:ded", "language:bvz", "language:kkj", "language:gux", "language:ikt", "language:bnp", "language:bgt", "language:quf", "language:dwr", "language:nod", "language:yal", "language:bmr", "language:ljp", "language:xla", "language:zyb", "language:gof", "language:niv", "language:nrf", "language:npy", "language:ura", "language:dob", "language:gfk", "language:gdr", "language:sdc", "language:pjt", "language:spp", "language:irk", "language:cpa", "language:knc", "language:gvl", "language:agr", "language:njo", "language:xrb", "language:kao", "language:zpz", "language:bgr", "language:rnd", "language:ntu", "language:aai", "language:gai", "language:dgi", "language:kez", "language:dad", "language:kmh", "language:aii", "language:ifk", "language:aji", "language:noa", "language:bhl", "language:ztq", "language:gde", "language:dnj", "language:men", "language:miq", "language:isd", "language:lgg", "language:ncx", "language:gub", "language:itv", "language:tac", "language:cce", "language:kwi", "language:nhu", "language:sml", "language:pah", "language:sas", "language:cwt", "language:spy", "language:enb", "language:fai", "language:cas", "language:sue", "language:yss", "language:ozm", "language:bku", "language:biv", "language:akp", "language:dts", "language:kdr", "language:fal", "language:mmo", "language:byr", "language:cbv", "language:cbu", "language:eza", "language:kgp", "language:sda", "language:gbo", "language:mfi", "language:bdd", "language:boj", "language:blh", "language:ibg", "language:agn", "language:vmy", "language:sua", "language:gul", "language:rap", "language:bmh", "language:sxn", "language:dyi", "language:tdx", "language:car", "language:heh", "language:dgc", "language:sgb", "language:bpr", "language:gbi", "language:avu", "language:udu", "language:yli", "language:cjs", "language:gnn", "language:nhi", "language:urk", "language:kpy", "language:qup", "language:qvh", "language:pir", "language:tsc", "language:thk", "language:grt", "language:kqn", "language:hay", "language:mqb", "language:tbg", "language:bss", "language:trn", "language:jae", "language:myy", "language:ipk", "language:bao", "language:qvz", "language:dua", "language:mwv", "language:nct", "language:kyc", "language:tuo", "language:tee", "language:mop", "language:mxt", "language:qvm", "language:gkn", "language:lam", "language:ntr", "language:sbe", "language:dyo", "language:lex", "language:smk", "language:coe", "language:kpe", "language:xbi", "language:atb", "language:tcf", "language:bfo", "language:cbc", "language:swg", "language:cnt", "language:izz", "language:knf", "language:mpp", "language:kki", "language:nho", "language:kbr", "language:bmu", "language:hig", "language:qxr", "language:orv", "language:pma", "language:zpl", "language:kpr", "language:sig", "language:mxp", "language:lef", "language:mlp", "language:soq", "language:cre", "language:aey", "language:qvs", "language:sur", "language:suk", "language:cax", "language:alq", "language:chw", "language:dww", "language:gog", "language:viv", "language:qvw", "language:ted", "language:yuj", "language:ziw", "language:kto", "language:mcq", "language:sim", "language:lue", "language:cya", "language:knk", "language:tpt", "language:taj", "language:blz", "language:mil", "language:kde", "language:kpz", "language:hag", "language:vun", "language:kus", "language:lid", "language:tos", "language:bfd", "language:chd", "language:cle", "language:yon", "language:bgs", "language:lsm", "language:msb", "language:ota", "language:mxq", "language:myw", "language:aso", "language:esu", "language:kdi", "language:bhp", "language:mfz", "language:sgw", "language:xsi", "language:gun", "language:kxc", "language:mux", "language:otw", "language:cjp", "language:nyo", "language:zia", "language:cco", "language:ojb", "language:ktu", "language:cpy", "language:txu", "language:bjr", "language:bud", "language:ken", "language:bzh", "language:ipi", "language:crx", "language:cko", "language:gnd", "language:kix", "language:mmx", "language:esk", "language:kud", "language:toh", "language:byx", "language:mtp", "language:kyz", "language:lmp", "language:tiy", "language:ccp", "language:sbl", "language:tcs", "language:usp", "language:buk", "language:hvn", "language:amm", "language:kzj", "language:gng", "language:ter", "language:kij", "language:ngl", "language:pab", "language:pad", "language:kca", "language:meq", "language:niq", "language:dah", "language:lia", "language:kss", "language:bch", "language:khz", "language:nop", "language:yle", "language:ain", "language:pem", "language:yml", "language:gaw", "language:kze", "language:tby", "language:cso", "language:ifb", "language:rki", "language:aly", "language:kmu", "language:mhl", "language:kmo", "language:mva", "language:opm", "language:rtm", "language:xtn", "language:dgr", "language:ksr", "language:snp", "language:tvk", "language:zpv", "language:hrx", "language:kwj", "language:muh", "language:kak", "language:kpw", "language:akb", "language:ybb", "language:kjs", "language:wuv", "language:laj", "language:ogo", "language:nim", "language:czt", "language:aoz", "language:rro", "language:yuw", "language:heg", "language:mrw", "language:zac", "language:kpf", "language:leu", "language:nwi", "language:awx", "language:gso", "language:keo", "language:tte", "language:ceg", "language:nhy", "language:bhw", "language:gnw", "language:nin", "language:xmv", "language:crm", "language:mxv", "language:ubr", "language:gld", "language:bzi", "language:ann", "language:lac", "language:mej", "language:zpc", "language:dje", "language:caq", "language:guk", "language:wos", "language:msm", "language:zaw", "language:cap", "language:mox", "language:zab", "language:mca", "language:wrs", "language:hae", "language:nss", "language:rav", "language:uvh", "language:dga", "language:ppo", "language:arq", "language:bim", "language:lwg", "language:kms", "language:kne", "language:tkl", "language:caf", "language:zat", "language:aba", "language:chf", "language:lew", "language:npl", "language:uvl", "language:rmq", "language:mek", "language:snc", "language:nsn", "language:amn", "language:abz", "language:cek", "language:ong", "language:txq", "language:bjp", "language:gvf", "language:crk", "language:snf", "language:nhg", "language:kqw", "language:mic", "language:mie", "language:nus", "language:plu", "language:idu", "language:sll", "language:thl", "language:bef", "language:kwd", "language:mqy", "language:caa", "language:aia", "language:wer", "language:agm", "language:mbl", "language:mbs", "language:adh", "language:hub", "language:mav", "language:nab", "language:bqp", "language:guo", "language:auy", "language:big", "language:nii", "language:row", "language:kim", "language:mti", "language:otm", "language:prg", "language:icr", "language:mcp", "language:tbo", "language:chy", "language:oji", "language:kpx", "language:lbb", "language:pao", "language:xuo", "language:zgh", "language:wls", "language:aca", "language:apy", "language:wnc", "language:ssg", "language:eve", "language:mee", "language:yut", "language:kxm", "language:mur", "language:mcd", "language:cto", "language:mqj", "language:usa", "language:emi", "language:liv", "language:guz", "language:tgp", "language:ncl", "language:azg", "language:kck", "language:apb", "language:kbm", "language:sgz", "language:wsk", "language:gbm", "language:csw", "language:ctp", "language:eri", "language:vid", "language:bsq", "language:dak", "language:tif", "language:xsr", "language:mwp", "language:roo", "language:wbp", "language:gdn", "language:tgo", "language:zpm", "language:mih", "language:qvc", "language:tod", "language:abn", "language:cao", "language:kbc", "language:kog", "language:moh", "language:leh", "language:nsu", "language:okv", "language:tih", "language:zos", "language:llg", "language:gmv", "language:kyf", "language:mhx", "language:mvp", "language:naf", "language:ino", "language:dng", "language:mnk", "language:oke", "language:omw", "language:tnk", "language:xtd", "language:agt", "language:cbr", "language:eko", "language:nhk", "language:hot", "language:iou", "language:mpm", "language:myx", "language:ndh", "language:pbb", "language:rng", "language:cri", "language:bvd", "language:kmz", "language:cta", "language:blw", "language:clu", "language:cof", "language:kje", "language:nmf", "language:kbh", "language:qxn", "language:ria", "language:wed", "language:zar", "language:huv", "language:lsi", "language:msk", "language:nbq", "language:ati", "language:lww", "language:yva", "language:amr", "language:lmk", "language:tim", "language:bbb", "language:bzd", "language:djr", "language:kwf", "language:nuy", "language:poi", "language:ptp", "language:atd", "language:bps", "language:lcm", "language:mbh", "language:nuj", "language:ayp", "language:cwe", "language:geb", "language:aoi", "language:mto", "language:cbi", "language:gvn", "language:kqf", "language:rkb", "language:xed", "language:zas", "language:apz", "language:cpb", "language:ese", "language:gdg", "language:iws", "language:apu", "language:cag", "language:kdc", "language:nou", "language:too", "language:xmm", "language:beq", "language:hnn", "language:myk", "language:sby", "language:arl", "language:ncu", "language:rml", "language:gam", "language:kvn", "language:mbc", "language:mfy", "language:urt", "language:luc", "language:mio", "language:snn", "language:tar", "language:tku", "language:upv", "language:kjg", "language:btd", "language:cut", "language:mwn", "language:tue", "language:adz", "language:kyg", "language:rel", "language:tew", "language:ttc", "language:nkf", "language:yrb", "language:fub", "language:nsm", "language:nyf", "language:bkd", "language:cpc", "language:lif", "language:mwc", "language:apw", "language:azz", "language:zpo", "language:faa", "language:ood", "language:toc", "language:wmt", "language:ajg", "language:nko", "language:ssd", "language:sxb", "language:zxx", "language:not", "language:amk", "language:hch", "language:kqc", "language:aui", "language:llb", "language:avt", "language:kaq", "language:tna", "language:zpt", "language:bwd", "language:stn", "language:kgk", "language:mck", "language:bhg", "language:ifu", "language:kkl", "language:zao", "language:huu", "language:sil", "language:trq", "language:tuf", "language:wnu", "language:amf", "language:fan", "language:zdj", "language:bco", "language:kdl", "language:lln", "language:mit", "language:yaq", "language:ake", "language:ige", "language:mna", "language:nhx", "language:njn", "language:wba", "language:zaa", "language:syb", "language:qxo", "language:rgu", "language:wiu", "language:bla", "language:etr", "language:miy", "language:mjc", "language:nif", "language:pov", "language:qxl", "language:sey", "language:bxh", "language:ddg", "language:mks", "language:nki", "language:pot", "language:prf", "language:hra", "language:law", "language:plw", "language:zpi", "language:atg", "language:daf", "language:drg", "language:dru", "language:ngp", "language:boa", "language:cbt", "language:dhm", "language:ikw", "language:kqe", "language:lbj", "language:loq", "language:xsb", "language:yad", "language:kyu", "language:mcb", "language:tks", "language:cnl", "language:far", "language:miz", "language:maj", "language:mgm", "language:mib", "language:mza", "language:nhr", "language:smt", "language:ish", "language:mlu", "language:yka", "language:anv", "language:ign", "language:mir", "language:tav", "language:gyr", "language:klt", "language:apn", "language:wbm", "language:cjk", "language:dln", "language:mcf", "language:twx", "language:ldi", "language:poy", "language:yaa", "language:zae", "language:bdq", "language:con", "language:dnw", "language:gah", "language:lcp", "language:mbj", "language:xog", "language:yan", "language:sdq", "language:sgh", "language:gwi", "language:lbk", "language:ses", "language:ycn", "language:kau", "language:hix", "language:mig", "language:mlh", "language:aer", "language:amx", "language:auc", "language:cly", "language:dsh", "language:gnb", "language:neb", "language:ttt", "language:jic", "language:xtm", "language:tll", "language:apt", "language:kgr", "language:pio", "language:pmf", "language:akh", "language:box", "language:cub", "language:cux", "language:mrq", "language:bsp", "language:for", "language:kny", "language:uri", "language:zsr", "language:pce", "language:cme", "language:cot", "language:kxw", "language:omb", "language:srq", "language:vag", "language:cpu", "language:kmy", "language:ksc", "language:lai", "language:nnp", "language:ruf", "language:spm", "language:tro", "language:ttj", "language:waj", "language:raj", "language:ian", "language:ivb", "language:kmm", "language:kzf", "language:maw", "language:tuv", "language:whk", "language:aph", "language:anm", "language:mny", "language:trp", "language:are", "language:esi", "language:mhi", "language:obo", "language:bwu", "language:lwo", "language:mrg", "language:old", "language:zav", "language:snk", "language:daa", "language:fuq", "language:lud", "language:nlg", "language:sck", "language:tbl", "language:khb", "language:tpu", "language:fue", "language:tmd", "language:whg", "language:blt", "language:gqr", "language:kub", "language:ots", "language:tpp", "language:var", "language:hbb", "language:krr", "language:alj", "language:ebk", "language:goa", "language:hav", "language:kmk", "language:kqo", "language:muy", "language:njb", "language:snw", "language:wib", "language:tkr", "language:ksp", "language:lip", "language:mog", "language:nla", "language:pss", "language:zad", "language:awi", "language:frd", "language:kei", "language:kmd", "language:mim", "language:adi", "language:any", "language:arp", "language:biu", "language:bvc", "language:ghs", "language:ttq", "language:vmk", "language:zpj", "language:crl", "language:dtb", "language:dug", "language:kam", "language:nmo", "language:qva", "language:rhg", "language:taw", "language:tui", "language:uth", "language:wap", "language:zpg", "language:brb", "language:bqj", "language:cjv", "language:cnw", "language:kgf", "language:mfh", "language:mns", "language:nnw", "language:ntp", "language:oto", "language:dks", "language:mpt", "language:nmw", "language:sba", "language:sfw", "language:shu", "language:ury", "language:yrl", "language:xkg", "language:iqw", "language:kpj", "language:nfa", "language:nph", "language:nre", "language:wsg", "language:xsu", "language:nut", "language:bmk", "language:cdf", "language:enl", "language:hop", "language:ife", "language:lnd", "language:mrv", "language:nzm", "language:tem", "language:gwc", "language:udi", "language:ajz", "language:kru", "language:qvo", "language:sld", "language:yup", "language:kwu", "language:tdg", "language:ade", "language:bcw", "language:bgz", "language:cul", "language:fmu", "language:gvc", "language:ktj", "language:lis", "language:mev", "language:msc", "language:mta", "language:nbc", "language:ncq", "language:way", "language:wlv", "language:wlx", "language:jmx", "language:wni", "language:aim", "language:byv", "language:cgg", "language:fud", "language:jmc", "language:ker", "language:kia", "language:lom", "language:tnc", "language:bwx", "language:gjn", "language:guq", "language:lap", "language:mip", "language:mkl", "language:mtg", "language:mzk", "language:njm", "language:nse", "language:pne", "language:pww", "language:zam", "language:zca", "language:the", "language:dis", "language:lgl", "language:mbd", "language:mda", "language:mhy", "language:nst", "language:pkb", "language:pmq", "language:poe", "language:swk", "language:trs", "language:vot", "language:yam", "language:zpq", "language:atq", "language:bav", "language:cho", "language:chq", "language:cjo", "language:due", "language:duo", "language:etu", "language:ifa", "language:kby", "language:khq", "language:kno", "language:lem", "language:mcn", "language:mkz", "language:mnb", "language:myb", "language:niy", "language:pxm", "language:rub", "language:sju", "language:tmc", "language:tpm", "language:wob", "language:nxa", "language:sdk", "language:bhz", "language:bth", "language:crj", "language:eka", "language:khy", "language:led", "language:met", "language:mgo", "language:mus", "language:mzm", "language:naw", "language:sri", "language:tbk", "language:xbr", "language:tnl", "language:tnn", "language:awb", "language:bsc", "language:iri", "language:kpq", "language:ktm", "language:loe", "language:lun", "language:mfg", "language:moa", "language:ndj", "language:otn", "language:sjo", "language:wat", "language:bkm", "language:tuz", "language:ybi", "language:gbr", "language:gej", "language:giz", "language:gna", "language:gwr", "language:kex", "language:kle", "language:knx", "language:ktz", "language:kvj", "language:lob", "language:mhw", "language:mph", "language:pmx", "language:qus", "language:tcc", "language:azn", "language:bra", "language:gal", "language:nlv", "language:stk", "language:yux", "language:dip", "language:ivv", "language:kdj", "language:kff", "language:mnf", "language:moc", "language:mpg", "language:mua", "language:nma", "language:rim", "language:rjs", "language:rnl", "language:ssx", "language:tig", "language:urw", "language:idt", "language:mrn", "language:oki", "language:bbk", "language:bea", "language:bkq", "language:btt", "language:cou", "language:ddn", "language:did", "language:diu", "language:ilb", "language:ksj", "language:lhi", "language:ndi", "language:ngb", "language:njz", "language:nmz", "language:npo", "language:nwb", "language:pbi", "language:sbd", "language:soe", "language:tpw", "language:twb", "language:bfn", "language:boz", "language:lwl", "language:psp", "language:sgd", "language:ymp", "language:bkl", "language:bkv", "language:csk", "language:enx", "language:ess", "language:gud", "language:guu", "language:kdh", "language:krx", "language:kzn", "language:maf", "language:max", "language:mgc", "language:mvn", "language:mwm", "language:nbe", "language:nlc", "language:nxd", "language:pse", "language:sbs", "language:tlb", "language:wwa", "language:yim", "language:bkx", "language:bze", "language:kbq", "language:mry", "language:tkd", "language:ybh", "language:abi", "language:ayo", "language:bex", "language:bom", "language:bov", "language:dhg", "language:jaa", "language:kqs", "language:kqy", "language:ksb", "language:ldn", "language:log", "language:lol", "language:mfk", "language:mtj", "language:ndz", "language:ngc", "language:nio", "language:nri", "language:nuz", "language:pps", "language:shk", "language:tlj", "language:vut", "language:xnn", "language:bcc", "language:cuh", "language:hro", "language:nco", "language:nxl", "language:pex", "language:tnp", "language:vif", "language:aha", "language:avn", "language:bmv", "language:chj", "language:crt", "language:dos", "language:eto", "language:gya", "language:hlt", "language:jun", "language:ktb", "language:lgm", "language:mnx", "language:mor", "language:mug", "language:nng", "language:nnh", "language:nsa", "language:nyk", "language:otd", "language:oym", "language:phm", "language:prq", "language:saj", "language:szb", "language:tap", "language:tnr", "language:tzl", "language:wew", "language:yas", "language:yuz", "language:baw", "language:bwt", "language:bxa", "language:fli", "language:kqr", "language:lan", "language:lgr", "language:lhm", "language:mlk", "language:mve", "language:odk", "language:pea", "language:saq", "language:sea", "language:sps", "language:tio", "language:yin", "language:adl", "language:agw", "language:ald", "language:asg", "language:bnj", "language:bwi", "language:bwq", "language:dbq", "language:dow", "language:fad", "language:hoc", "language:kql", "language:ksf", "language:lea", "language:mse", "language:mzl", "language:nhd", "language:nnl", "language:nwx", "language:pbc", "language:pny", "language:tul", "language:aaa", "language:abc", "language:agq", "language:ags", "language:azo", "language:bag", "language:bax", "language:bce", "language:bfm", "language:bgf", "language:bhs", "language:bkc", "language:bkh", "language:bob", "language:bqm", "language:bri", "language:brv", "language:buo", "language:bya", "language:chp", "language:cim", "language:clo", "language:cuv", "language:dmg", "language:dtr", "language:eee", "language:ekm", "language:enc", "language:gbj", "language:gou", "language:hao", "language:hna", "language:hre", "language:isu", "language:jgo", "language:kbx", "language:kvt", "language:kxp", "language:lfa", "language:lkb", "language:lns", "language:loh", "language:lts", "language:luy", "language:mdr", "language:mfj", "language:mgg", "language:mgq", "language:mle", "language:mlw", "language:mmu", "language:mne", "language:muv", "language:mxu", "language:nge", "language:ngn", "language:njy", "language:nsk", "language:nwe", "language:nza", "language:pcg", "language:pdu", "language:pnz", "language:pwg", "language:qaa", "language:snl", "language:sox", "language:ssn", "language:syw", "language:tbj", "language:tdb", "language:thy", "language:tnt", "language:tom", "language:tpl", "language:tsb", "language:tvs", "language:udg", "language:unr", "language:wbr", "language:wms", "language:wnk", "language:wtk", "language:xmd", "language:xmg", "language:xty", "language:yav", "language:yea", "language:zuh", "license:other", "arxiv:2502.11546", "region:us", "multilingual" ]	null	"2025-03-25T04:55:24Z"	--- license: other pretty_name: dcad-2000 license_name: license license_link: LICENSE configs: - config_name: eng_Latn data_files: - split: train path: eng_Latn/_keep.jsonl - config_name: rus_Cyrl data_files: - split: train path: rus_Cyrl/_keep.jsonl - config_name: cmn_Hani data_files: - split: train path: cmn_Hani/_keep.jsonl - config_name: deu_Latn data_files: - split: train path: deu_Latn/_keep.jsonl - config_name: spa_Latn data_files: - split: train path: spa_Latn/_keep.jsonl - config_name: fra_Latn data_files: - split: train path: fra_Latn/_keep.jsonl - config_name: jpn_Jpan data_files: - split: train path: jpn_Jpan/_keep.jsonl - config_name: ita_Latn data_files: - split: train path: ita_Latn/_keep.jsonl - config_name: por_Latn data_files: - split: train path: por_Latn/_keep.jsonl - config_name: pol_Latn data_files: - split: train path: pol_Latn/_keep.jsonl - config_name: nld_Latn data_files: - split: train path: nld_Latn/_keep.jsonl - config_name: ind_Latn data_files: - split: train path: ind_Latn/_keep.jsonl - config_name: tur_Latn data_files: - split: train path: tur_Latn/_keep.jsonl - config_name: vie_Latn data_files: - split: train path: vie_Latn/_keep.jsonl - config_name: fas_Arab data_files: - split: train path: fas_Arab/_keep.jsonl - config_name: kor_Hang data_files: - split: train path: kor_Hang/_keep.jsonl - config_name: swe_Latn data_files: - split: train path: swe_Latn/_keep.jsonl - config_name: hun_Latn data_files: - split: train path: hun_Latn/_keep.jsonl - config_name: ell_Grek data_files: - split: train path: ell_Grek/_keep.jsonl - config_name: ukr_Cyrl data_files: - split: train path: ukr_Cyrl/_keep.jsonl - config_name: tha_Thai data_files: - split: train path: tha_Thai/_keep.jsonl - config_name: aze_Latn data_files: - split: train path: aze_Latn/_keep.jsonl - config_name: arb_Arab data_files: - split: train path: arb_Arab/_keep.jsonl - config_name: slv_Latn data_files: - split: train path: slv_Latn/_keep.jsonl - config_name: cat_Latn data_files: - split: train path: cat_Latn/_keep.jsonl - config_name: fin_Latn data_files: - split: train path: fin_Latn/_keep.jsonl - config_name: hbs_Latn data_files: - split: train path: hbs_Latn/_keep.jsonl - config_name: ces_Latn data_files: - split: train path: ces_Latn/_keep.jsonl - config_name: fil_Latn data_files: - split: train path: fil_Latn/_keep.jsonl - config_name: guj_Gujr data_files: - split: train path: guj_Gujr/_keep.jsonl - config_name: nob_Latn data_files: - split: train path: nob_Latn/_keep.jsonl - config_name: mal_Mlym data_files: - split: train path: mal_Mlym/_keep.jsonl - config_name: bul_Cyrl data_files: - split: train path: bul_Cyrl/_keep.jsonl - config_name: kan_Knda data_files: - split: train path: kan_Knda/_keep.jsonl - config_name: hin_Deva data_files: - split: train path: hin_Deva/_keep.jsonl - config_name: tam_Taml data_files: - split: train path: tam_Taml/_keep.jsonl - config_name: ara_Arab data_files: - split: train path: ara_Arab/_keep.jsonl - config_name: kaz_Cyrl data_files: - split: train path: kaz_Cyrl/_keep.jsonl - config_name: sqi_Latn data_files: - split: train path: sqi_Latn/_keep.jsonl - config_name: pan_Guru data_files: - split: train path: pan_Guru/_keep.jsonl - config_name: est_Latn data_files: - split: train path: est_Latn/_keep.jsonl - config_name: srp_Cyrl data_files: - split: train path: srp_Cyrl/_keep.jsonl - config_name: heb_Hebr data_files: - split: train path: heb_Hebr/_keep.jsonl - config_name: isl_Latn data_files: - split: train path: isl_Latn/_keep.jsonl - config_name: mlt_Latn data_files: - split: train path: mlt_Latn/_keep.jsonl - config_name: mkd_Cyrl data_files: - split: train path: mkd_Cyrl/_keep.jsonl - config_name: bos_Latn data_files: - split: train path: bos_Latn/_keep.jsonl - config_name: lit_Latn data_files: - split: train path: lit_Latn/_keep.jsonl - config_name: kat_Geor data_files: - split: train path: kat_Geor/_keep.jsonl - config_name: hrv_Latn data_files: - split: train path: hrv_Latn/_keep.jsonl - config_name: ben_Beng data_files: - split: train path: ben_Beng/_keep.jsonl - config_name: glg_Latn data_files: - split: train path: glg_Latn/_keep.jsonl - config_name: ceb_Latn data_files: - split: train path: ceb_Latn/_keep.jsonl - config_name: ron_Latn data_files: - split: train path: ron_Latn/_keep.jsonl - config_name: msa_Latn data_files: - split: train path: msa_Latn/_keep.jsonl - config_name: hye_Armn data_files: - split: train path: hye_Armn/_keep.jsonl - config_name: tgk_Cyrl data_files: - split: train path: tgk_Cyrl/_keep.jsonl - config_name: mar_Deva data_files: - split: train path: mar_Deva/_keep.jsonl - config_name: bel_Cyrl data_files: - split: train path: bel_Cyrl/_keep.jsonl - config_name: nep_Deva data_files: - split: train path: nep_Deva/_keep.jsonl - config_name: urd_Arab data_files: - split: train path: urd_Arab/_keep.jsonl - config_name: slk_Latn data_files: - split: train path: slk_Latn/_keep.jsonl - config_name: mon_Cyrl data_files: - split: train path: mon_Cyrl/_keep.jsonl - config_name: swa_Latn data_files: - split: train path: swa_Latn/_keep.jsonl - config_name: dan_Latn data_files: - split: train path: dan_Latn/_keep.jsonl - config_name: eus_Latn data_files: - split: train path: eus_Latn/_keep.jsonl - config_name: azj_Latn data_files: - split: train path: azj_Latn/_keep.jsonl - config_name: sin_Sinh data_files: - split: train path: sin_Sinh/_keep.jsonl - config_name: lat_Latn data_files: - split: train path: lat_Latn/_keep.jsonl - config_name: als_Latn data_files: - split: train path: als_Latn/_keep.jsonl - config_name: tel_Telu data_files: - split: train path: tel_Telu/_keep.jsonl - config_name: afr_Latn data_files: - split: train path: afr_Latn/_keep.jsonl - config_name: ekk_Latn data_files: - split: train path: ekk_Latn/_keep.jsonl - config_name: ltz_Latn data_files: - split: train path: ltz_Latn/_keep.jsonl - config_name: zsm_Latn data_files: - split: train path: zsm_Latn/_keep.jsonl - config_name: som_Latn data_files: - split: train path: som_Latn/_keep.jsonl - config_name: cym_Latn data_files: - split: train path: cym_Latn/_keep.jsonl - config_name: und_Kana data_files: - split: train path: und_Kana/_keep.jsonl - config_name: kir_Cyrl data_files: - split: train path: kir_Cyrl/_keep.jsonl - config_name: nor_Latn data_files: - split: train path: nor_Latn/_keep.jsonl - config_name: uzb_Latn data_files: - split: train path: uzb_Latn/_keep.jsonl - config_name: mya_Mymr data_files: - split: train path: mya_Mymr/_keep.jsonl - config_name: epo_Latn data_files: - split: train path: epo_Latn/_keep.jsonl - config_name: hau_Latn data_files: - split: train path: hau_Latn/_keep.jsonl - config_name: ary_Arab data_files: - split: train path: ary_Arab/_keep.jsonl - config_name: gle_Latn data_files: - split: train path: gle_Latn/_keep.jsonl - config_name: lvs_Latn data_files: - split: train path: lvs_Latn/_keep.jsonl - config_name: nno_Latn data_files: - split: train path: nno_Latn/_keep.jsonl - config_name: und_Bamu data_files: - split: train path: und_Bamu/_keep.jsonl - config_name: ory_Orya data_files: - split: train path: ory_Orya/_keep.jsonl - config_name: amh_Ethi data_files: - split: train path: amh_Ethi/_keep.jsonl - config_name: tat_Cyrl data_files: - split: train path: tat_Cyrl/_keep.jsonl - config_name: khm_Khmr data_files: - split: train path: khm_Khmr/_keep.jsonl - config_name: und_Copt data_files: - split: train path: und_Copt/_keep.jsonl - config_name: und_Tang data_files: - split: train path: und_Tang/_keep.jsonl - config_name: und_Xsux data_files: - split: train path: und_Xsux/_keep.jsonl - config_name: arz_Arab data_files: - split: train path: arz_Arab/_keep.jsonl - config_name: pus_Arab data_files: - split: train path: pus_Arab/_keep.jsonl - config_name: lav_Latn data_files: - split: train path: lav_Latn/_keep.jsonl - config_name: hbs_Cyrl data_files: - split: train path: hbs_Cyrl/_keep.jsonl - config_name: und_Yiii data_files: - split: train path: und_Yiii/_keep.jsonl - config_name: war_Latn data_files: - split: train path: war_Latn/_keep.jsonl - config_name: multi_Latn data_files: - split: train path: multi_Latn/_keep.jsonl - config_name: und_Hira data_files: - split: train path: und_Hira/_keep.jsonl - config_name: mlg_Latn data_files: - split: train path: mlg_Latn/_keep.jsonl - config_name: uzn_Cyrl data_files: - split: train path: uzn_Cyrl/_keep.jsonl - config_name: hat_Latn data_files: - split: train path: hat_Latn/_keep.jsonl - config_name: zul_Latn data_files: - split: train path: zul_Latn/_keep.jsonl - config_name: kur_Latn data_files: - split: train path: kur_Latn/_keep.jsonl - config_name: tgl_Latn data_files: - split: train path: tgl_Latn/_keep.jsonl - config_name: uzb_Cyrl data_files: - split: train path: uzb_Cyrl/_keep.jsonl - config_name: div_Thaa data_files: - split: train path: div_Thaa/_keep.jsonl - config_name: und_Laoo data_files: - split: train path: und_Laoo/_keep.jsonl - config_name: fry_Latn data_files: - split: train path: fry_Latn/_keep.jsonl - config_name: sna_Latn data_files: - split: train path: sna_Latn/_keep.jsonl - config_name: und_Cyrl data_files: - split: train path: und_Cyrl/_keep.jsonl - config_name: fao_Latn data_files: - split: train path: fao_Latn/_keep.jsonl - config_name: sun_Latn data_files: - split: train path: sun_Latn/_keep.jsonl - config_name: und_Kits data_files: - split: train path: und_Kits/_keep.jsonl - config_name: und_Hluw data_files: - split: train path: und_Hluw/_keep.jsonl - config_name: snd_Arab data_files: - split: train path: snd_Arab/_keep.jsonl - config_name: cos_Latn data_files: - split: train path: cos_Latn/_keep.jsonl - config_name: bak_Cyrl data_files: - split: train path: bak_Cyrl/_keep.jsonl - config_name: ckb_Arab data_files: - split: train path: ckb_Arab/_keep.jsonl - config_name: asm_Beng data_files: - split: train path: asm_Beng/_keep.jsonl - config_name: und_Grek data_files: - split: train path: und_Grek/_keep.jsonl - config_name: jpn_Japn data_files: - split: train path: jpn_Japn/_keep.jsonl - config_name: ast_Latn data_files: - split: train path: ast_Latn/_keep.jsonl - config_name: ibo_Latn data_files: - split: train path: ibo_Latn/_keep.jsonl - config_name: mri_Latn data_files: - split: train path: mri_Latn/_keep.jsonl - config_name: und_Lina data_files: - split: train path: und_Lina/_keep.jsonl - config_name: ars_Arab data_files: - split: train path: ars_Arab/_keep.jsonl - config_name: und_Shrd data_files: - split: train path: und_Shrd/_keep.jsonl - config_name: anp_Deva data_files: - split: train path: anp_Deva/_keep.jsonl - config_name: khk_Cyrl data_files: - split: train path: khk_Cyrl/_keep.jsonl - config_name: und_Samr data_files: - split: train path: und_Samr/_keep.jsonl - config_name: lao_Laoo data_files: - split: train path: lao_Laoo/_keep.jsonl - config_name: ori_Orya data_files: - split: train path: ori_Orya/_keep.jsonl - config_name: und_Cans data_files: - split: train path: und_Cans/_keep.jsonl - config_name: yid_Hebr data_files: - split: train path: yid_Hebr/_keep.jsonl - config_name: hmn_Latn data_files: - split: train path: hmn_Latn/_keep.jsonl - config_name: jav_Latn data_files: - split: train path: jav_Latn/_keep.jsonl - config_name: nya_Latn data_files: - split: train path: nya_Latn/_keep.jsonl - config_name: und_Mend data_files: - split: train path: und_Mend/_keep.jsonl - config_name: und_Adlm data_files: - split: train path: und_Adlm/_keep.jsonl - config_name: und_Egyp data_files: - split: train path: und_Egyp/_keep.jsonl - config_name: tir_Ethi data_files: - split: train path: tir_Ethi/_keep.jsonl - config_name: uig_Arab data_files: - split: train path: uig_Arab/_keep.jsonl - config_name: wln_Latn data_files: - split: train path: wln_Latn/_keep.jsonl - config_name: und_Syrc data_files: - split: train path: und_Syrc/_keep.jsonl - config_name: yor_Latn data_files: - split: train path: yor_Latn/_keep.jsonl - config_name: swh_Latn data_files: - split: train path: swh_Latn/_keep.jsonl - config_name: gla_Latn data_files: - split: train path: gla_Latn/_keep.jsonl - config_name: xho_Latn data_files: - split: train path: xho_Latn/_keep.jsonl - config_name: uzn_Latn data_files: - split: train path: uzn_Latn/_keep.jsonl - config_name: bre_Latn data_files: - split: train path: bre_Latn/_keep.jsonl - config_name: sot_Latn data_files: - split: train path: sot_Latn/_keep.jsonl - config_name: che_Cyrl data_files: - split: train path: che_Cyrl/_keep.jsonl - config_name: nan_Latn data_files: - split: train path: nan_Latn/_keep.jsonl - config_name: tel_Latn data_files: - split: train path: tel_Latn/_keep.jsonl - config_name: bew_Latn data_files: - split: train path: bew_Latn/_keep.jsonl - config_name: glk_Arab data_files: - split: train path: glk_Arab/_keep.jsonl - config_name: smo_Latn data_files: - split: train path: smo_Latn/_keep.jsonl - config_name: orm_Latn data_files: - split: train path: orm_Latn/_keep.jsonl - config_name: zho_Hani data_files: - split: train path: zho_Hani/_keep.jsonl - config_name: haw_Latn data_files: - split: train path: haw_Latn/_keep.jsonl - config_name: pnb_Arab data_files: - split: train path: pnb_Arab/_keep.jsonl - config_name: und_Linb data_files: - split: train path: und_Linb/_keep.jsonl - config_name: oci_Latn data_files: - split: train path: oci_Latn/_keep.jsonl - config_name: chv_Cyrl data_files: - split: train path: chv_Cyrl/_keep.jsonl - config_name: kin_Latn data_files: - split: train path: kin_Latn/_keep.jsonl - config_name: und_Brai data_files: - split: train path: und_Brai/_keep.jsonl - config_name: srp_Latn data_files: - split: train path: srp_Latn/_keep.jsonl - config_name: und_Hung data_files: - split: train path: und_Hung/_keep.jsonl - config_name: und_Sgnw data_files: - split: train path: und_Sgnw/_keep.jsonl - config_name: pcm_Latn data_files: - split: train path: pcm_Latn/_keep.jsonl - config_name: kaa_Cyrl data_files: - split: train path: kaa_Cyrl/_keep.jsonl - config_name: lug_Latn data_files: - split: train path: lug_Latn/_keep.jsonl - config_name: pbt_Arab data_files: - split: train path: pbt_Arab/_keep.jsonl - config_name: aze_Arab data_files: - split: train path: aze_Arab/_keep.jsonl - config_name: gsw_Latn data_files: - split: train path: gsw_Latn/_keep.jsonl - config_name: min_Latn data_files: - split: train path: min_Latn/_keep.jsonl - config_name: tuk_Latn data_files: - split: train path: tuk_Latn/_keep.jsonl - config_name: lim_Latn data_files: - split: train path: lim_Latn/_keep.jsonl - config_name: kmr_Latn data_files: - split: train path: kmr_Latn/_keep.jsonl - config_name: und_Nshu data_files: - split: train path: und_Nshu/_keep.jsonl - config_name: roh_Latn data_files: - split: train path: roh_Latn/_keep.jsonl - config_name: und_Bali data_files: - split: train path: und_Bali/_keep.jsonl - config_name: und_Lana data_files: - split: train path: und_Lana/_keep.jsonl - config_name: vec_Latn data_files: - split: train path: vec_Latn/_keep.jsonl - config_name: san_Deva data_files: - split: train path: san_Deva/_keep.jsonl - config_name: und_Modi data_files: - split: train path: und_Modi/_keep.jsonl - config_name: gmh_Latn data_files: - split: train path: gmh_Latn/_keep.jsonl - config_name: nds_Latn data_files: - split: train path: nds_Latn/_keep.jsonl - config_name: sco_Latn data_files: - split: train path: sco_Latn/_keep.jsonl - config_name: und_Mong data_files: - split: train path: und_Mong/_keep.jsonl - config_name: und_Ethi data_files: - split: train path: und_Ethi/_keep.jsonl - config_name: azb_Arab data_files: - split: train path: azb_Arab/_keep.jsonl - config_name: tsn_Latn data_files: - split: train path: tsn_Latn/_keep.jsonl - config_name: rus_Latn data_files: - split: train path: rus_Latn/_keep.jsonl - config_name: und_Hebr data_files: - split: train path: und_Hebr/_keep.jsonl - config_name: mon_Latn data_files: - split: train path: mon_Latn/_keep.jsonl - config_name: und_Saur data_files: - split: train path: und_Saur/_keep.jsonl - config_name: tgk_Latn data_files: - split: train path: tgk_Latn/_keep.jsonl - config_name: sah_Cyrl data_files: - split: train path: sah_Cyrl/_keep.jsonl - config_name: pri_Latn data_files: - split: train path: pri_Latn/_keep.jsonl - config_name: pap_Latn data_files: - split: train path: pap_Latn/_keep.jsonl - config_name: plt_Latn data_files: - split: train path: plt_Latn/_keep.jsonl - config_name: lmo_Latn data_files: - split: train path: lmo_Latn/_keep.jsonl - config_name: bod_Tibt data_files: - split: train path: bod_Tibt/_keep.jsonl - config_name: und_Vaii data_files: - split: train path: und_Vaii/_keep.jsonl - config_name: yue_Hani data_files: - split: train path: yue_Hani/_keep.jsonl - config_name: und_Dupl data_files: - split: train path: und_Dupl/_keep.jsonl - config_name: und_Glag data_files: - split: train path: und_Glag/_keep.jsonl - config_name: und_Thai data_files: - split: train path: und_Thai/_keep.jsonl - config_name: bar_Latn data_files: - split: train path: bar_Latn/_keep.jsonl - config_name: und_Thaa data_files: - split: train path: und_Thaa/_keep.jsonl - config_name: hif_Latn data_files: - split: train path: hif_Latn/_keep.jsonl - config_name: und_Runr data_files: - split: train path: und_Runr/_keep.jsonl - config_name: arg_Latn data_files: - split: train path: arg_Latn/_keep.jsonl - config_name: pms_Latn data_files: - split: train path: pms_Latn/_keep.jsonl - config_name: kat_Latn data_files: - split: train path: kat_Latn/_keep.jsonl - config_name: nrm_Latn data_files: - split: train path: nrm_Latn/_keep.jsonl - config_name: vol_Latn data_files: - split: train path: vol_Latn/_keep.jsonl - config_name: aeb_Arab data_files: - split: train path: aeb_Arab/_keep.jsonl - config_name: und_Khmr data_files: - split: train path: und_Khmr/_keep.jsonl - config_name: und_Geor data_files: - split: train path: und_Geor/_keep.jsonl - config_name: ido_Latn data_files: - split: train path: ido_Latn/_keep.jsonl - config_name: pam_Latn data_files: - split: train path: pam_Latn/_keep.jsonl - config_name: kal_Latn data_files: - split: train path: kal_Latn/_keep.jsonl - config_name: und_Dsrt data_files: - split: train path: und_Dsrt/_keep.jsonl - config_name: und_Tibt data_files: - split: train path: und_Tibt/_keep.jsonl - config_name: und_Mymr data_files: - split: train path: und_Mymr/_keep.jsonl - config_name: lus_Latn data_files: - split: train path: lus_Latn/_keep.jsonl - config_name: und_Armn data_files: - split: train path: und_Armn/_keep.jsonl - config_name: und_Mroo data_files: - split: train path: und_Mroo/_keep.jsonl - config_name: und_Bopo data_files: - split: train path: und_Bopo/_keep.jsonl - config_name: new_Deva data_files: - split: train path: new_Deva/_keep.jsonl - config_name: sme_Latn data_files: - split: train path: sme_Latn/_keep.jsonl - config_name: und_Khar data_files: - split: train path: und_Khar/_keep.jsonl - config_name: und_Mtei data_files: - split: train path: und_Mtei/_keep.jsonl - config_name: nso_Latn data_files: - split: train path: nso_Latn/_keep.jsonl - config_name: lld_Latn data_files: - split: train path: lld_Latn/_keep.jsonl - config_name: ina_Latn data_files: - split: train path: ina_Latn/_keep.jsonl - config_name: scn_Latn data_files: - split: train path: scn_Latn/_keep.jsonl - config_name: und_Deva data_files: - split: train path: und_Deva/_keep.jsonl - config_name: und_Brah data_files: - split: train path: und_Brah/_keep.jsonl - config_name: und_Bhks data_files: - split: train path: und_Bhks/_keep.jsonl - config_name: hyw_Armn data_files: - split: train path: hyw_Armn/_keep.jsonl - config_name: abk_Cyrl data_files: - split: train path: abk_Cyrl/_keep.jsonl - config_name: bew_Cyrl data_files: - split: train path: bew_Cyrl/_keep.jsonl - config_name: und_Telu data_files: - split: train path: und_Telu/_keep.jsonl - config_name: und_Merc data_files: - split: train path: und_Merc/_keep.jsonl - config_name: bpy_Beng data_files: - split: train path: bpy_Beng/_keep.jsonl - config_name: tgk_Arab data_files: - split: train path: tgk_Arab/_keep.jsonl - config_name: lin_Latn data_files: - split: train path: lin_Latn/_keep.jsonl - config_name: oss_Cyrl data_files: - split: train path: oss_Cyrl/_keep.jsonl - config_name: que_Latn data_files: - split: train path: que_Latn/_keep.jsonl - config_name: szl_Latn data_files: - split: train path: szl_Latn/_keep.jsonl - config_name: sdh_Arab data_files: - split: train path: sdh_Arab/_keep.jsonl - config_name: mww_Latn data_files: - split: train path: mww_Latn/_keep.jsonl - config_name: mhr_Cyrl data_files: - split: train path: mhr_Cyrl/_keep.jsonl - config_name: und_Hmnp data_files: - split: train path: und_Hmnp/_keep.jsonl - config_name: und_Orya data_files: - split: train path: und_Orya/_keep.jsonl - config_name: und_Kali data_files: - split: train path: und_Kali/_keep.jsonl - config_name: rmy_Latn data_files: - split: train path: rmy_Latn/_keep.jsonl - config_name: diq_Latn data_files: - split: train path: diq_Latn/_keep.jsonl - config_name: srd_Latn data_files: - split: train path: srd_Latn/_keep.jsonl - config_name: und_Plrd data_files: - split: train path: und_Plrd/_keep.jsonl - config_name: und_Phag data_files: - split: train path: und_Phag/_keep.jsonl - config_name: ydd_Hebr data_files: - split: train path: ydd_Hebr/_keep.jsonl - config_name: und_Hmng data_files: - split: train path: und_Hmng/_keep.jsonl - config_name: run_Latn data_files: - split: train path: run_Latn/_keep.jsonl - config_name: und_Nkoo data_files: - split: train path: und_Nkoo/_keep.jsonl - config_name: hsb_Latn data_files: - split: train path: hsb_Latn/_keep.jsonl - config_name: und_Lisu data_files: - split: train path: und_Lisu/_keep.jsonl - config_name: wol_Latn data_files: - split: train path: wol_Latn/_keep.jsonl - config_name: und_Gran data_files: - split: train path: und_Gran/_keep.jsonl - config_name: urd_Latn data_files: - split: train path: urd_Latn/_keep.jsonl - config_name: und_Cher data_files: - split: train path: und_Cher/_keep.jsonl - config_name: kiu_Latn data_files: - split: train path: kiu_Latn/_keep.jsonl - config_name: ilo_Latn data_files: - split: train path: ilo_Latn/_keep.jsonl - config_name: und_Taml data_files: - split: train path: und_Taml/_keep.jsonl - config_name: cak_Latn data_files: - split: train path: cak_Latn/_keep.jsonl - config_name: und_Gonm data_files: - split: train path: und_Gonm/_keep.jsonl - config_name: acm_Arab data_files: - split: train path: acm_Arab/_keep.jsonl - config_name: und_Tnsa data_files: - split: train path: und_Tnsa/_keep.jsonl - config_name: und_Cprt data_files: - split: train path: und_Cprt/_keep.jsonl - config_name: grc_Grek data_files: - split: train path: grc_Grek/_keep.jsonl - config_name: xmf_Geor data_files: - split: train path: xmf_Geor/_keep.jsonl - config_name: vls_Latn data_files: - split: train path: vls_Latn/_keep.jsonl - config_name: und_Gujr data_files: - split: train path: und_Gujr/_keep.jsonl - config_name: und_Cari data_files: - split: train path: und_Cari/_keep.jsonl - config_name: tso_Latn data_files: - split: train path: tso_Latn/_keep.jsonl - config_name: crh_Latn data_files: - split: train path: crh_Latn/_keep.jsonl - config_name: nav_Latn data_files: - split: train path: nav_Latn/_keep.jsonl - config_name: mwl_Latn data_files: - split: train path: mwl_Latn/_keep.jsonl - config_name: und_Diak data_files: - split: train path: und_Diak/_keep.jsonl - config_name: tat_Latn data_files: - split: train path: tat_Latn/_keep.jsonl - config_name: grn_Latn data_files: - split: train path: grn_Latn/_keep.jsonl - config_name: mui_Latn data_files: - split: train path: mui_Latn/_keep.jsonl - config_name: hin_Latn data_files: - split: train path: hin_Latn/_keep.jsonl - config_name: mvf_Mong data_files: - split: train path: mvf_Mong/_keep.jsonl - config_name: udm_Cyrl data_files: - split: train path: udm_Cyrl/_keep.jsonl - config_name: mzn_Arab data_files: - split: train path: mzn_Arab/_keep.jsonl - config_name: und_Marc data_files: - split: train path: und_Marc/_keep.jsonl - config_name: und_Talu data_files: - split: train path: und_Talu/_keep.jsonl - config_name: und_Vith data_files: - split: train path: und_Vith/_keep.jsonl - config_name: bcl_Latn data_files: - split: train path: bcl_Latn/_keep.jsonl - config_name: und_Nagm data_files: - split: train path: und_Nagm/_keep.jsonl - config_name: und_Mani data_files: - split: train path: und_Mani/_keep.jsonl - config_name: ban_Latn data_files: - split: train path: ban_Latn/_keep.jsonl - config_name: und_Mlym data_files: - split: train path: und_Mlym/_keep.jsonl - config_name: afb_Arab data_files: - split: train path: afb_Arab/_keep.jsonl - config_name: und_Java data_files: - split: train path: und_Java/_keep.jsonl - config_name: cnh_Latn data_files: - split: train path: cnh_Latn/_keep.jsonl - config_name: und_Ahom data_files: - split: train path: und_Ahom/_keep.jsonl - config_name: cbk_Latn data_files: - split: train path: cbk_Latn/_keep.jsonl - config_name: kaa_Latn data_files: - split: train path: kaa_Latn/_keep.jsonl - config_name: tyv_Cyrl data_files: - split: train path: tyv_Cyrl/_keep.jsonl - config_name: kur_Arab data_files: - split: train path: kur_Arab/_keep.jsonl - config_name: ful_Latn data_files: - split: train path: ful_Latn/_keep.jsonl - config_name: und_Beng data_files: - split: train path: und_Beng/_keep.jsonl - config_name: zea_Latn data_files: - split: train path: zea_Latn/_keep.jsonl - config_name: frp_Latn data_files: - split: train path: frp_Latn/_keep.jsonl - config_name: frr_Latn data_files: - split: train path: frr_Latn/_keep.jsonl - config_name: pfl_Latn data_files: - split: train path: pfl_Latn/_keep.jsonl - config_name: lij_Latn data_files: - split: train path: lij_Latn/_keep.jsonl - config_name: apc_Arab data_files: - split: train path: apc_Arab/_keep.jsonl - config_name: mai_Deva data_files: - split: train path: mai_Deva/_keep.jsonl - config_name: und_Wara data_files: - split: train path: und_Wara/_keep.jsonl - config_name: und_Palm data_files: - split: train path: und_Palm/_keep.jsonl - config_name: pon_Latn data_files: - split: train path: pon_Latn/_keep.jsonl - config_name: bak_Latn data_files: - split: train path: bak_Latn/_keep.jsonl - config_name: eml_Latn data_files: - split: train path: eml_Latn/_keep.jsonl - config_name: uzs_Arab data_files: - split: train path: uzs_Arab/_keep.jsonl - config_name: nde_Latn data_files: - split: train path: nde_Latn/_keep.jsonl - config_name: hil_Latn data_files: - split: train path: hil_Latn/_keep.jsonl - config_name: mam_Latn data_files: - split: train path: mam_Latn/_keep.jsonl - config_name: gom_Latn data_files: - split: train path: gom_Latn/_keep.jsonl - config_name: dag_Latn data_files: - split: train path: dag_Latn/_keep.jsonl - config_name: nap_Latn data_files: - split: train path: nap_Latn/_keep.jsonl - config_name: bjn_Latn data_files: - split: train path: bjn_Latn/_keep.jsonl - config_name: und_Khoj data_files: - split: train path: und_Khoj/_keep.jsonl - config_name: hbo_Hebr data_files: - split: train path: hbo_Hebr/_keep.jsonl - config_name: tet_Latn data_files: - split: train path: tet_Latn/_keep.jsonl - config_name: inh_Cyrl data_files: - split: train path: inh_Cyrl/_keep.jsonl - config_name: ven_Latn data_files: - split: train path: ven_Latn/_keep.jsonl - config_name: gaz_Latn data_files: - split: train path: gaz_Latn/_keep.jsonl - config_name: tpi_Latn data_files: - split: train path: tpi_Latn/_keep.jsonl - config_name: und_Sidd data_files: - split: train path: und_Sidd/_keep.jsonl - config_name: ajp_Arab data_files: - split: train path: ajp_Arab/_keep.jsonl - config_name: sat_Olck data_files: - split: train path: sat_Olck/_keep.jsonl - config_name: wuu_Hani data_files: - split: train path: wuu_Hani/_keep.jsonl - config_name: bam_Latn data_files: - split: train path: bam_Latn/_keep.jsonl - config_name: vep_Latn data_files: - split: train path: vep_Latn/_keep.jsonl - config_name: glv_Latn data_files: - split: train path: glv_Latn/_keep.jsonl - config_name: tzo_Latn data_files: - split: train path: tzo_Latn/_keep.jsonl - config_name: bik_Latn data_files: - split: train path: bik_Latn/_keep.jsonl - config_name: und_Rohg data_files: - split: train path: und_Rohg/_keep.jsonl - config_name: acr_Latn data_files: - split: train path: acr_Latn/_keep.jsonl - config_name: twi_Latn data_files: - split: train path: twi_Latn/_keep.jsonl - config_name: myv_Cyrl data_files: - split: train path: myv_Cyrl/_keep.jsonl - config_name: ewe_Latn data_files: - split: train path: ewe_Latn/_keep.jsonl - config_name: poh_Latn data_files: - split: train path: poh_Latn/_keep.jsonl - config_name: und_Avst data_files: - split: train path: und_Avst/_keep.jsonl - config_name: ile_Latn data_files: - split: train path: ile_Latn/_keep.jsonl - config_name: rue_Cyrl data_files: - split: train path: rue_Cyrl/_keep.jsonl - config_name: und_Ougr data_files: - split: train path: und_Ougr/_keep.jsonl - config_name: und_Wcho data_files: - split: train path: und_Wcho/_keep.jsonl - config_name: ace_Latn data_files: - split: train path: ace_Latn/_keep.jsonl - config_name: kha_Latn data_files: - split: train path: kha_Latn/_keep.jsonl - config_name: und_Yezi data_files: - split: train path: und_Yezi/_keep.jsonl - config_name: und_Ital data_files: - split: train path: und_Ital/_keep.jsonl - config_name: und_Kthi data_files: - split: train path: und_Kthi/_keep.jsonl - config_name: und_Takr data_files: - split: train path: und_Takr/_keep.jsonl - config_name: ksh_Latn data_files: - split: train path: ksh_Latn/_keep.jsonl - config_name: hui_Latn data_files: - split: train path: hui_Latn/_keep.jsonl - config_name: gor_Latn data_files: - split: train path: gor_Latn/_keep.jsonl - config_name: krc_Cyrl data_files: - split: train path: krc_Cyrl/_keep.jsonl - config_name: lfn_Latn data_files: - split: train path: lfn_Latn/_keep.jsonl - config_name: tls_Latn data_files: - split: train path: tls_Latn/_keep.jsonl - config_name: fur_Latn data_files: - split: train path: fur_Latn/_keep.jsonl - config_name: und_Tavt data_files: - split: train path: und_Tavt/_keep.jsonl - config_name: gag_Latn data_files: - split: train path: gag_Latn/_keep.jsonl - config_name: chk_Latn data_files: - split: train path: chk_Latn/_keep.jsonl - config_name: hmo_Latn data_files: - split: train path: hmo_Latn/_keep.jsonl - config_name: kek_Latn data_files: - split: train path: kek_Latn/_keep.jsonl - config_name: fon_Latn data_files: - split: train path: fon_Latn/_keep.jsonl - config_name: ssw_Latn data_files: - split: train path: ssw_Latn/_keep.jsonl - config_name: quh_Latn data_files: - split: train path: quh_Latn/_keep.jsonl - config_name: meu_Latn data_files: - split: train path: meu_Latn/_keep.jsonl - config_name: csb_Latn data_files: - split: train path: csb_Latn/_keep.jsonl - config_name: ksd_Latn data_files: - split: train path: ksd_Latn/_keep.jsonl - config_name: ext_Latn data_files: - split: train path: ext_Latn/_keep.jsonl - config_name: rop_Latn data_files: - split: train path: rop_Latn/_keep.jsonl - config_name: und_Tfng data_files: - split: train path: und_Tfng/_keep.jsonl - config_name: aln_Latn data_files: - split: train path: aln_Latn/_keep.jsonl - config_name: kab_Latn data_files: - split: train path: kab_Latn/_keep.jsonl - config_name: shn_Mymr data_files: - split: train path: shn_Mymr/_keep.jsonl - config_name: tbz_Latn data_files: - split: train path: tbz_Latn/_keep.jsonl - config_name: knv_Latn data_files: - split: train path: knv_Latn/_keep.jsonl - config_name: bqc_Latn data_files: - split: train path: bqc_Latn/_keep.jsonl - config_name: und_Elba data_files: - split: train path: und_Elba/_keep.jsonl - config_name: und_Zanb data_files: - split: train path: und_Zanb/_keep.jsonl - config_name: npi_Deva data_files: - split: train path: npi_Deva/_keep.jsonl - config_name: rug_Latn data_files: - split: train path: rug_Latn/_keep.jsonl - config_name: und_Tale data_files: - split: train path: und_Tale/_keep.jsonl - config_name: kom_Cyrl data_files: - split: train path: kom_Cyrl/_keep.jsonl - config_name: kpg_Latn data_files: - split: train path: kpg_Latn/_keep.jsonl - config_name: kbd_Cyrl data_files: - split: train path: kbd_Cyrl/_keep.jsonl - config_name: dzo_Tibt data_files: - split: train path: dzo_Tibt/_keep.jsonl - config_name: wal_Latn data_files: - split: train path: wal_Latn/_keep.jsonl - config_name: zlm_Latn data_files: - split: train path: zlm_Latn/_keep.jsonl - config_name: und_Soyo data_files: - split: train path: und_Soyo/_keep.jsonl - config_name: mzh_Latn data_files: - split: train path: mzh_Latn/_keep.jsonl - config_name: pan_Latn data_files: - split: train path: pan_Latn/_keep.jsonl - config_name: hac_Arab data_files: - split: train path: hac_Arab/_keep.jsonl - config_name: und_Sogo data_files: - split: train path: und_Sogo/_keep.jsonl - config_name: tum_Latn data_files: - split: train path: tum_Latn/_keep.jsonl - config_name: sgs_Latn data_files: - split: train path: sgs_Latn/_keep.jsonl - config_name: fij_Latn data_files: - split: train path: fij_Latn/_keep.jsonl - config_name: tuc_Latn data_files: - split: train path: tuc_Latn/_keep.jsonl - config_name: und_Dogr data_files: - split: train path: und_Dogr/_keep.jsonl - config_name: und_Kawi data_files: - split: train path: und_Kawi/_keep.jsonl - config_name: jbo_Latn data_files: - split: train path: jbo_Latn/_keep.jsonl - config_name: iba_Latn data_files: - split: train path: iba_Latn/_keep.jsonl - config_name: pcd_Latn data_files: - split: train path: pcd_Latn/_keep.jsonl - config_name: kjh_Cyrl data_files: - split: train path: kjh_Cyrl/_keep.jsonl - config_name: ixl_Latn data_files: - split: train path: ixl_Latn/_keep.jsonl - config_name: und_Phli data_files: - split: train path: und_Phli/_keep.jsonl - config_name: und_Cham data_files: - split: train path: und_Cham/_keep.jsonl - config_name: und_Guru data_files: - split: train path: und_Guru/_keep.jsonl - config_name: ndo_Latn data_files: - split: train path: ndo_Latn/_keep.jsonl - config_name: suz_Deva data_files: - split: train path: suz_Deva/_keep.jsonl - config_name: und_Nbat data_files: - split: train path: und_Nbat/_keep.jsonl - config_name: und_Nand data_files: - split: train path: und_Nand/_keep.jsonl - config_name: mfe_Latn data_files: - split: train path: mfe_Latn/_keep.jsonl - config_name: bxr_Cyrl data_files: - split: train path: bxr_Cyrl/_keep.jsonl - config_name: ava_Cyrl data_files: - split: train path: ava_Cyrl/_keep.jsonl - config_name: und_Osma data_files: - split: train path: und_Osma/_keep.jsonl - config_name: bho_Deva data_files: - split: train path: bho_Deva/_keep.jsonl - config_name: brh_Arab data_files: - split: train path: brh_Arab/_keep.jsonl - config_name: und_Sind data_files: - split: train path: und_Sind/_keep.jsonl - config_name: ctd_Latn data_files: - split: train path: ctd_Latn/_keep.jsonl - config_name: aym_Latn data_files: - split: train path: aym_Latn/_keep.jsonl - config_name: ady_Cyrl data_files: - split: train path: ady_Cyrl/_keep.jsonl - config_name: nbl_Latn data_files: - split: train path: nbl_Latn/_keep.jsonl - config_name: gom_Deva data_files: - split: train path: gom_Deva/_keep.jsonl - config_name: hus_Latn data_files: - split: train path: hus_Latn/_keep.jsonl - config_name: gug_Latn data_files: - split: train path: gug_Latn/_keep.jsonl - config_name: und_Pauc data_files: - split: train path: und_Pauc/_keep.jsonl - config_name: und_Sogd data_files: - split: train path: und_Sogd/_keep.jsonl - config_name: bat_Latn data_files: - split: train path: bat_Latn/_keep.jsonl - config_name: guj_Deva data_files: - split: train path: guj_Deva/_keep.jsonl - config_name: hne_Deva data_files: - split: train path: hne_Deva/_keep.jsonl - config_name: srn_Latn data_files: - split: train path: srn_Latn/_keep.jsonl - config_name: ctu_Latn data_files: - split: train path: ctu_Latn/_keep.jsonl - config_name: san_Latn data_files: - split: train path: san_Latn/_keep.jsonl - config_name: ton_Latn data_files: - split: train path: ton_Latn/_keep.jsonl - config_name: bug_Latn data_files: - split: train path: bug_Latn/_keep.jsonl - config_name: aoj_Latn data_files: - split: train path: aoj_Latn/_keep.jsonl - config_name: jam_Latn data_files: - split: train path: jam_Latn/_keep.jsonl - config_name: und_Sylo data_files: - split: train path: und_Sylo/_keep.jsonl - config_name: lez_Cyrl data_files: - split: train path: lez_Cyrl/_keep.jsonl - config_name: xav_Latn data_files: - split: train path: xav_Latn/_keep.jsonl - config_name: luo_Latn data_files: - split: train path: luo_Latn/_keep.jsonl - config_name: ltg_Latn data_files: - split: train path: ltg_Latn/_keep.jsonl - config_name: bih_Deva data_files: - split: train path: bih_Deva/_keep.jsonl - config_name: uig_Cyrl data_files: - split: train path: uig_Cyrl/_keep.jsonl - config_name: mrj_Cyrl data_files: - split: train path: mrj_Cyrl/_keep.jsonl - config_name: avk_Latn data_files: - split: train path: avk_Latn/_keep.jsonl - config_name: kos_Latn data_files: - split: train path: kos_Latn/_keep.jsonl - config_name: kbp_Latn data_files: - split: train path: kbp_Latn/_keep.jsonl - config_name: alt_Cyrl data_files: - split: train path: alt_Cyrl/_keep.jsonl - config_name: cfm_Latn data_files: - split: train path: cfm_Latn/_keep.jsonl - config_name: goh_Latn data_files: - split: train path: goh_Latn/_keep.jsonl - config_name: lad_Latn data_files: - split: train path: lad_Latn/_keep.jsonl - config_name: und_Rjng data_files: - split: train path: und_Rjng/_keep.jsonl - config_name: cor_Latn data_files: - split: train path: cor_Latn/_keep.jsonl - config_name: quc_Latn data_files: - split: train path: quc_Latn/_keep.jsonl - config_name: und_Goth data_files: - split: train path: und_Goth/_keep.jsonl - config_name: kpv_Cyrl data_files: - split: train path: kpv_Cyrl/_keep.jsonl - config_name: und_Chrs data_files: - split: train path: und_Chrs/_keep.jsonl - config_name: aka_Latn data_files: - split: train path: aka_Latn/_keep.jsonl - config_name: und_Phlp data_files: - split: train path: und_Phlp/_keep.jsonl - config_name: hak_Latn data_files: - split: train path: hak_Latn/_keep.jsonl - config_name: rmn_Latn data_files: - split: train path: rmn_Latn/_keep.jsonl - config_name: pls_Latn data_files: - split: train path: pls_Latn/_keep.jsonl - config_name: sag_Latn data_files: - split: train path: sag_Latn/_keep.jsonl - config_name: min_Arab data_files: - split: train path: min_Arab/_keep.jsonl - config_name: und_Tglg data_files: - split: train path: und_Tglg/_keep.jsonl - config_name: rcf_Latn data_files: - split: train path: rcf_Latn/_keep.jsonl - config_name: som_Arab data_files: - split: train path: som_Arab/_keep.jsonl - config_name: gym_Latn data_files: - split: train path: gym_Latn/_keep.jsonl - config_name: und_Mand data_files: - split: train path: und_Mand/_keep.jsonl - config_name: kik_Latn data_files: - split: train path: kik_Latn/_keep.jsonl - config_name: pag_Latn data_files: - split: train path: pag_Latn/_keep.jsonl - config_name: arn_Latn data_files: - split: train path: arn_Latn/_keep.jsonl - config_name: und_Shaw data_files: - split: train path: und_Shaw/_keep.jsonl - config_name: ngu_Latn data_files: - split: train path: ngu_Latn/_keep.jsonl - config_name: dsb_Latn data_files: - split: train path: dsb_Latn/_keep.jsonl - config_name: tca_Latn data_files: - split: train path: tca_Latn/_keep.jsonl - config_name: mni_Mtei data_files: - split: train path: mni_Mtei/_keep.jsonl - config_name: naq_Latn data_files: - split: train path: naq_Latn/_keep.jsonl - config_name: pdc_Latn data_files: - split: train path: pdc_Latn/_keep.jsonl - config_name: mps_Latn data_files: - split: train path: mps_Latn/_keep.jsonl - config_name: und_Hatr data_files: - split: train path: und_Hatr/_keep.jsonl - config_name: olo_Latn data_files: - split: train path: olo_Latn/_keep.jsonl - config_name: fro_Latn data_files: - split: train path: fro_Latn/_keep.jsonl - config_name: fit_Latn data_files: - split: train path: fit_Latn/_keep.jsonl - config_name: crh_Cyrl data_files: - split: train path: crh_Cyrl/_keep.jsonl - config_name: cdo_Latn data_files: - split: train path: cdo_Latn/_keep.jsonl - config_name: kac_Latn data_files: - split: train path: kac_Latn/_keep.jsonl - config_name: mdf_Cyrl data_files: - split: train path: mdf_Cyrl/_keep.jsonl - config_name: mad_Latn data_files: - split: train path: mad_Latn/_keep.jsonl - config_name: cab_Latn data_files: - split: train path: cab_Latn/_keep.jsonl - config_name: srm_Latn data_files: - split: train path: srm_Latn/_keep.jsonl - config_name: toj_Latn data_files: - split: train path: toj_Latn/_keep.jsonl - config_name: zai_Latn data_files: - split: train path: zai_Latn/_keep.jsonl - config_name: guc_Latn data_files: - split: train path: guc_Latn/_keep.jsonl - config_name: smn_Latn data_files: - split: train path: smn_Latn/_keep.jsonl - config_name: ote_Latn data_files: - split: train path: ote_Latn/_keep.jsonl - config_name: nch_Latn data_files: - split: train path: nch_Latn/_keep.jsonl - config_name: und_Bugi data_files: - split: train path: und_Bugi/_keep.jsonl - config_name: prs_Arab data_files: - split: train path: prs_Arab/_keep.jsonl - config_name: tuk_Arab data_files: - split: train path: tuk_Arab/_keep.jsonl - config_name: bis_Latn data_files: - split: train path: bis_Latn/_keep.jsonl - config_name: cuk_Latn data_files: - split: train path: cuk_Latn/_keep.jsonl - config_name: bzj_Latn data_files: - split: train path: bzj_Latn/_keep.jsonl - config_name: map_Latn data_files: - split: train path: map_Latn/_keep.jsonl - config_name: djk_Latn data_files: - split: train path: djk_Latn/_keep.jsonl - config_name: ncj_Latn data_files: - split: train path: ncj_Latn/_keep.jsonl - config_name: und_Olck data_files: - split: train path: und_Olck/_keep.jsonl - config_name: mco_Latn data_files: - split: train path: mco_Latn/_keep.jsonl - config_name: shp_Latn data_files: - split: train path: shp_Latn/_keep.jsonl - config_name: und_Tagb data_files: - split: train path: und_Tagb/_keep.jsonl - config_name: ang_Latn data_files: - split: train path: ang_Latn/_keep.jsonl - config_name: seh_Latn data_files: - split: train path: seh_Latn/_keep.jsonl - config_name: ikk_Latn data_files: - split: train path: ikk_Latn/_keep.jsonl - config_name: qvi_Latn data_files: - split: train path: qvi_Latn/_keep.jsonl - config_name: yom_Latn data_files: - split: train path: yom_Latn/_keep.jsonl - config_name: top_Latn data_files: - split: train path: top_Latn/_keep.jsonl - config_name: awa_Deva data_files: - split: train path: awa_Deva/_keep.jsonl - config_name: ike_Cans data_files: - split: train path: ike_Cans/_keep.jsonl - config_name: mau_Latn data_files: - split: train path: mau_Latn/_keep.jsonl - config_name: kum_Cyrl data_files: - split: train path: kum_Cyrl/_keep.jsonl - config_name: mos_Latn data_files: - split: train path: mos_Latn/_keep.jsonl - config_name: tly_Latn data_files: - split: train path: tly_Latn/_keep.jsonl - config_name: und_Prti data_files: - split: train path: und_Prti/_keep.jsonl - config_name: ayr_Latn data_files: - split: train path: ayr_Latn/_keep.jsonl - config_name: tdt_Latn data_files: - split: train path: tdt_Latn/_keep.jsonl - config_name: yap_Latn data_files: - split: train path: yap_Latn/_keep.jsonl - config_name: evn_Cyrl data_files: - split: train path: evn_Cyrl/_keep.jsonl - config_name: tah_Latn data_files: - split: train path: tah_Latn/_keep.jsonl - config_name: xal_Cyrl data_files: - split: train path: xal_Cyrl/_keep.jsonl - config_name: szy_Latn data_files: - split: train path: szy_Latn/_keep.jsonl - config_name: quw_Latn data_files: - split: train path: quw_Latn/_keep.jsonl - config_name: stq_Latn data_files: - split: train path: stq_Latn/_keep.jsonl - config_name: tlh_Latn data_files: - split: train path: tlh_Latn/_keep.jsonl - config_name: otq_Latn data_files: - split: train path: otq_Latn/_keep.jsonl - config_name: und_Narb data_files: - split: train path: und_Narb/_keep.jsonl - config_name: nov_Latn data_files: - split: train path: nov_Latn/_keep.jsonl - config_name: skr_Arab data_files: - split: train path: skr_Arab/_keep.jsonl - config_name: yua_Latn data_files: - split: train path: yua_Latn/_keep.jsonl - config_name: raw_Latn data_files: - split: train path: raw_Latn/_keep.jsonl - config_name: und_Sarb data_files: - split: train path: und_Sarb/_keep.jsonl - config_name: fiu_Latn data_files: - split: train path: fiu_Latn/_keep.jsonl - config_name: enm_Latn data_files: - split: train path: enm_Latn/_keep.jsonl - config_name: bbc_Latn data_files: - split: train path: bbc_Latn/_keep.jsonl - config_name: und_Lydi data_files: - split: train path: und_Lydi/_keep.jsonl - config_name: non_Latn data_files: - split: train path: non_Latn/_keep.jsonl - config_name: und_Ugar data_files: - split: train path: und_Ugar/_keep.jsonl - config_name: ber_Latn data_files: - split: train path: ber_Latn/_keep.jsonl - config_name: kea_Latn data_files: - split: train path: kea_Latn/_keep.jsonl - config_name: uig_Latn data_files: - split: train path: uig_Latn/_keep.jsonl - config_name: bua_Cyrl data_files: - split: train path: bua_Cyrl/_keep.jsonl - config_name: kua_Latn data_files: - split: train path: kua_Latn/_keep.jsonl - config_name: zza_Latn data_files: - split: train path: zza_Latn/_keep.jsonl - config_name: csy_Latn data_files: - split: train path: csy_Latn/_keep.jsonl - config_name: mnw_Mymr data_files: - split: train path: mnw_Mymr/_keep.jsonl - config_name: dtp_Latn data_files: - split: train path: dtp_Latn/_keep.jsonl - config_name: nah_Latn data_files: - split: train path: nah_Latn/_keep.jsonl - config_name: yao_Latn data_files: - split: train path: yao_Latn/_keep.jsonl - config_name: azj_Cyrl data_files: - split: train path: azj_Cyrl/_keep.jsonl - config_name: hau_Arab data_files: - split: train path: hau_Arab/_keep.jsonl - config_name: nog_Cyrl data_files: - split: train path: nog_Cyrl/_keep.jsonl - config_name: abt_Latn data_files: - split: train path: abt_Latn/_keep.jsonl - config_name: meo_Latn data_files: - split: train path: meo_Latn/_keep.jsonl - config_name: ame_Latn data_files: - split: train path: ame_Latn/_keep.jsonl - config_name: mbf_Latn data_files: - split: train path: mbf_Latn/_keep.jsonl - config_name: chm_Cyrl data_files: - split: train path: chm_Cyrl/_keep.jsonl - config_name: arb_Latn data_files: - split: train path: arb_Latn/_keep.jsonl - config_name: kas_Arab data_files: - split: train path: kas_Arab/_keep.jsonl - config_name: tam_Latn data_files: - split: train path: tam_Latn/_keep.jsonl - config_name: crs_Latn data_files: - split: train path: crs_Latn/_keep.jsonl - config_name: tcy_Knda data_files: - split: train path: tcy_Knda/_keep.jsonl - config_name: lbe_Cyrl data_files: - split: train path: lbe_Cyrl/_keep.jsonl - config_name: cni_Latn data_files: - split: train path: cni_Latn/_keep.jsonl - config_name: ben_Latn data_files: - split: train path: ben_Latn/_keep.jsonl - config_name: rom_Latn data_files: - split: train path: rom_Latn/_keep.jsonl - config_name: zom_Latn data_files: - split: train path: zom_Latn/_keep.jsonl - config_name: blk_Mymr data_files: - split: train path: blk_Mymr/_keep.jsonl - config_name: efi_Latn data_files: - split: train path: efi_Latn/_keep.jsonl - config_name: ada_Latn data_files: - split: train path: ada_Latn/_keep.jsonl - config_name: und_Buhd data_files: - split: train path: und_Buhd/_keep.jsonl - config_name: koi_Cyrl data_files: - split: train path: koi_Cyrl/_keep.jsonl - config_name: und_Perm data_files: - split: train path: und_Perm/_keep.jsonl - config_name: bbj_Latn data_files: - split: train path: bbj_Latn/_keep.jsonl - config_name: trv_Latn data_files: - split: train path: trv_Latn/_keep.jsonl - config_name: ach_Latn data_files: - split: train path: ach_Latn/_keep.jsonl - config_name: mgh_Latn data_files: - split: train path: mgh_Latn/_keep.jsonl - config_name: kas_Latn data_files: - split: train path: kas_Latn/_keep.jsonl - config_name: gcr_Latn data_files: - split: train path: gcr_Latn/_keep.jsonl - config_name: krl_Latn data_files: - split: train path: krl_Latn/_keep.jsonl - config_name: iso_Latn data_files: - split: train path: iso_Latn/_keep.jsonl - config_name: lki_Arab data_files: - split: train path: lki_Arab/_keep.jsonl - config_name: atj_Latn data_files: - split: train path: atj_Latn/_keep.jsonl - config_name: cmo_Latn data_files: - split: train path: cmo_Latn/_keep.jsonl - config_name: chu_Cyrl data_files: - split: train path: chu_Cyrl/_keep.jsonl - config_name: gur_Latn data_files: - split: train path: gur_Latn/_keep.jsonl - config_name: mni_Beng data_files: - split: train path: mni_Beng/_keep.jsonl - config_name: iku_Cans data_files: - split: train path: iku_Cans/_keep.jsonl - config_name: sma_Latn data_files: - split: train path: sma_Latn/_keep.jsonl - config_name: lrc_Arab data_files: - split: train path: lrc_Arab/_keep.jsonl - config_name: gos_Latn data_files: - split: train path: gos_Latn/_keep.jsonl - config_name: dty_Deva data_files: - split: train path: dty_Deva/_keep.jsonl - config_name: nzi_Latn data_files: - split: train path: nzi_Latn/_keep.jsonl - config_name: btx_Latn data_files: - split: train path: btx_Latn/_keep.jsonl - config_name: brx_Deva data_files: - split: train path: brx_Deva/_keep.jsonl - config_name: bts_Latn data_files: - split: train path: bts_Latn/_keep.jsonl - config_name: nyu_Latn data_files: - split: train path: nyu_Latn/_keep.jsonl - config_name: ckt_Latn data_files: - split: train path: ckt_Latn/_keep.jsonl - config_name: guw_Latn data_files: - split: train path: guw_Latn/_keep.jsonl - config_name: pck_Latn data_files: - split: train path: pck_Latn/_keep.jsonl - config_name: quy_Latn data_files: - split: train path: quy_Latn/_keep.jsonl - config_name: gcf_Latn data_files: - split: train path: gcf_Latn/_keep.jsonl - config_name: ksw_Mymr data_files: - split: train path: ksw_Mymr/_keep.jsonl - config_name: nia_Latn data_files: - split: train path: nia_Latn/_keep.jsonl - config_name: bal_Arab data_files: - split: train path: bal_Arab/_keep.jsonl - config_name: nhe_Latn data_files: - split: train path: nhe_Latn/_keep.jsonl - config_name: hwc_Latn data_files: - split: train path: hwc_Latn/_keep.jsonl - config_name: mup_Deva data_files: - split: train path: mup_Deva/_keep.jsonl - config_name: dyu_Latn data_files: - split: train path: dyu_Latn/_keep.jsonl - config_name: ami_Latn data_files: - split: train path: ami_Latn/_keep.jsonl - config_name: tay_Latn data_files: - split: train path: tay_Latn/_keep.jsonl - config_name: gaa_Latn data_files: - split: train path: gaa_Latn/_keep.jsonl - config_name: loz_Latn data_files: - split: train path: loz_Latn/_keep.jsonl - config_name: abq_Cyrl data_files: - split: train path: abq_Cyrl/_keep.jsonl - config_name: pnt_Grek data_files: - split: train path: pnt_Grek/_keep.jsonl - config_name: snd_Latn data_files: - split: train path: snd_Latn/_keep.jsonl - config_name: ium_Latn data_files: - split: train path: ium_Latn/_keep.jsonl - config_name: abs_Latn data_files: - split: train path: abs_Latn/_keep.jsonl - config_name: cmr_Latn data_files: - split: train path: cmr_Latn/_keep.jsonl - config_name: shi_Latn data_files: - split: train path: shi_Latn/_keep.jsonl - config_name: tzm_Tfng data_files: - split: train path: tzm_Tfng/_keep.jsonl - config_name: gil_Latn data_files: - split: train path: gil_Latn/_keep.jsonl - config_name: ewo_Latn data_files: - split: train path: ewo_Latn/_keep.jsonl - config_name: kon_Latn data_files: - split: train path: kon_Latn/_keep.jsonl - config_name: sms_Latn data_files: - split: train path: sms_Latn/_keep.jsonl - config_name: ape_Latn data_files: - split: train path: ape_Latn/_keep.jsonl - config_name: tzh_Latn data_files: - split: train path: tzh_Latn/_keep.jsonl - config_name: bci_Latn data_files: - split: train path: bci_Latn/_keep.jsonl - config_name: acd_Latn data_files: - split: train path: acd_Latn/_keep.jsonl - config_name: tab_Cyrl data_files: - split: train path: tab_Cyrl/_keep.jsonl - config_name: fuv_Latn data_files: - split: train path: fuv_Latn/_keep.jsonl - config_name: swc_Latn data_files: - split: train path: swc_Latn/_keep.jsonl - config_name: tcz_Latn data_files: - split: train path: tcz_Latn/_keep.jsonl - config_name: und_Elym data_files: - split: train path: und_Elym/_keep.jsonl - config_name: sgc_Latn data_files: - split: train path: sgc_Latn/_keep.jsonl - config_name: aaz_Latn data_files: - split: train path: aaz_Latn/_keep.jsonl - config_name: tly_Arab data_files: - split: train path: tly_Arab/_keep.jsonl - config_name: tvl_Latn data_files: - split: train path: tvl_Latn/_keep.jsonl - config_name: zha_Latn data_files: - split: train path: zha_Latn/_keep.jsonl - config_name: pib_Latn data_files: - split: train path: pib_Latn/_keep.jsonl - config_name: pli_Deva data_files: - split: train path: pli_Deva/_keep.jsonl - config_name: bru_Latn data_files: - split: train path: bru_Latn/_keep.jsonl - config_name: quz_Latn data_files: - split: train path: quz_Latn/_keep.jsonl - config_name: cha_Latn data_files: - split: train path: cha_Latn/_keep.jsonl - config_name: aeu_Latn data_files: - split: train path: aeu_Latn/_keep.jsonl - config_name: bjn_Arab data_files: - split: train path: bjn_Arab/_keep.jsonl - config_name: nqo_Nkoo data_files: - split: train path: nqo_Nkoo/_keep.jsonl - config_name: mer_Latn data_files: - split: train path: mer_Latn/_keep.jsonl - config_name: acf_Latn data_files: - split: train path: acf_Latn/_keep.jsonl - config_name: rmc_Latn data_files: - split: train path: rmc_Latn/_keep.jsonl - config_name: msi_Latn data_files: - split: train path: msi_Latn/_keep.jsonl - config_name: smj_Latn data_files: - split: train path: smj_Latn/_keep.jsonl - config_name: kng_Latn data_files: - split: train path: kng_Latn/_keep.jsonl - config_name: dhv_Latn data_files: - split: train path: dhv_Latn/_keep.jsonl - config_name: doi_Deva data_files: - split: train path: doi_Deva/_keep.jsonl - config_name: zap_Latn data_files: - split: train path: zap_Latn/_keep.jsonl - config_name: hla_Latn data_files: - split: train path: hla_Latn/_keep.jsonl - config_name: cac_Latn data_files: - split: train path: cac_Latn/_keep.jsonl - config_name: pdt_Latn data_files: - split: train path: pdt_Latn/_keep.jsonl - config_name: mbt_Latn data_files: - split: train path: mbt_Latn/_keep.jsonl - config_name: taq_Latn data_files: - split: train path: taq_Latn/_keep.jsonl - config_name: bgp_Latn data_files: - split: train path: bgp_Latn/_keep.jsonl - config_name: tyz_Latn data_files: - split: train path: tyz_Latn/_keep.jsonl - config_name: aau_Latn data_files: - split: train path: aau_Latn/_keep.jsonl - config_name: mah_Latn data_files: - split: train path: mah_Latn/_keep.jsonl - config_name: nak_Latn data_files: - split: train path: nak_Latn/_keep.jsonl - config_name: kmb_Latn data_files: - split: train path: kmb_Latn/_keep.jsonl - config_name: mjw_Latn data_files: - split: train path: mjw_Latn/_keep.jsonl - config_name: fuf_Latn data_files: - split: train path: fuf_Latn/_keep.jsonl - config_name: bba_Latn data_files: - split: train path: bba_Latn/_keep.jsonl - config_name: ron_Cyrl data_files: - split: train path: ron_Cyrl/_keep.jsonl - config_name: amu_Latn data_files: - split: train path: amu_Latn/_keep.jsonl - config_name: alz_Latn data_files: - split: train path: alz_Latn/_keep.jsonl - config_name: cop_Copt data_files: - split: train path: cop_Copt/_keep.jsonl - config_name: rar_Latn data_files: - split: train path: rar_Latn/_keep.jsonl - config_name: emp_Latn data_files: - split: train path: emp_Latn/_keep.jsonl - config_name: arc_Syrc data_files: - split: train path: arc_Syrc/_keep.jsonl - config_name: nyn_Latn data_files: - split: train path: nyn_Latn/_keep.jsonl - config_name: rut_Cyrl data_files: - split: train path: rut_Cyrl/_keep.jsonl - config_name: lub_Latn data_files: - split: train path: lub_Latn/_keep.jsonl - config_name: tzj_Latn data_files: - split: train path: tzj_Latn/_keep.jsonl - config_name: fat_Latn data_files: - split: train path: fat_Latn/_keep.jsonl - config_name: lzh_Hani data_files: - split: train path: lzh_Hani/_keep.jsonl - config_name: aak_Latn data_files: - split: train path: aak_Latn/_keep.jsonl - config_name: nnb_Latn data_files: - split: train path: nnb_Latn/_keep.jsonl - config_name: lhu_Latn data_files: - split: train path: lhu_Latn/_keep.jsonl - config_name: bjv_Latn data_files: - split: train path: bjv_Latn/_keep.jsonl - config_name: bum_Latn data_files: - split: train path: bum_Latn/_keep.jsonl - config_name: maq_Latn data_files: - split: train path: maq_Latn/_keep.jsonl - config_name: roa_Latn data_files: - split: train path: roa_Latn/_keep.jsonl - config_name: bvr_Latn data_files: - split: train path: bvr_Latn/_keep.jsonl - config_name: kcg_Latn data_files: - split: train path: kcg_Latn/_keep.jsonl - config_name: tok_Latn data_files: - split: train path: tok_Latn/_keep.jsonl - config_name: yrk_Cyrl data_files: - split: train path: yrk_Cyrl/_keep.jsonl - config_name: khs_Latn data_files: - split: train path: khs_Latn/_keep.jsonl - config_name: rup_Latn data_files: - split: train path: rup_Latn/_keep.jsonl - config_name: tuk_Cyrl data_files: - split: train path: tuk_Cyrl/_keep.jsonl - config_name: qub_Latn data_files: - split: train path: qub_Latn/_keep.jsonl - config_name: jac_Latn data_files: - split: train path: jac_Latn/_keep.jsonl - config_name: hmr_Latn data_files: - split: train path: hmr_Latn/_keep.jsonl - config_name: sid_Latn data_files: - split: train path: sid_Latn/_keep.jsonl - config_name: chr_Cher data_files: - split: train path: chr_Cher/_keep.jsonl - config_name: amp_Latn data_files: - split: train path: amp_Latn/_keep.jsonl - config_name: qug_Latn data_files: - split: train path: qug_Latn/_keep.jsonl - config_name: mas_Latn data_files: - split: train path: mas_Latn/_keep.jsonl - config_name: fkv_Latn data_files: - split: train path: fkv_Latn/_keep.jsonl - config_name: mal_Latn data_files: - split: train path: mal_Latn/_keep.jsonl - config_name: bem_Latn data_files: - split: train path: bem_Latn/_keep.jsonl - config_name: cav_Latn data_files: - split: train path: cav_Latn/_keep.jsonl - config_name: her_Latn data_files: - split: train path: her_Latn/_keep.jsonl - config_name: kwn_Latn data_files: - split: train path: kwn_Latn/_keep.jsonl - config_name: ify_Latn data_files: - split: train path: ify_Latn/_keep.jsonl - config_name: asm_Latn data_files: - split: train path: asm_Latn/_keep.jsonl - config_name: gpe_Latn data_files: - split: train path: gpe_Latn/_keep.jsonl - config_name: zpa_Latn data_files: - split: train path: zpa_Latn/_keep.jsonl - config_name: agu_Latn data_files: - split: train path: agu_Latn/_keep.jsonl - config_name: ppk_Latn data_files: - split: train path: ppk_Latn/_keep.jsonl - config_name: tiv_Latn data_files: - split: train path: tiv_Latn/_keep.jsonl - config_name: npi_Latn data_files: - split: train path: npi_Latn/_keep.jsonl - config_name: ahk_Latn data_files: - split: train path: ahk_Latn/_keep.jsonl - config_name: pis_Latn data_files: - split: train path: pis_Latn/_keep.jsonl - config_name: hns_Latn data_files: - split: train path: hns_Latn/_keep.jsonl - config_name: sus_Latn data_files: - split: train path: sus_Latn/_keep.jsonl - config_name: hak_Hani data_files: - split: train path: hak_Hani/_keep.jsonl - config_name: bon_Latn data_files: - split: train path: bon_Latn/_keep.jsonl - config_name: sja_Latn data_files: - split: train path: sja_Latn/_keep.jsonl - config_name: kas_Deva data_files: - split: train path: kas_Deva/_keep.jsonl - config_name: mar_Latn data_files: - split: train path: mar_Latn/_keep.jsonl - config_name: kri_Latn data_files: - split: train path: kri_Latn/_keep.jsonl - config_name: dik_Latn data_files: - split: train path: dik_Latn/_keep.jsonl - config_name: wrk_Latn data_files: - split: train path: wrk_Latn/_keep.jsonl - config_name: got_Goth data_files: - split: train path: got_Goth/_keep.jsonl - config_name: dar_Cyrl data_files: - split: train path: dar_Cyrl/_keep.jsonl - config_name: gui_Latn data_files: - split: train path: gui_Latn/_keep.jsonl - config_name: mak_Latn data_files: - split: train path: mak_Latn/_keep.jsonl - config_name: jiv_Latn data_files: - split: train path: jiv_Latn/_keep.jsonl - config_name: kjb_Latn data_files: - split: train path: kjb_Latn/_keep.jsonl - config_name: maz_Latn data_files: - split: train path: maz_Latn/_keep.jsonl - config_name: bsn_Latn data_files: - split: train path: bsn_Latn/_keep.jsonl - config_name: dov_Latn data_files: - split: train path: dov_Latn/_keep.jsonl - config_name: cok_Latn data_files: - split: train path: cok_Latn/_keep.jsonl - config_name: rwo_Latn data_files: - split: train path: rwo_Latn/_keep.jsonl - config_name: mag_Deva data_files: - split: train path: mag_Deva/_keep.jsonl - config_name: hnj_Latn data_files: - split: train path: hnj_Latn/_keep.jsonl - config_name: krj_Latn data_files: - split: train path: krj_Latn/_keep.jsonl - config_name: teo_Latn data_files: - split: train path: teo_Latn/_keep.jsonl - config_name: enq_Latn data_files: - split: train path: enq_Latn/_keep.jsonl - config_name: aom_Latn data_files: - split: train path: aom_Latn/_keep.jsonl - config_name: ffm_Latn data_files: - split: train path: ffm_Latn/_keep.jsonl - config_name: din_Latn data_files: - split: train path: din_Latn/_keep.jsonl - config_name: ubu_Latn data_files: - split: train path: ubu_Latn/_keep.jsonl - config_name: pwn_Latn data_files: - split: train path: pwn_Latn/_keep.jsonl - config_name: gum_Latn data_files: - split: train path: gum_Latn/_keep.jsonl - config_name: sny_Latn data_files: - split: train path: sny_Latn/_keep.jsonl - config_name: twu_Latn data_files: - split: train path: twu_Latn/_keep.jsonl - config_name: med_Latn data_files: - split: train path: med_Latn/_keep.jsonl - config_name: acn_Latn data_files: - split: train path: acn_Latn/_keep.jsonl - config_name: rme_Latn data_files: - split: train path: rme_Latn/_keep.jsonl - config_name: cbs_Latn data_files: - split: train path: cbs_Latn/_keep.jsonl - config_name: abx_Latn data_files: - split: train path: abx_Latn/_keep.jsonl - config_name: ndc_Latn data_files: - split: train path: ndc_Latn/_keep.jsonl - config_name: ibb_Latn data_files: - split: train path: ibb_Latn/_keep.jsonl - config_name: pih_Latn data_files: - split: train path: pih_Latn/_keep.jsonl - config_name: zty_Latn data_files: - split: train path: zty_Latn/_keep.jsonl - config_name: rad_Latn data_files: - split: train path: rad_Latn/_keep.jsonl - config_name: aby_Latn data_files: - split: train path: aby_Latn/_keep.jsonl - config_name: zne_Latn data_files: - split: train path: zne_Latn/_keep.jsonl - config_name: cui_Latn data_files: - split: train path: cui_Latn/_keep.jsonl - config_name: lua_Latn data_files: - split: train path: lua_Latn/_keep.jsonl - config_name: yby_Latn data_files: - split: train path: yby_Latn/_keep.jsonl - config_name: bno_Latn data_files: - split: train path: bno_Latn/_keep.jsonl - config_name: niu_Latn data_files: - split: train path: niu_Latn/_keep.jsonl - config_name: agd_Latn data_files: - split: train path: agd_Latn/_keep.jsonl - config_name: nij_Latn data_files: - split: train path: nij_Latn/_keep.jsonl - config_name: agg_Latn data_files: - split: train path: agg_Latn/_keep.jsonl - config_name: yre_Latn data_files: - split: train path: yre_Latn/_keep.jsonl - config_name: fip_Latn data_files: - split: train path: fip_Latn/_keep.jsonl - config_name: qve_Latn data_files: - split: train path: qve_Latn/_keep.jsonl - config_name: tsg_Latn data_files: - split: train path: tsg_Latn/_keep.jsonl - config_name: skg_Latn data_files: - split: train path: skg_Latn/_keep.jsonl - config_name: adj_Latn data_files: - split: train path: adj_Latn/_keep.jsonl - config_name: mfq_Latn data_files: - split: train path: mfq_Latn/_keep.jsonl - config_name: agx_Cyrl data_files: - split: train path: agx_Cyrl/_keep.jsonl - config_name: kmg_Latn data_files: - split: train path: kmg_Latn/_keep.jsonl - config_name: umb_Latn data_files: - split: train path: umb_Latn/_keep.jsonl - config_name: cnk_Latn data_files: - split: train path: cnk_Latn/_keep.jsonl - config_name: nhw_Latn data_files: - split: train path: nhw_Latn/_keep.jsonl - config_name: maa_Latn data_files: - split: train path: maa_Latn/_keep.jsonl - config_name: kwy_Latn data_files: - split: train path: kwy_Latn/_keep.jsonl - config_name: jra_Latn data_files: - split: train path: jra_Latn/_keep.jsonl - config_name: syr_Syrc data_files: - split: train path: syr_Syrc/_keep.jsonl - config_name: inb_Latn data_files: - split: train path: inb_Latn/_keep.jsonl - config_name: pau_Latn data_files: - split: train path: pau_Latn/_keep.jsonl - config_name: xsm_Latn data_files: - split: train path: xsm_Latn/_keep.jsonl - config_name: vap_Latn data_files: - split: train path: vap_Latn/_keep.jsonl - config_name: alp_Latn data_files: - split: train path: alp_Latn/_keep.jsonl - config_name: des_Latn data_files: - split: train path: des_Latn/_keep.jsonl - config_name: syl_Latn data_files: - split: train path: syl_Latn/_keep.jsonl - config_name: kmr_Cyrl data_files: - split: train path: kmr_Cyrl/_keep.jsonl - config_name: mkn_Latn data_files: - split: train path: mkn_Latn/_keep.jsonl - config_name: gan_Hani data_files: - split: train path: gan_Hani/_keep.jsonl - config_name: qwh_Latn data_files: - split: train path: qwh_Latn/_keep.jsonl - config_name: jvn_Latn data_files: - split: train path: jvn_Latn/_keep.jsonl - config_name: bib_Latn data_files: - split: train path: bib_Latn/_keep.jsonl - config_name: ckt_Cyrl data_files: - split: train path: ckt_Cyrl/_keep.jsonl - config_name: mpx_Latn data_files: - split: train path: mpx_Latn/_keep.jsonl - config_name: bin_Latn data_files: - split: train path: bin_Latn/_keep.jsonl - config_name: klv_Latn data_files: - split: train path: klv_Latn/_keep.jsonl - config_name: xon_Latn data_files: - split: train path: xon_Latn/_keep.jsonl - config_name: jbu_Latn data_files: - split: train path: jbu_Latn/_keep.jsonl - config_name: bdh_Latn data_files: - split: train path: bdh_Latn/_keep.jsonl - config_name: knj_Latn data_files: - split: train path: knj_Latn/_keep.jsonl - config_name: ptu_Latn data_files: - split: train path: ptu_Latn/_keep.jsonl - config_name: mmn_Latn data_files: - split: train path: mmn_Latn/_keep.jsonl - config_name: mwq_Latn data_files: - split: train path: mwq_Latn/_keep.jsonl - config_name: sop_Latn data_files: - split: train path: sop_Latn/_keep.jsonl - config_name: cgc_Latn data_files: - split: train path: cgc_Latn/_keep.jsonl - config_name: rmy_Cyrl data_files: - split: train path: rmy_Cyrl/_keep.jsonl - config_name: dop_Latn data_files: - split: train path: dop_Latn/_keep.jsonl - config_name: mgr_Latn data_files: - split: train path: mgr_Latn/_keep.jsonl - config_name: rmo_Latn data_files: - split: train path: rmo_Latn/_keep.jsonl - config_name: tbc_Latn data_files: - split: train path: tbc_Latn/_keep.jsonl - config_name: kyq_Latn data_files: - split: train path: kyq_Latn/_keep.jsonl - config_name: zpu_Latn data_files: - split: train path: zpu_Latn/_keep.jsonl - config_name: kkc_Latn data_files: - split: train path: kkc_Latn/_keep.jsonl - config_name: acu_Latn data_files: - split: train path: acu_Latn/_keep.jsonl - config_name: ata_Latn data_files: - split: train path: ata_Latn/_keep.jsonl - config_name: gag_Cyrl data_files: - split: train path: gag_Cyrl/_keep.jsonl - config_name: kan_Latn data_files: - split: train path: kan_Latn/_keep.jsonl - config_name: mif_Latn data_files: - split: train path: mif_Latn/_keep.jsonl - config_name: sus_Arab data_files: - split: train path: sus_Arab/_keep.jsonl - config_name: tsz_Latn data_files: - split: train path: tsz_Latn/_keep.jsonl - config_name: mbi_Latn data_files: - split: train path: mbi_Latn/_keep.jsonl - config_name: imo_Latn data_files: - split: train path: imo_Latn/_keep.jsonl - config_name: fuh_Latn data_files: - split: train path: fuh_Latn/_keep.jsonl - config_name: zyp_Latn data_files: - split: train path: zyp_Latn/_keep.jsonl - config_name: apr_Latn data_files: - split: train path: apr_Latn/_keep.jsonl - config_name: att_Latn data_files: - split: train path: att_Latn/_keep.jsonl - config_name: bus_Latn data_files: - split: train path: bus_Latn/_keep.jsonl - config_name: kqp_Latn data_files: - split: train path: kqp_Latn/_keep.jsonl - config_name: koo_Latn data_files: - split: train path: koo_Latn/_keep.jsonl - config_name: bas_Latn data_files: - split: train path: bas_Latn/_keep.jsonl - config_name: urh_Latn data_files: - split: train path: urh_Latn/_keep.jsonl - config_name: bbr_Latn data_files: - split: train path: bbr_Latn/_keep.jsonl - config_name: msy_Latn data_files: - split: train path: msy_Latn/_keep.jsonl - config_name: mdy_Ethi data_files: - split: train path: mdy_Ethi/_keep.jsonl - config_name: nas_Latn data_files: - split: train path: nas_Latn/_keep.jsonl - config_name: lee_Latn data_files: - split: train path: lee_Latn/_keep.jsonl - config_name: mcu_Latn data_files: - split: train path: mcu_Latn/_keep.jsonl - config_name: mrj_Latn data_files: - split: train path: mrj_Latn/_keep.jsonl - config_name: dig_Latn data_files: - split: train path: dig_Latn/_keep.jsonl - config_name: izr_Latn data_files: - split: train path: izr_Latn/_keep.jsonl - config_name: nfr_Latn data_files: - split: train path: nfr_Latn/_keep.jsonl - config_name: hto_Latn data_files: - split: train path: hto_Latn/_keep.jsonl - config_name: mzw_Latn data_files: - split: train path: mzw_Latn/_keep.jsonl - config_name: qxh_Latn data_files: - split: train path: qxh_Latn/_keep.jsonl - config_name: chz_Latn data_files: - split: train path: chz_Latn/_keep.jsonl - config_name: guh_Latn data_files: - split: train path: guh_Latn/_keep.jsonl - config_name: ded_Latn data_files: - split: train path: ded_Latn/_keep.jsonl - config_name: bvz_Latn data_files: - split: train path: bvz_Latn/_keep.jsonl - config_name: kkj_Latn data_files: - split: train path: kkj_Latn/_keep.jsonl - config_name: gux_Latn data_files: - split: train path: gux_Latn/_keep.jsonl - config_name: ikt_Latn data_files: - split: train path: ikt_Latn/_keep.jsonl - config_name: bnp_Latn data_files: - split: train path: bnp_Latn/_keep.jsonl - config_name: bgt_Latn data_files: - split: train path: bgt_Latn/_keep.jsonl - config_name: quf_Latn data_files: - split: train path: quf_Latn/_keep.jsonl - config_name: dwr_Latn data_files: - split: train path: dwr_Latn/_keep.jsonl - config_name: nod_Thai data_files: - split: train path: nod_Thai/_keep.jsonl - config_name: yal_Latn data_files: - split: train path: yal_Latn/_keep.jsonl - config_name: bmr_Latn data_files: - split: train path: bmr_Latn/_keep.jsonl - config_name: ljp_Latn data_files: - split: train path: ljp_Latn/_keep.jsonl - config_name: xla_Latn data_files: - split: train path: xla_Latn/_keep.jsonl - config_name: zyb_Latn data_files: - split: train path: zyb_Latn/_keep.jsonl - config_name: gof_Latn data_files: - split: train path: gof_Latn/_keep.jsonl - config_name: niv_Cyrl data_files: - split: train path: niv_Cyrl/_keep.jsonl - config_name: nrf_Latn data_files: - split: train path: nrf_Latn/_keep.jsonl - config_name: npy_Latn data_files: - split: train path: npy_Latn/_keep.jsonl - config_name: ura_Latn data_files: - split: train path: ura_Latn/_keep.jsonl - config_name: dob_Latn data_files: - split: train path: dob_Latn/_keep.jsonl - config_name: gfk_Latn data_files: - split: train path: gfk_Latn/_keep.jsonl - config_name: gdr_Latn data_files: - split: train path: gdr_Latn/_keep.jsonl - config_name: sdc_Latn data_files: - split: train path: sdc_Latn/_keep.jsonl - config_name: pjt_Latn data_files: - split: train path: pjt_Latn/_keep.jsonl - config_name: spp_Latn data_files: - split: train path: spp_Latn/_keep.jsonl - config_name: irk_Latn data_files: - split: train path: irk_Latn/_keep.jsonl - config_name: cpa_Latn data_files: - split: train path: cpa_Latn/_keep.jsonl - config_name: knc_Latn data_files: - split: train path: knc_Latn/_keep.jsonl - config_name: gvl_Latn data_files: - split: train path: gvl_Latn/_keep.jsonl - config_name: agr_Latn data_files: - split: train path: agr_Latn/_keep.jsonl - config_name: njo_Latn data_files: - split: train path: njo_Latn/_keep.jsonl - config_name: xrb_Latn data_files: - split: train path: xrb_Latn/_keep.jsonl - config_name: kao_Latn data_files: - split: train path: kao_Latn/_keep.jsonl - config_name: zpz_Latn data_files: - split: train path: zpz_Latn/_keep.jsonl - config_name: bgr_Latn data_files: - split: train path: bgr_Latn/_keep.jsonl - config_name: rnd_Latn data_files: - split: train path: rnd_Latn/_keep.jsonl - config_name: ntu_Latn data_files: - split: train path: ntu_Latn/_keep.jsonl - config_name: aai_Latn data_files: - split: train path: aai_Latn/_keep.jsonl - config_name: gai_Latn data_files: - split: train path: gai_Latn/_keep.jsonl - config_name: dgi_Latn data_files: - split: train path: dgi_Latn/_keep.jsonl - config_name: kez_Latn data_files: - split: train path: kez_Latn/_keep.jsonl - config_name: dad_Latn data_files: - split: train path: dad_Latn/_keep.jsonl - config_name: kmh_Latn data_files: - split: train path: kmh_Latn/_keep.jsonl - config_name: aii_Syrc data_files: - split: train path: aii_Syrc/_keep.jsonl - config_name: ifk_Latn data_files: - split: train path: ifk_Latn/_keep.jsonl - config_name: aji_Latn data_files: - split: train path: aji_Latn/_keep.jsonl - config_name: noa_Latn data_files: - split: train path: noa_Latn/_keep.jsonl - config_name: bhl_Latn data_files: - split: train path: bhl_Latn/_keep.jsonl - config_name: ztq_Latn data_files: - split: train path: ztq_Latn/_keep.jsonl - config_name: rmn_Cyrl data_files: - split: train path: rmn_Cyrl/_keep.jsonl - config_name: gde_Latn data_files: - split: train path: gde_Latn/_keep.jsonl - config_name: dnj_Latn data_files: - split: train path: dnj_Latn/_keep.jsonl - config_name: men_Latn data_files: - split: train path: men_Latn/_keep.jsonl - config_name: miq_Latn data_files: - split: train path: miq_Latn/_keep.jsonl - config_name: mdf_Latn data_files: - split: train path: mdf_Latn/_keep.jsonl - config_name: isd_Latn data_files: - split: train path: isd_Latn/_keep.jsonl - config_name: lgg_Latn data_files: - split: train path: lgg_Latn/_keep.jsonl - config_name: ncx_Latn data_files: - split: train path: ncx_Latn/_keep.jsonl - config_name: gub_Latn data_files: - split: train path: gub_Latn/_keep.jsonl - config_name: itv_Latn data_files: - split: train path: itv_Latn/_keep.jsonl - config_name: tac_Latn data_files: - split: train path: tac_Latn/_keep.jsonl - config_name: cce_Latn data_files: - split: train path: cce_Latn/_keep.jsonl - config_name: kwi_Latn data_files: - split: train path: kwi_Latn/_keep.jsonl - config_name: nhu_Latn data_files: - split: train path: nhu_Latn/_keep.jsonl - config_name: snd_Deva data_files: - split: train path: snd_Deva/_keep.jsonl - config_name: sml_Latn data_files: - split: train path: sml_Latn/_keep.jsonl - config_name: pah_Latn data_files: - split: train path: pah_Latn/_keep.jsonl - config_name: sas_Latn data_files: - split: train path: sas_Latn/_keep.jsonl - config_name: cwt_Latn data_files: - split: train path: cwt_Latn/_keep.jsonl - config_name: spy_Latn data_files: - split: train path: spy_Latn/_keep.jsonl - config_name: enb_Latn data_files: - split: train path: enb_Latn/_keep.jsonl - config_name: fai_Latn data_files: - split: train path: fai_Latn/_keep.jsonl - config_name: cas_Latn data_files: - split: train path: cas_Latn/_keep.jsonl - config_name: sue_Latn data_files: - split: train path: sue_Latn/_keep.jsonl - config_name: yss_Latn data_files: - split: train path: yss_Latn/_keep.jsonl - config_name: ozm_Latn data_files: - split: train path: ozm_Latn/_keep.jsonl - config_name: bku_Latn data_files: - split: train path: bku_Latn/_keep.jsonl - config_name: biv_Latn data_files: - split: train path: biv_Latn/_keep.jsonl - config_name: akp_Latn data_files: - split: train path: akp_Latn/_keep.jsonl - config_name: dts_Latn data_files: - split: train path: dts_Latn/_keep.jsonl - config_name: kdr_Latn data_files: - split: train path: kdr_Latn/_keep.jsonl - config_name: fal_Latn data_files: - split: train path: fal_Latn/_keep.jsonl - config_name: mmo_Latn data_files: - split: train path: mmo_Latn/_keep.jsonl - config_name: byr_Latn data_files: - split: train path: byr_Latn/_keep.jsonl - config_name: cbv_Latn data_files: - split: train path: cbv_Latn/_keep.jsonl - config_name: cbu_Latn data_files: - split: train path: cbu_Latn/_keep.jsonl - config_name: eza_Latn data_files: - split: train path: eza_Latn/_keep.jsonl - config_name: kgp_Latn data_files: - split: train path: kgp_Latn/_keep.jsonl - config_name: sda_Latn data_files: - split: train path: sda_Latn/_keep.jsonl - config_name: gbo_Latn data_files: - split: train path: gbo_Latn/_keep.jsonl - config_name: mfi_Latn data_files: - split: train path: mfi_Latn/_keep.jsonl - config_name: bdd_Latn data_files: - split: train path: bdd_Latn/_keep.jsonl - config_name: boj_Latn data_files: - split: train path: boj_Latn/_keep.jsonl - config_name: blh_Latn data_files: - split: train path: blh_Latn/_keep.jsonl - config_name: ibg_Latn data_files: - split: train path: ibg_Latn/_keep.jsonl - config_name: agn_Latn data_files: - split: train path: agn_Latn/_keep.jsonl - config_name: vmy_Latn data_files: - split: train path: vmy_Latn/_keep.jsonl - config_name: sua_Latn data_files: - split: train path: sua_Latn/_keep.jsonl - config_name: gul_Latn data_files: - split: train path: gul_Latn/_keep.jsonl - config_name: rap_Latn data_files: - split: train path: rap_Latn/_keep.jsonl - config_name: bmh_Latn data_files: - split: train path: bmh_Latn/_keep.jsonl - config_name: sxn_Latn data_files: - split: train path: sxn_Latn/_keep.jsonl - config_name: dyi_Latn data_files: - split: train path: dyi_Latn/_keep.jsonl - config_name: tdx_Latn data_files: - split: train path: tdx_Latn/_keep.jsonl - config_name: car_Latn data_files: - split: train path: car_Latn/_keep.jsonl - config_name: heh_Latn data_files: - split: train path: heh_Latn/_keep.jsonl - config_name: dgc_Latn data_files: - split: train path: dgc_Latn/_keep.jsonl - config_name: sgb_Latn data_files: - split: train path: sgb_Latn/_keep.jsonl - config_name: bpr_Latn data_files: - split: train path: bpr_Latn/_keep.jsonl - config_name: gbi_Latn data_files: - split: train path: gbi_Latn/_keep.jsonl - config_name: avu_Latn data_files: - split: train path: avu_Latn/_keep.jsonl - config_name: udu_Latn data_files: - split: train path: udu_Latn/_keep.jsonl - config_name: yli_Latn data_files: - split: train path: yli_Latn/_keep.jsonl - config_name: cjs_Cyrl data_files: - split: train path: cjs_Cyrl/_keep.jsonl - config_name: gnn_Latn data_files: - split: train path: gnn_Latn/_keep.jsonl - config_name: nhi_Latn data_files: - split: train path: nhi_Latn/_keep.jsonl - config_name: urk_Thai data_files: - split: train path: urk_Thai/_keep.jsonl - config_name: kpy_Cyrl data_files: - split: train path: kpy_Cyrl/_keep.jsonl - config_name: qup_Latn data_files: - split: train path: qup_Latn/_keep.jsonl - config_name: qvh_Latn data_files: - split: train path: qvh_Latn/_keep.jsonl - config_name: pir_Latn data_files: - split: train path: pir_Latn/_keep.jsonl - config_name: tsc_Latn data_files: - split: train path: tsc_Latn/_keep.jsonl - config_name: bxr_Latn data_files: - split: train path: bxr_Latn/_keep.jsonl - config_name: thk_Latn data_files: - split: train path: thk_Latn/_keep.jsonl - config_name: grt_Beng data_files: - split: train path: grt_Beng/_keep.jsonl - config_name: kqn_Latn data_files: - split: train path: kqn_Latn/_keep.jsonl - config_name: hay_Latn data_files: - split: train path: hay_Latn/_keep.jsonl - config_name: mqb_Latn data_files: - split: train path: mqb_Latn/_keep.jsonl - config_name: tbg_Latn data_files: - split: train path: tbg_Latn/_keep.jsonl - config_name: bss_Latn data_files: - split: train path: bss_Latn/_keep.jsonl - config_name: trn_Latn data_files: - split: train path: trn_Latn/_keep.jsonl - config_name: jae_Latn data_files: - split: train path: jae_Latn/_keep.jsonl - config_name: myy_Latn data_files: - split: train path: myy_Latn/_keep.jsonl - config_name: ipk_Latn data_files: - split: train path: ipk_Latn/_keep.jsonl - config_name: bao_Latn data_files: - split: train path: bao_Latn/_keep.jsonl - config_name: qvz_Latn data_files: - split: train path: qvz_Latn/_keep.jsonl - config_name: dua_Latn data_files: - split: train path: dua_Latn/_keep.jsonl - config_name: mwv_Latn data_files: - split: train path: mwv_Latn/_keep.jsonl - config_name: nct_Latn data_files: - split: train path: nct_Latn/_keep.jsonl - config_name: kyc_Latn data_files: - split: train path: kyc_Latn/_keep.jsonl - config_name: tuo_Latn data_files: - split: train path: tuo_Latn/_keep.jsonl - config_name: tee_Latn data_files: - split: train path: tee_Latn/_keep.jsonl - config_name: mop_Latn data_files: - split: train path: mop_Latn/_keep.jsonl - config_name: mxt_Latn data_files: - split: train path: mxt_Latn/_keep.jsonl - config_name: qvm_Latn data_files: - split: train path: qvm_Latn/_keep.jsonl - config_name: gkn_Latn data_files: - split: train path: gkn_Latn/_keep.jsonl - config_name: lam_Latn data_files: - split: train path: lam_Latn/_keep.jsonl - config_name: ntr_Latn data_files: - split: train path: ntr_Latn/_keep.jsonl - config_name: sbe_Latn data_files: - split: train path: sbe_Latn/_keep.jsonl - config_name: dyo_Latn data_files: - split: train path: dyo_Latn/_keep.jsonl - config_name: lex_Latn data_files: - split: train path: lex_Latn/_keep.jsonl - config_name: smk_Latn data_files: - split: train path: smk_Latn/_keep.jsonl - config_name: coe_Latn data_files: - split: train path: coe_Latn/_keep.jsonl - config_name: kpe_Latn data_files: - split: train path: kpe_Latn/_keep.jsonl - config_name: mni_Latn data_files: - split: train path: mni_Latn/_keep.jsonl - config_name: xbi_Latn data_files: - split: train path: xbi_Latn/_keep.jsonl - config_name: atb_Latn data_files: - split: train path: atb_Latn/_keep.jsonl - config_name: tcf_Latn data_files: - split: train path: tcf_Latn/_keep.jsonl - config_name: bfo_Latn data_files: - split: train path: bfo_Latn/_keep.jsonl - config_name: cbc_Latn data_files: - split: train path: cbc_Latn/_keep.jsonl - config_name: swg_Latn data_files: - split: train path: swg_Latn/_keep.jsonl - config_name: niv_Latn data_files: - split: train path: niv_Latn/_keep.jsonl - config_name: cnt_Latn data_files: - split: train path: cnt_Latn/_keep.jsonl - config_name: izz_Latn data_files: - split: train path: izz_Latn/_keep.jsonl - config_name: knf_Latn data_files: - split: train path: knf_Latn/_keep.jsonl - config_name: mpp_Latn data_files: - split: train path: mpp_Latn/_keep.jsonl - config_name: kki_Latn data_files: - split: train path: kki_Latn/_keep.jsonl - config_name: nho_Latn data_files: - split: train path: nho_Latn/_keep.jsonl - config_name: sat_Latn data_files: - split: train path: sat_Latn/_keep.jsonl - config_name: kbr_Latn data_files: - split: train path: kbr_Latn/_keep.jsonl - config_name: bmu_Latn data_files: - split: train path: bmu_Latn/_keep.jsonl - config_name: hig_Latn data_files: - split: train path: hig_Latn/_keep.jsonl - config_name: qxr_Latn data_files: - split: train path: qxr_Latn/_keep.jsonl - config_name: orv_Cyrl data_files: - split: train path: orv_Cyrl/_keep.jsonl - config_name: pma_Latn data_files: - split: train path: pma_Latn/_keep.jsonl - config_name: zpl_Latn data_files: - split: train path: zpl_Latn/_keep.jsonl - config_name: kpr_Latn data_files: - split: train path: kpr_Latn/_keep.jsonl - config_name: sig_Latn data_files: - split: train path: sig_Latn/_keep.jsonl - config_name: ory_Latn data_files: - split: train path: ory_Latn/_keep.jsonl - config_name: mxp_Latn data_files: - split: train path: mxp_Latn/_keep.jsonl - config_name: lef_Latn data_files: - split: train path: lef_Latn/_keep.jsonl - config_name: mlp_Latn data_files: - split: train path: mlp_Latn/_keep.jsonl - config_name: soq_Latn data_files: - split: train path: soq_Latn/_keep.jsonl - config_name: cre_Latn data_files: - split: train path: cre_Latn/_keep.jsonl - config_name: aey_Latn data_files: - split: train path: aey_Latn/_keep.jsonl - config_name: qvs_Latn data_files: - split: train path: qvs_Latn/_keep.jsonl - config_name: sur_Latn data_files: - split: train path: sur_Latn/_keep.jsonl - config_name: knc_Arab data_files: - split: train path: knc_Arab/_keep.jsonl - config_name: suk_Latn data_files: - split: train path: suk_Latn/_keep.jsonl - config_name: cax_Latn data_files: - split: train path: cax_Latn/_keep.jsonl - config_name: alq_Latn data_files: - split: train path: alq_Latn/_keep.jsonl - config_name: chw_Latn data_files: - split: train path: chw_Latn/_keep.jsonl - config_name: dww_Latn data_files: - split: train path: dww_Latn/_keep.jsonl - config_name: gog_Latn data_files: - split: train path: gog_Latn/_keep.jsonl - config_name: viv_Latn data_files: - split: train path: viv_Latn/_keep.jsonl - config_name: qvw_Latn data_files: - split: train path: qvw_Latn/_keep.jsonl - config_name: ted_Latn data_files: - split: train path: ted_Latn/_keep.jsonl - config_name: yuj_Latn data_files: - split: train path: yuj_Latn/_keep.jsonl - config_name: ziw_Latn data_files: - split: train path: ziw_Latn/_keep.jsonl - config_name: kto_Latn data_files: - split: train path: kto_Latn/_keep.jsonl - config_name: mcq_Latn data_files: - split: train path: mcq_Latn/_keep.jsonl - config_name: sim_Latn data_files: - split: train path: sim_Latn/_keep.jsonl - config_name: koi_Latn data_files: - split: train path: koi_Latn/_keep.jsonl - config_name: lue_Latn data_files: - split: train path: lue_Latn/_keep.jsonl - config_name: cya_Latn data_files: - split: train path: cya_Latn/_keep.jsonl - config_name: knk_Latn data_files: - split: train path: knk_Latn/_keep.jsonl - config_name: tpt_Latn data_files: - split: train path: tpt_Latn/_keep.jsonl - config_name: taj_Deva data_files: - split: train path: taj_Deva/_keep.jsonl - config_name: blz_Latn data_files: - split: train path: blz_Latn/_keep.jsonl - config_name: mil_Latn data_files: - split: train path: mil_Latn/_keep.jsonl - config_name: kde_Latn data_files: - split: train path: kde_Latn/_keep.jsonl - config_name: kpz_Latn data_files: - split: train path: kpz_Latn/_keep.jsonl - config_name: hag_Latn data_files: - split: train path: hag_Latn/_keep.jsonl - config_name: vun_Latn data_files: - split: train path: vun_Latn/_keep.jsonl - config_name: kus_Latn data_files: - split: train path: kus_Latn/_keep.jsonl - config_name: lid_Latn data_files: - split: train path: lid_Latn/_keep.jsonl - config_name: tos_Latn data_files: - split: train path: tos_Latn/_keep.jsonl - config_name: bfd_Latn data_files: - split: train path: bfd_Latn/_keep.jsonl - config_name: chd_Latn data_files: - split: train path: chd_Latn/_keep.jsonl - config_name: cle_Latn data_files: - split: train path: cle_Latn/_keep.jsonl - config_name: yon_Latn data_files: - split: train path: yon_Latn/_keep.jsonl - config_name: bgs_Latn data_files: - split: train path: bgs_Latn/_keep.jsonl - config_name: lsm_Latn data_files: - split: train path: lsm_Latn/_keep.jsonl - config_name: msb_Latn data_files: - split: train path: msb_Latn/_keep.jsonl - config_name: ota_Arab data_files: - split: train path: ota_Arab/_keep.jsonl - config_name: guj_Latn data_files: - split: train path: guj_Latn/_keep.jsonl - config_name: mxq_Latn data_files: - split: train path: mxq_Latn/_keep.jsonl - config_name: lfn_Cyrl data_files: - split: train path: lfn_Cyrl/_keep.jsonl - config_name: myw_Latn data_files: - split: train path: myw_Latn/_keep.jsonl - config_name: aso_Latn data_files: - split: train path: aso_Latn/_keep.jsonl - config_name: esu_Latn data_files: - split: train path: esu_Latn/_keep.jsonl - config_name: kdi_Latn data_files: - split: train path: kdi_Latn/_keep.jsonl - config_name: bhp_Latn data_files: - split: train path: bhp_Latn/_keep.jsonl - config_name: mfz_Latn data_files: - split: train path: mfz_Latn/_keep.jsonl - config_name: sgw_Ethi data_files: - split: train path: sgw_Ethi/_keep.jsonl - config_name: xsi_Latn data_files: - split: train path: xsi_Latn/_keep.jsonl - config_name: gun_Latn data_files: - split: train path: gun_Latn/_keep.jsonl - config_name: kxc_Ethi data_files: - split: train path: kxc_Ethi/_keep.jsonl - config_name: mux_Latn data_files: - split: train path: mux_Latn/_keep.jsonl - config_name: otw_Latn data_files: - split: train path: otw_Latn/_keep.jsonl - config_name: cjp_Latn data_files: - split: train path: cjp_Latn/_keep.jsonl - config_name: nyo_Latn data_files: - split: train path: nyo_Latn/_keep.jsonl - config_name: zia_Latn data_files: - split: train path: zia_Latn/_keep.jsonl - config_name: cco_Latn data_files: - split: train path: cco_Latn/_keep.jsonl - config_name: ojb_Cans data_files: - split: train path: ojb_Cans/_keep.jsonl - config_name: ktu_Latn data_files: - split: train path: ktu_Latn/_keep.jsonl - config_name: cpy_Latn data_files: - split: train path: cpy_Latn/_keep.jsonl - config_name: txu_Latn data_files: - split: train path: txu_Latn/_keep.jsonl - config_name: bjr_Latn data_files: - split: train path: bjr_Latn/_keep.jsonl - config_name: bud_Latn data_files: - split: train path: bud_Latn/_keep.jsonl - config_name: ken_Latn data_files: - split: train path: ken_Latn/_keep.jsonl - config_name: bzh_Latn data_files: - split: train path: bzh_Latn/_keep.jsonl - config_name: ipi_Latn data_files: - split: train path: ipi_Latn/_keep.jsonl - config_name: crx_Latn data_files: - split: train path: crx_Latn/_keep.jsonl - config_name: cko_Latn data_files: - split: train path: cko_Latn/_keep.jsonl - config_name: gnd_Latn data_files: - split: train path: gnd_Latn/_keep.jsonl - config_name: kix_Latn data_files: - split: train path: kix_Latn/_keep.jsonl - config_name: mmx_Latn data_files: - split: train path: mmx_Latn/_keep.jsonl - config_name: esk_Latn data_files: - split: train path: esk_Latn/_keep.jsonl - config_name: kud_Latn data_files: - split: train path: kud_Latn/_keep.jsonl - config_name: toh_Latn data_files: - split: train path: toh_Latn/_keep.jsonl - config_name: byx_Latn data_files: - split: train path: byx_Latn/_keep.jsonl - config_name: mtp_Latn data_files: - split: train path: mtp_Latn/_keep.jsonl - config_name: kpv_Latn data_files: - split: train path: kpv_Latn/_keep.jsonl - config_name: kyz_Latn data_files: - split: train path: kyz_Latn/_keep.jsonl - config_name: lmp_Latn data_files: - split: train path: lmp_Latn/_keep.jsonl - config_name: tiy_Latn data_files: - split: train path: tiy_Latn/_keep.jsonl - config_name: ccp_Latn data_files: - split: train path: ccp_Latn/_keep.jsonl - config_name: sbl_Latn data_files: - split: train path: sbl_Latn/_keep.jsonl - config_name: tcs_Latn data_files: - split: train path: tcs_Latn/_keep.jsonl - config_name: usp_Latn data_files: - split: train path: usp_Latn/_keep.jsonl - config_name: buk_Latn data_files: - split: train path: buk_Latn/_keep.jsonl - config_name: hvn_Latn data_files: - split: train path: hvn_Latn/_keep.jsonl - config_name: amm_Latn data_files: - split: train path: amm_Latn/_keep.jsonl - config_name: kzj_Latn data_files: - split: train path: kzj_Latn/_keep.jsonl - config_name: gng_Latn data_files: - split: train path: gng_Latn/_keep.jsonl - config_name: ter_Latn data_files: - split: train path: ter_Latn/_keep.jsonl - config_name: kij_Latn data_files: - split: train path: kij_Latn/_keep.jsonl - config_name: ngl_Latn data_files: - split: train path: ngl_Latn/_keep.jsonl - config_name: pab_Latn data_files: - split: train path: pab_Latn/_keep.jsonl - config_name: pad_Latn data_files: - split: train path: pad_Latn/_keep.jsonl - config_name: kca_Cyrl data_files: - split: train path: kca_Cyrl/_keep.jsonl - config_name: meq_Latn data_files: - split: train path: meq_Latn/_keep.jsonl - config_name: kas_Cyrl data_files: - split: train path: kas_Cyrl/_keep.jsonl - config_name: niq_Latn data_files: - split: train path: niq_Latn/_keep.jsonl - config_name: dah_Latn data_files: - split: train path: dah_Latn/_keep.jsonl - config_name: lia_Latn data_files: - split: train path: lia_Latn/_keep.jsonl - config_name: kss_Latn data_files: - split: train path: kss_Latn/_keep.jsonl - config_name: bch_Latn data_files: - split: train path: bch_Latn/_keep.jsonl - config_name: khz_Latn data_files: - split: train path: khz_Latn/_keep.jsonl - config_name: nop_Latn data_files: - split: train path: nop_Latn/_keep.jsonl - config_name: yle_Latn data_files: - split: train path: yle_Latn/_keep.jsonl - config_name: ain_Latn data_files: - split: train path: ain_Latn/_keep.jsonl - config_name: pem_Latn data_files: - split: train path: pem_Latn/_keep.jsonl - config_name: yml_Latn data_files: - split: train path: yml_Latn/_keep.jsonl - config_name: taq_Tfng data_files: - split: train path: taq_Tfng/_keep.jsonl - config_name: gaw_Latn data_files: - split: train path: gaw_Latn/_keep.jsonl - config_name: kze_Latn data_files: - split: train path: kze_Latn/_keep.jsonl - config_name: tby_Latn data_files: - split: train path: tby_Latn/_keep.jsonl - config_name: cso_Latn data_files: - split: train path: cso_Latn/_keep.jsonl - config_name: ifb_Latn data_files: - split: train path: ifb_Latn/_keep.jsonl - config_name: rki_Mymr data_files: - split: train path: rki_Mymr/_keep.jsonl - config_name: aly_Latn data_files: - split: train path: aly_Latn/_keep.jsonl - config_name: kmu_Latn data_files: - split: train path: kmu_Latn/_keep.jsonl - config_name: mhl_Latn data_files: - split: train path: mhl_Latn/_keep.jsonl - config_name: kmo_Latn data_files: - split: train path: kmo_Latn/_keep.jsonl - config_name: mva_Latn data_files: - split: train path: mva_Latn/_keep.jsonl - config_name: opm_Latn data_files: - split: train path: opm_Latn/_keep.jsonl - config_name: rtm_Latn data_files: - split: train path: rtm_Latn/_keep.jsonl - config_name: xtn_Latn data_files: - split: train path: xtn_Latn/_keep.jsonl - config_name: dgr_Latn data_files: - split: train path: dgr_Latn/_keep.jsonl - config_name: ksr_Latn data_files: - split: train path: ksr_Latn/_keep.jsonl - config_name: snp_Latn data_files: - split: train path: snp_Latn/_keep.jsonl - config_name: tvk_Latn data_files: - split: train path: tvk_Latn/_keep.jsonl - config_name: zpv_Latn data_files: - split: train path: zpv_Latn/_keep.jsonl - config_name: hrx_Latn data_files: - split: train path: hrx_Latn/_keep.jsonl - config_name: kwj_Latn data_files: - split: train path: kwj_Latn/_keep.jsonl - config_name: muh_Latn data_files: - split: train path: muh_Latn/_keep.jsonl - config_name: kak_Latn data_files: - split: train path: kak_Latn/_keep.jsonl - config_name: kpw_Latn data_files: - split: train path: kpw_Latn/_keep.jsonl - config_name: akb_Latn data_files: - split: train path: akb_Latn/_keep.jsonl - config_name: ybb_Latn data_files: - split: train path: ybb_Latn/_keep.jsonl - config_name: kjs_Latn data_files: - split: train path: kjs_Latn/_keep.jsonl - config_name: wuv_Latn data_files: - split: train path: wuv_Latn/_keep.jsonl - config_name: laj_Latn data_files: - split: train path: laj_Latn/_keep.jsonl - config_name: ogo_Latn data_files: - split: train path: ogo_Latn/_keep.jsonl - config_name: nim_Latn data_files: - split: train path: nim_Latn/_keep.jsonl - config_name: czt_Latn data_files: - split: train path: czt_Latn/_keep.jsonl - config_name: aoz_Latn data_files: - split: train path: aoz_Latn/_keep.jsonl - config_name: rro_Latn data_files: - split: train path: rro_Latn/_keep.jsonl - config_name: yuw_Latn data_files: - split: train path: yuw_Latn/_keep.jsonl - config_name: heg_Latn data_files: - split: train path: heg_Latn/_keep.jsonl - config_name: mrw_Latn data_files: - split: train path: mrw_Latn/_keep.jsonl - config_name: zac_Latn data_files: - split: train path: zac_Latn/_keep.jsonl - config_name: kpf_Latn data_files: - split: train path: kpf_Latn/_keep.jsonl - config_name: leu_Latn data_files: - split: train path: leu_Latn/_keep.jsonl - config_name: nwi_Latn data_files: - split: train path: nwi_Latn/_keep.jsonl - config_name: awx_Latn data_files: - split: train path: awx_Latn/_keep.jsonl - config_name: gso_Latn data_files: - split: train path: gso_Latn/_keep.jsonl - config_name: keo_Latn data_files: - split: train path: keo_Latn/_keep.jsonl - config_name: tte_Latn data_files: - split: train path: tte_Latn/_keep.jsonl - config_name: ceg_Latn data_files: - split: train path: ceg_Latn/_keep.jsonl - config_name: nhy_Latn data_files: - split: train path: nhy_Latn/_keep.jsonl - config_name: bhw_Latn data_files: - split: train path: bhw_Latn/_keep.jsonl - config_name: gnw_Latn data_files: - split: train path: gnw_Latn/_keep.jsonl - config_name: nin_Latn data_files: - split: train path: nin_Latn/_keep.jsonl - config_name: xmv_Latn data_files: - split: train path: xmv_Latn/_keep.jsonl - config_name: crm_Cans data_files: - split: train path: crm_Cans/_keep.jsonl - config_name: mxv_Latn data_files: - split: train path: mxv_Latn/_keep.jsonl - config_name: ubr_Latn data_files: - split: train path: ubr_Latn/_keep.jsonl - config_name: gld_Cyrl data_files: - split: train path: gld_Cyrl/_keep.jsonl - config_name: bzi_Thai data_files: - split: train path: bzi_Thai/_keep.jsonl - config_name: ann_Latn data_files: - split: train path: ann_Latn/_keep.jsonl - config_name: lac_Latn data_files: - split: train path: lac_Latn/_keep.jsonl - config_name: mej_Latn data_files: - split: train path: mej_Latn/_keep.jsonl - config_name: zpc_Latn data_files: - split: train path: zpc_Latn/_keep.jsonl - config_name: dje_Latn data_files: - split: train path: dje_Latn/_keep.jsonl - config_name: caq_Latn data_files: - split: train path: caq_Latn/_keep.jsonl - config_name: guk_Ethi data_files: - split: train path: guk_Ethi/_keep.jsonl - config_name: wos_Latn data_files: - split: train path: wos_Latn/_keep.jsonl - config_name: msm_Latn data_files: - split: train path: msm_Latn/_keep.jsonl - config_name: zaw_Latn data_files: - split: train path: zaw_Latn/_keep.jsonl - config_name: cap_Latn data_files: - split: train path: cap_Latn/_keep.jsonl - config_name: mox_Latn data_files: - split: train path: mox_Latn/_keep.jsonl - config_name: zab_Latn data_files: - split: train path: zab_Latn/_keep.jsonl - config_name: mca_Latn data_files: - split: train path: mca_Latn/_keep.jsonl - config_name: wrs_Latn data_files: - split: train path: wrs_Latn/_keep.jsonl - config_name: hae_Latn data_files: - split: train path: hae_Latn/_keep.jsonl - config_name: nss_Latn data_files: - split: train path: nss_Latn/_keep.jsonl - config_name: rav_Deva data_files: - split: train path: rav_Deva/_keep.jsonl - config_name: uvh_Latn data_files: - split: train path: uvh_Latn/_keep.jsonl - config_name: dga_Latn data_files: - split: train path: dga_Latn/_keep.jsonl - config_name: ppo_Latn data_files: - split: train path: ppo_Latn/_keep.jsonl - config_name: nog_Latn data_files: - split: train path: nog_Latn/_keep.jsonl - config_name: arq_Arab data_files: - split: train path: arq_Arab/_keep.jsonl - config_name: bim_Latn data_files: - split: train path: bim_Latn/_keep.jsonl - config_name: lwg_Latn data_files: - split: train path: lwg_Latn/_keep.jsonl - config_name: kms_Latn data_files: - split: train path: kms_Latn/_keep.jsonl - config_name: kne_Latn data_files: - split: train path: kne_Latn/_keep.jsonl - config_name: tkl_Latn data_files: - split: train path: tkl_Latn/_keep.jsonl - config_name: ady_Latn data_files: - split: train path: ady_Latn/_keep.jsonl - config_name: caf_Latn data_files: - split: train path: caf_Latn/_keep.jsonl - config_name: zat_Latn data_files: - split: train path: zat_Latn/_keep.jsonl - config_name: aba_Latn data_files: - split: train path: aba_Latn/_keep.jsonl - config_name: chf_Latn data_files: - split: train path: chf_Latn/_keep.jsonl - config_name: lew_Latn data_files: - split: train path: lew_Latn/_keep.jsonl - config_name: npl_Latn data_files: - split: train path: npl_Latn/_keep.jsonl - config_name: uvl_Latn data_files: - split: train path: uvl_Latn/_keep.jsonl - config_name: cdo_Hani data_files: - split: train path: cdo_Hani/_keep.jsonl - config_name: rmq_Latn data_files: - split: train path: rmq_Latn/_keep.jsonl - config_name: mek_Latn data_files: - split: train path: mek_Latn/_keep.jsonl - config_name: snc_Latn data_files: - split: train path: snc_Latn/_keep.jsonl - config_name: nsn_Latn data_files: - split: train path: nsn_Latn/_keep.jsonl - config_name: amn_Latn data_files: - split: train path: amn_Latn/_keep.jsonl - config_name: abz_Latn data_files: - split: train path: abz_Latn/_keep.jsonl - config_name: cek_Latn data_files: - split: train path: cek_Latn/_keep.jsonl - config_name: ong_Latn data_files: - split: train path: ong_Latn/_keep.jsonl - config_name: txq_Latn data_files: - split: train path: txq_Latn/_keep.jsonl - config_name: bjp_Latn data_files: - split: train path: bjp_Latn/_keep.jsonl - config_name: gvf_Latn data_files: - split: train path: gvf_Latn/_keep.jsonl - config_name: crk_Cans data_files: - split: train path: crk_Cans/_keep.jsonl - config_name: snf_Latn data_files: - split: train path: snf_Latn/_keep.jsonl - config_name: nhg_Latn data_files: - split: train path: nhg_Latn/_keep.jsonl - config_name: kqw_Latn data_files: - split: train path: kqw_Latn/_keep.jsonl - config_name: mic_Latn data_files: - split: train path: mic_Latn/_keep.jsonl - config_name: mie_Latn data_files: - split: train path: mie_Latn/_keep.jsonl - config_name: nus_Latn data_files: - split: train path: nus_Latn/_keep.jsonl - config_name: plu_Latn data_files: - split: train path: plu_Latn/_keep.jsonl - config_name: idu_Latn data_files: - split: train path: idu_Latn/_keep.jsonl - config_name: sll_Latn data_files: - split: train path: sll_Latn/_keep.jsonl - config_name: thl_Deva data_files: - split: train path: thl_Deva/_keep.jsonl - config_name: bef_Latn data_files: - split: train path: bef_Latn/_keep.jsonl - config_name: kwd_Latn data_files: - split: train path: kwd_Latn/_keep.jsonl - config_name: mqy_Latn data_files: - split: train path: mqy_Latn/_keep.jsonl - config_name: caa_Latn data_files: - split: train path: caa_Latn/_keep.jsonl - config_name: aia_Latn data_files: - split: train path: aia_Latn/_keep.jsonl - config_name: wer_Latn data_files: - split: train path: wer_Latn/_keep.jsonl - config_name: agm_Latn data_files: - split: train path: agm_Latn/_keep.jsonl - config_name: mbl_Latn data_files: - split: train path: mbl_Latn/_keep.jsonl - config_name: mbs_Latn data_files: - split: train path: mbs_Latn/_keep.jsonl - config_name: adh_Latn data_files: - split: train path: adh_Latn/_keep.jsonl - config_name: hub_Latn data_files: - split: train path: hub_Latn/_keep.jsonl - config_name: mav_Latn data_files: - split: train path: mav_Latn/_keep.jsonl - config_name: nab_Latn data_files: - split: train path: nab_Latn/_keep.jsonl - config_name: bqp_Latn data_files: - split: train path: bqp_Latn/_keep.jsonl - config_name: guo_Latn data_files: - split: train path: guo_Latn/_keep.jsonl - config_name: auy_Latn data_files: - split: train path: auy_Latn/_keep.jsonl - config_name: big_Latn data_files: - split: train path: big_Latn/_keep.jsonl - config_name: nii_Latn data_files: - split: train path: nii_Latn/_keep.jsonl - config_name: row_Latn data_files: - split: train path: row_Latn/_keep.jsonl - config_name: kim_Cyrl data_files: - split: train path: kim_Cyrl/_keep.jsonl - config_name: mti_Latn data_files: - split: train path: mti_Latn/_keep.jsonl - config_name: otm_Latn data_files: - split: train path: otm_Latn/_keep.jsonl - config_name: prg_Latn data_files: - split: train path: prg_Latn/_keep.jsonl - config_name: icr_Latn data_files: - split: train path: icr_Latn/_keep.jsonl - config_name: mcp_Latn data_files: - split: train path: mcp_Latn/_keep.jsonl - config_name: tbo_Latn data_files: - split: train path: tbo_Latn/_keep.jsonl - config_name: chy_Latn data_files: - split: train path: chy_Latn/_keep.jsonl - config_name: oji_Latn data_files: - split: train path: oji_Latn/_keep.jsonl - config_name: kpx_Latn data_files: - split: train path: kpx_Latn/_keep.jsonl - config_name: lbb_Latn data_files: - split: train path: lbb_Latn/_keep.jsonl - config_name: pao_Latn data_files: - split: train path: pao_Latn/_keep.jsonl - config_name: xuo_Latn data_files: - split: train path: xuo_Latn/_keep.jsonl - config_name: zgh_Tfng data_files: - split: train path: zgh_Tfng/_keep.jsonl - config_name: wls_Latn data_files: - split: train path: wls_Latn/_keep.jsonl - config_name: aca_Latn data_files: - split: train path: aca_Latn/_keep.jsonl - config_name: apy_Latn data_files: - split: train path: apy_Latn/_keep.jsonl - config_name: wnc_Latn data_files: - split: train path: wnc_Latn/_keep.jsonl - config_name: ssg_Latn data_files: - split: train path: ssg_Latn/_keep.jsonl - config_name: eve_Cyrl data_files: - split: train path: eve_Cyrl/_keep.jsonl - config_name: mee_Latn data_files: - split: train path: mee_Latn/_keep.jsonl - config_name: yut_Latn data_files: - split: train path: yut_Latn/_keep.jsonl - config_name: chr_Latn data_files: - split: train path: chr_Latn/_keep.jsonl - config_name: kxm_Thai data_files: - split: train path: kxm_Thai/_keep.jsonl - config_name: mur_Latn data_files: - split: train path: mur_Latn/_keep.jsonl - config_name: lad_Hebr data_files: - split: train path: lad_Hebr/_keep.jsonl - config_name: mcd_Latn data_files: - split: train path: mcd_Latn/_keep.jsonl - config_name: cto_Latn data_files: - split: train path: cto_Latn/_keep.jsonl - config_name: mqj_Latn data_files: - split: train path: mqj_Latn/_keep.jsonl - config_name: usa_Latn data_files: - split: train path: usa_Latn/_keep.jsonl - config_name: emi_Latn data_files: - split: train path: emi_Latn/_keep.jsonl - config_name: liv_Latn data_files: - split: train path: liv_Latn/_keep.jsonl - config_name: guz_Latn data_files: - split: train path: guz_Latn/_keep.jsonl - config_name: tgp_Latn data_files: - split: train path: tgp_Latn/_keep.jsonl - config_name: ncl_Latn data_files: - split: train path: ncl_Latn/_keep.jsonl - config_name: azg_Latn data_files: - split: train path: azg_Latn/_keep.jsonl - config_name: kck_Latn data_files: - split: train path: kck_Latn/_keep.jsonl - config_name: apb_Latn data_files: - split: train path: apb_Latn/_keep.jsonl - config_name: kbm_Latn data_files: - split: train path: kbm_Latn/_keep.jsonl - config_name: sgz_Latn data_files: - split: train path: sgz_Latn/_keep.jsonl - config_name: wsk_Latn data_files: - split: train path: wsk_Latn/_keep.jsonl - config_name: gbm_Deva data_files: - split: train path: gbm_Deva/_keep.jsonl - config_name: csw_Latn data_files: - split: train path: csw_Latn/_keep.jsonl - config_name: ctp_Latn data_files: - split: train path: ctp_Latn/_keep.jsonl - config_name: eri_Latn data_files: - split: train path: eri_Latn/_keep.jsonl - config_name: vid_Latn data_files: - split: train path: vid_Latn/_keep.jsonl - config_name: bsq_Latn data_files: - split: train path: bsq_Latn/_keep.jsonl - config_name: dak_Latn data_files: - split: train path: dak_Latn/_keep.jsonl - config_name: tif_Latn data_files: - split: train path: tif_Latn/_keep.jsonl - config_name: xsr_Deva data_files: - split: train path: xsr_Deva/_keep.jsonl - config_name: mwp_Latn data_files: - split: train path: mwp_Latn/_keep.jsonl - config_name: roo_Latn data_files: - split: train path: roo_Latn/_keep.jsonl - config_name: wbp_Latn data_files: - split: train path: wbp_Latn/_keep.jsonl - config_name: gdn_Latn data_files: - split: train path: gdn_Latn/_keep.jsonl - config_name: tgo_Latn data_files: - split: train path: tgo_Latn/_keep.jsonl - config_name: zpm_Latn data_files: - split: train path: zpm_Latn/_keep.jsonl - config_name: mih_Latn data_files: - split: train path: mih_Latn/_keep.jsonl - config_name: qvc_Latn data_files: - split: train path: qvc_Latn/_keep.jsonl - config_name: tod_Latn data_files: - split: train path: tod_Latn/_keep.jsonl - config_name: abn_Latn data_files: - split: train path: abn_Latn/_keep.jsonl - config_name: cao_Latn data_files: - split: train path: cao_Latn/_keep.jsonl - config_name: kbc_Latn data_files: - split: train path: kbc_Latn/_keep.jsonl - config_name: kog_Latn data_files: - split: train path: kog_Latn/_keep.jsonl - config_name: moh_Latn data_files: - split: train path: moh_Latn/_keep.jsonl - config_name: leh_Latn data_files: - split: train path: leh_Latn/_keep.jsonl - config_name: nsu_Latn data_files: - split: train path: nsu_Latn/_keep.jsonl - config_name: okv_Latn data_files: - split: train path: okv_Latn/_keep.jsonl - config_name: tih_Latn data_files: - split: train path: tih_Latn/_keep.jsonl - config_name: zos_Latn data_files: - split: train path: zos_Latn/_keep.jsonl - config_name: llg_Latn data_files: - split: train path: llg_Latn/_keep.jsonl - config_name: gmv_Ethi data_files: - split: train path: gmv_Ethi/_keep.jsonl - config_name: kyf_Latn data_files: - split: train path: kyf_Latn/_keep.jsonl - config_name: mhx_Latn data_files: - split: train path: mhx_Latn/_keep.jsonl - config_name: mvp_Latn data_files: - split: train path: mvp_Latn/_keep.jsonl - config_name: naf_Latn data_files: - split: train path: naf_Latn/_keep.jsonl - config_name: ino_Latn data_files: - split: train path: ino_Latn/_keep.jsonl - config_name: dng_Cyrl data_files: - split: train path: dng_Cyrl/_keep.jsonl - config_name: mnk_Latn data_files: - split: train path: mnk_Latn/_keep.jsonl - config_name: oke_Latn data_files: - split: train path: oke_Latn/_keep.jsonl - config_name: omw_Latn data_files: - split: train path: omw_Latn/_keep.jsonl - config_name: tnk_Latn data_files: - split: train path: tnk_Latn/_keep.jsonl - config_name: xtd_Latn data_files: - split: train path: xtd_Latn/_keep.jsonl - config_name: agt_Latn data_files: - split: train path: agt_Latn/_keep.jsonl - config_name: cbr_Latn data_files: - split: train path: cbr_Latn/_keep.jsonl - config_name: eko_Latn data_files: - split: train path: eko_Latn/_keep.jsonl - config_name: nhk_Latn data_files: - split: train path: nhk_Latn/_keep.jsonl - config_name: hot_Latn data_files: - split: train path: hot_Latn/_keep.jsonl - config_name: iou_Latn data_files: - split: train path: iou_Latn/_keep.jsonl - config_name: mpm_Latn data_files: - split: train path: mpm_Latn/_keep.jsonl - config_name: myx_Latn data_files: - split: train path: myx_Latn/_keep.jsonl - config_name: ndh_Latn data_files: - split: train path: ndh_Latn/_keep.jsonl - config_name: pbb_Latn data_files: - split: train path: pbb_Latn/_keep.jsonl - config_name: rng_Latn data_files: - split: train path: rng_Latn/_keep.jsonl - config_name: cri_Latn data_files: - split: train path: cri_Latn/_keep.jsonl - config_name: bvd_Latn data_files: - split: train path: bvd_Latn/_keep.jsonl - config_name: kmz_Latn data_files: - split: train path: kmz_Latn/_keep.jsonl - config_name: cta_Latn data_files: - split: train path: cta_Latn/_keep.jsonl - config_name: blw_Latn data_files: - split: train path: blw_Latn/_keep.jsonl - config_name: clu_Latn data_files: - split: train path: clu_Latn/_keep.jsonl - config_name: cof_Latn data_files: - split: train path: cof_Latn/_keep.jsonl - config_name: kje_Latn data_files: - split: train path: kje_Latn/_keep.jsonl - config_name: nmf_Latn data_files: - split: train path: nmf_Latn/_keep.jsonl - config_name: kbh_Latn data_files: - split: train path: kbh_Latn/_keep.jsonl - config_name: qxn_Latn data_files: - split: train path: qxn_Latn/_keep.jsonl - config_name: ria_Latn data_files: - split: train path: ria_Latn/_keep.jsonl - config_name: wed_Latn data_files: - split: train path: wed_Latn/_keep.jsonl - config_name: zar_Latn data_files: - split: train path: zar_Latn/_keep.jsonl - config_name: huv_Latn data_files: - split: train path: huv_Latn/_keep.jsonl - config_name: lsi_Latn data_files: - split: train path: lsi_Latn/_keep.jsonl - config_name: msk_Latn data_files: - split: train path: msk_Latn/_keep.jsonl - config_name: nbq_Latn data_files: - split: train path: nbq_Latn/_keep.jsonl - config_name: ati_Latn data_files: - split: train path: ati_Latn/_keep.jsonl - config_name: lww_Latn data_files: - split: train path: lww_Latn/_keep.jsonl - config_name: yva_Latn data_files: - split: train path: yva_Latn/_keep.jsonl - config_name: amr_Latn data_files: - split: train path: amr_Latn/_keep.jsonl - config_name: lmk_Latn data_files: - split: train path: lmk_Latn/_keep.jsonl - config_name: tim_Latn data_files: - split: train path: tim_Latn/_keep.jsonl - config_name: bbb_Latn data_files: - split: train path: bbb_Latn/_keep.jsonl - config_name: bzd_Latn data_files: - split: train path: bzd_Latn/_keep.jsonl - config_name: djr_Latn data_files: - split: train path: djr_Latn/_keep.jsonl - config_name: kwf_Latn data_files: - split: train path: kwf_Latn/_keep.jsonl - config_name: nuy_Latn data_files: - split: train path: nuy_Latn/_keep.jsonl - config_name: poi_Latn data_files: - split: train path: poi_Latn/_keep.jsonl - config_name: ptp_Latn data_files: - split: train path: ptp_Latn/_keep.jsonl - config_name: atd_Latn data_files: - split: train path: atd_Latn/_keep.jsonl - config_name: bps_Latn data_files: - split: train path: bps_Latn/_keep.jsonl - config_name: lcm_Latn data_files: - split: train path: lcm_Latn/_keep.jsonl - config_name: mbh_Latn data_files: - split: train path: mbh_Latn/_keep.jsonl - config_name: nuj_Latn data_files: - split: train path: nuj_Latn/_keep.jsonl - config_name: ayp_Arab data_files: - split: train path: ayp_Arab/_keep.jsonl - config_name: cwe_Latn data_files: - split: train path: cwe_Latn/_keep.jsonl - config_name: geb_Latn data_files: - split: train path: geb_Latn/_keep.jsonl - config_name: aoi_Latn data_files: - split: train path: aoi_Latn/_keep.jsonl - config_name: mto_Latn data_files: - split: train path: mto_Latn/_keep.jsonl - config_name: cbi_Latn data_files: - split: train path: cbi_Latn/_keep.jsonl - config_name: gvn_Latn data_files: - split: train path: gvn_Latn/_keep.jsonl - config_name: kqf_Latn data_files: - split: train path: kqf_Latn/_keep.jsonl - config_name: rkb_Latn data_files: - split: train path: rkb_Latn/_keep.jsonl - config_name: xed_Latn data_files: - split: train path: xed_Latn/_keep.jsonl - config_name: zas_Latn data_files: - split: train path: zas_Latn/_keep.jsonl - config_name: apz_Latn data_files: - split: train path: apz_Latn/_keep.jsonl - config_name: cpb_Latn data_files: - split: train path: cpb_Latn/_keep.jsonl - config_name: ese_Latn data_files: - split: train path: ese_Latn/_keep.jsonl - config_name: gdg_Latn data_files: - split: train path: gdg_Latn/_keep.jsonl - config_name: iws_Latn data_files: - split: train path: iws_Latn/_keep.jsonl - config_name: apu_Latn data_files: - split: train path: apu_Latn/_keep.jsonl - config_name: cag_Latn data_files: - split: train path: cag_Latn/_keep.jsonl - config_name: kdc_Latn data_files: - split: train path: kdc_Latn/_keep.jsonl - config_name: nou_Latn data_files: - split: train path: nou_Latn/_keep.jsonl - config_name: too_Latn data_files: - split: train path: too_Latn/_keep.jsonl - config_name: xmm_Latn data_files: - split: train path: xmm_Latn/_keep.jsonl - config_name: beq_Latn data_files: - split: train path: beq_Latn/_keep.jsonl - config_name: hnn_Latn data_files: - split: train path: hnn_Latn/_keep.jsonl - config_name: myk_Latn data_files: - split: train path: myk_Latn/_keep.jsonl - config_name: sby_Latn data_files: - split: train path: sby_Latn/_keep.jsonl - config_name: arl_Latn data_files: - split: train path: arl_Latn/_keep.jsonl - config_name: ncu_Latn data_files: - split: train path: ncu_Latn/_keep.jsonl - config_name: rml_Latn data_files: - split: train path: rml_Latn/_keep.jsonl - config_name: gam_Latn data_files: - split: train path: gam_Latn/_keep.jsonl - config_name: kvn_Latn data_files: - split: train path: kvn_Latn/_keep.jsonl - config_name: mbc_Latn data_files: - split: train path: mbc_Latn/_keep.jsonl - config_name: mfy_Latn data_files: - split: train path: mfy_Latn/_keep.jsonl - config_name: urt_Latn data_files: - split: train path: urt_Latn/_keep.jsonl - config_name: luc_Latn data_files: - split: train path: luc_Latn/_keep.jsonl - config_name: mio_Latn data_files: - split: train path: mio_Latn/_keep.jsonl - config_name: snn_Latn data_files: - split: train path: snn_Latn/_keep.jsonl - config_name: tar_Latn data_files: - split: train path: tar_Latn/_keep.jsonl - config_name: tku_Latn data_files: - split: train path: tku_Latn/_keep.jsonl - config_name: upv_Latn data_files: - split: train path: upv_Latn/_keep.jsonl - config_name: kjg_Laoo data_files: - split: train path: kjg_Laoo/_keep.jsonl - config_name: btd_Latn data_files: - split: train path: btd_Latn/_keep.jsonl - config_name: cut_Latn data_files: - split: train path: cut_Latn/_keep.jsonl - config_name: mwn_Latn data_files: - split: train path: mwn_Latn/_keep.jsonl - config_name: tue_Latn data_files: - split: train path: tue_Latn/_keep.jsonl - config_name: adz_Latn data_files: - split: train path: adz_Latn/_keep.jsonl - config_name: kyg_Latn data_files: - split: train path: kyg_Latn/_keep.jsonl - config_name: rel_Latn data_files: - split: train path: rel_Latn/_keep.jsonl - config_name: tew_Latn data_files: - split: train path: tew_Latn/_keep.jsonl - config_name: ttc_Latn data_files: - split: train path: ttc_Latn/_keep.jsonl - config_name: nkf_Latn data_files: - split: train path: nkf_Latn/_keep.jsonl - config_name: yrb_Latn data_files: - split: train path: yrb_Latn/_keep.jsonl - config_name: fub_Latn data_files: - split: train path: fub_Latn/_keep.jsonl - config_name: nsm_Latn data_files: - split: train path: nsm_Latn/_keep.jsonl - config_name: nyf_Latn data_files: - split: train path: nyf_Latn/_keep.jsonl - config_name: ava_Latn data_files: - split: train path: ava_Latn/_keep.jsonl - config_name: bkd_Latn data_files: - split: train path: bkd_Latn/_keep.jsonl - config_name: cpc_Latn data_files: - split: train path: cpc_Latn/_keep.jsonl - config_name: lif_Limb data_files: - split: train path: lif_Limb/_keep.jsonl - config_name: mwc_Latn data_files: - split: train path: mwc_Latn/_keep.jsonl - config_name: gan_Latn data_files: - split: train path: gan_Latn/_keep.jsonl - config_name: apw_Latn data_files: - split: train path: apw_Latn/_keep.jsonl - config_name: azz_Latn data_files: - split: train path: azz_Latn/_keep.jsonl - config_name: zpo_Latn data_files: - split: train path: zpo_Latn/_keep.jsonl - config_name: ace_Arab data_files: - split: train path: ace_Arab/_keep.jsonl - config_name: faa_Latn data_files: - split: train path: faa_Latn/_keep.jsonl - config_name: ood_Latn data_files: - split: train path: ood_Latn/_keep.jsonl - config_name: toc_Latn data_files: - split: train path: toc_Latn/_keep.jsonl - config_name: wmt_Latn data_files: - split: train path: wmt_Latn/_keep.jsonl - config_name: ajg_Latn data_files: - split: train path: ajg_Latn/_keep.jsonl - config_name: nko_Latn data_files: - split: train path: nko_Latn/_keep.jsonl - config_name: ssd_Latn data_files: - split: train path: ssd_Latn/_keep.jsonl - config_name: sxb_Latn data_files: - split: train path: sxb_Latn/_keep.jsonl - config_name: zxx_Latn data_files: - split: train path: zxx_Latn/_keep.jsonl - config_name: not_Latn data_files: - split: train path: not_Latn/_keep.jsonl - config_name: amk_Latn data_files: - split: train path: amk_Latn/_keep.jsonl - config_name: hch_Latn data_files: - split: train path: hch_Latn/_keep.jsonl - config_name: kqc_Latn data_files: - split: train path: kqc_Latn/_keep.jsonl - config_name: aui_Latn data_files: - split: train path: aui_Latn/_keep.jsonl - config_name: llb_Latn data_files: - split: train path: llb_Latn/_keep.jsonl - config_name: avt_Latn data_files: - split: train path: avt_Latn/_keep.jsonl - config_name: kaq_Latn data_files: - split: train path: kaq_Latn/_keep.jsonl - config_name: tna_Latn data_files: - split: train path: tna_Latn/_keep.jsonl - config_name: zpt_Latn data_files: - split: train path: zpt_Latn/_keep.jsonl - config_name: mnw_Latn data_files: - split: train path: mnw_Latn/_keep.jsonl - config_name: bwd_Latn data_files: - split: train path: bwd_Latn/_keep.jsonl - config_name: lif_Deva data_files: - split: train path: lif_Deva/_keep.jsonl - config_name: stn_Latn data_files: - split: train path: stn_Latn/_keep.jsonl - config_name: crk_Latn data_files: - split: train path: crk_Latn/_keep.jsonl - config_name: kgk_Latn data_files: - split: train path: kgk_Latn/_keep.jsonl - config_name: mck_Latn data_files: - split: train path: mck_Latn/_keep.jsonl - config_name: bhg_Latn data_files: - split: train path: bhg_Latn/_keep.jsonl - config_name: ifu_Latn data_files: - split: train path: ifu_Latn/_keep.jsonl - config_name: kkl_Latn data_files: - split: train path: kkl_Latn/_keep.jsonl - config_name: zao_Latn data_files: - split: train path: zao_Latn/_keep.jsonl - config_name: huu_Latn data_files: - split: train path: huu_Latn/_keep.jsonl - config_name: sil_Latn data_files: - split: train path: sil_Latn/_keep.jsonl - config_name: trq_Latn data_files: - split: train path: trq_Latn/_keep.jsonl - config_name: tuf_Latn data_files: - split: train path: tuf_Latn/_keep.jsonl - config_name: wnu_Latn data_files: - split: train path: wnu_Latn/_keep.jsonl - config_name: amf_Latn data_files: - split: train path: amf_Latn/_keep.jsonl - config_name: fan_Latn data_files: - split: train path: fan_Latn/_keep.jsonl - config_name: zdj_Latn data_files: - split: train path: zdj_Latn/_keep.jsonl - config_name: bco_Latn data_files: - split: train path: bco_Latn/_keep.jsonl - config_name: kdl_Latn data_files: - split: train path: kdl_Latn/_keep.jsonl - config_name: lln_Latn data_files: - split: train path: lln_Latn/_keep.jsonl - config_name: mit_Latn data_files: - split: train path: mit_Latn/_keep.jsonl - config_name: yaq_Latn data_files: - split: train path: yaq_Latn/_keep.jsonl - config_name: ake_Latn data_files: - split: train path: ake_Latn/_keep.jsonl - config_name: ige_Latn data_files: - split: train path: ige_Latn/_keep.jsonl - config_name: mna_Latn data_files: - split: train path: mna_Latn/_keep.jsonl - config_name: nhx_Latn data_files: - split: train path: nhx_Latn/_keep.jsonl - config_name: njn_Latn data_files: - split: train path: njn_Latn/_keep.jsonl - config_name: wba_Latn data_files: - split: train path: wba_Latn/_keep.jsonl - config_name: zaa_Latn data_files: - split: train path: zaa_Latn/_keep.jsonl - config_name: lez_Latn data_files: - split: train path: lez_Latn/_keep.jsonl - config_name: syb_Latn data_files: - split: train path: syb_Latn/_keep.jsonl - config_name: qxo_Latn data_files: - split: train path: qxo_Latn/_keep.jsonl - config_name: rgu_Latn data_files: - split: train path: rgu_Latn/_keep.jsonl - config_name: wiu_Latn data_files: - split: train path: wiu_Latn/_keep.jsonl - config_name: bla_Latn data_files: - split: train path: bla_Latn/_keep.jsonl - config_name: etr_Latn data_files: - split: train path: etr_Latn/_keep.jsonl - config_name: miy_Latn data_files: - split: train path: miy_Latn/_keep.jsonl - config_name: mjc_Latn data_files: - split: train path: mjc_Latn/_keep.jsonl - config_name: nif_Latn data_files: - split: train path: nif_Latn/_keep.jsonl - config_name: pov_Latn data_files: - split: train path: pov_Latn/_keep.jsonl - config_name: qxl_Latn data_files: - split: train path: qxl_Latn/_keep.jsonl - config_name: sey_Latn data_files: - split: train path: sey_Latn/_keep.jsonl - config_name: bxh_Latn data_files: - split: train path: bxh_Latn/_keep.jsonl - config_name: ddg_Latn data_files: - split: train path: ddg_Latn/_keep.jsonl - config_name: mks_Latn data_files: - split: train path: mks_Latn/_keep.jsonl - config_name: nki_Latn data_files: - split: train path: nki_Latn/_keep.jsonl - config_name: pot_Latn data_files: - split: train path: pot_Latn/_keep.jsonl - config_name: prf_Latn data_files: - split: train path: prf_Latn/_keep.jsonl - config_name: hra_Latn data_files: - split: train path: hra_Latn/_keep.jsonl - config_name: law_Latn data_files: - split: train path: law_Latn/_keep.jsonl - config_name: plw_Latn data_files: - split: train path: plw_Latn/_keep.jsonl - config_name: zpi_Latn data_files: - split: train path: zpi_Latn/_keep.jsonl - config_name: atg_Latn data_files: - split: train path: atg_Latn/_keep.jsonl - config_name: daf_Latn data_files: - split: train path: daf_Latn/_keep.jsonl - config_name: drg_Latn data_files: - split: train path: drg_Latn/_keep.jsonl - config_name: dru_Latn data_files: - split: train path: dru_Latn/_keep.jsonl - config_name: ngp_Latn data_files: - split: train path: ngp_Latn/_keep.jsonl - config_name: boa_Latn data_files: - split: train path: boa_Latn/_keep.jsonl - config_name: cbt_Latn data_files: - split: train path: cbt_Latn/_keep.jsonl - config_name: dhm_Latn data_files: - split: train path: dhm_Latn/_keep.jsonl - config_name: ikw_Latn data_files: - split: train path: ikw_Latn/_keep.jsonl - config_name: kqe_Latn data_files: - split: train path: kqe_Latn/_keep.jsonl - config_name: lbj_Tibt data_files: - split: train path: lbj_Tibt/_keep.jsonl - config_name: loq_Latn data_files: - split: train path: loq_Latn/_keep.jsonl - config_name: xsb_Latn data_files: - split: train path: xsb_Latn/_keep.jsonl - config_name: yad_Latn data_files: - split: train path: yad_Latn/_keep.jsonl - config_name: kyu_Latn data_files: - split: train path: kyu_Latn/_keep.jsonl - config_name: mcb_Latn data_files: - split: train path: mcb_Latn/_keep.jsonl - config_name: tks_Arab data_files: - split: train path: tks_Arab/_keep.jsonl - config_name: cnl_Latn data_files: - split: train path: cnl_Latn/_keep.jsonl - config_name: far_Latn data_files: - split: train path: far_Latn/_keep.jsonl - config_name: miz_Latn data_files: - split: train path: miz_Latn/_keep.jsonl - config_name: maj_Latn data_files: - split: train path: maj_Latn/_keep.jsonl - config_name: mgm_Latn data_files: - split: train path: mgm_Latn/_keep.jsonl - config_name: mib_Latn data_files: - split: train path: mib_Latn/_keep.jsonl - config_name: mza_Latn data_files: - split: train path: mza_Latn/_keep.jsonl - config_name: nhr_Latn data_files: - split: train path: nhr_Latn/_keep.jsonl - config_name: smt_Latn data_files: - split: train path: smt_Latn/_keep.jsonl - config_name: ish_Latn data_files: - split: train path: ish_Latn/_keep.jsonl - config_name: mlu_Latn data_files: - split: train path: mlu_Latn/_keep.jsonl - config_name: yka_Latn data_files: - split: train path: yka_Latn/_keep.jsonl - config_name: anv_Latn data_files: - split: train path: anv_Latn/_keep.jsonl - config_name: ign_Latn data_files: - split: train path: ign_Latn/_keep.jsonl - config_name: mir_Latn data_files: - split: train path: mir_Latn/_keep.jsonl - config_name: tav_Latn data_files: - split: train path: tav_Latn/_keep.jsonl - config_name: gyr_Latn data_files: - split: train path: gyr_Latn/_keep.jsonl - config_name: klt_Latn data_files: - split: train path: klt_Latn/_keep.jsonl - config_name: apn_Latn data_files: - split: train path: apn_Latn/_keep.jsonl - config_name: wbm_Latn data_files: - split: train path: wbm_Latn/_keep.jsonl - config_name: cjk_Latn data_files: - split: train path: cjk_Latn/_keep.jsonl - config_name: dln_Latn data_files: - split: train path: dln_Latn/_keep.jsonl - config_name: mcf_Latn data_files: - split: train path: mcf_Latn/_keep.jsonl - config_name: twx_Latn data_files: - split: train path: twx_Latn/_keep.jsonl - config_name: ldi_Latn data_files: - split: train path: ldi_Latn/_keep.jsonl - config_name: poy_Latn data_files: - split: train path: poy_Latn/_keep.jsonl - config_name: yaa_Latn data_files: - split: train path: yaa_Latn/_keep.jsonl - config_name: zae_Latn data_files: - split: train path: zae_Latn/_keep.jsonl - config_name: bdq_Latn data_files: - split: train path: bdq_Latn/_keep.jsonl - config_name: con_Latn data_files: - split: train path: con_Latn/_keep.jsonl - config_name: dnw_Latn data_files: - split: train path: dnw_Latn/_keep.jsonl - config_name: gah_Latn data_files: - split: train path: gah_Latn/_keep.jsonl - config_name: lcp_Thai data_files: - split: train path: lcp_Thai/_keep.jsonl - config_name: mbj_Latn data_files: - split: train path: mbj_Latn/_keep.jsonl - config_name: xog_Latn data_files: - split: train path: xog_Latn/_keep.jsonl - config_name: yan_Latn data_files: - split: train path: yan_Latn/_keep.jsonl - config_name: sdq_Latn data_files: - split: train path: sdq_Latn/_keep.jsonl - config_name: sgh_Cyrl data_files: - split: train path: sgh_Cyrl/_keep.jsonl - config_name: gwi_Latn data_files: - split: train path: gwi_Latn/_keep.jsonl - config_name: lbk_Latn data_files: - split: train path: lbk_Latn/_keep.jsonl - config_name: ses_Latn data_files: - split: train path: ses_Latn/_keep.jsonl - config_name: ycn_Latn data_files: - split: train path: ycn_Latn/_keep.jsonl - config_name: kau_Latn data_files: - split: train path: kau_Latn/_keep.jsonl - config_name: hix_Latn data_files: - split: train path: hix_Latn/_keep.jsonl - config_name: mig_Latn data_files: - split: train path: mig_Latn/_keep.jsonl - config_name: mlh_Latn data_files: - split: train path: mlh_Latn/_keep.jsonl - config_name: aer_Latn data_files: - split: train path: aer_Latn/_keep.jsonl - config_name: amx_Latn data_files: - split: train path: amx_Latn/_keep.jsonl - config_name: auc_Latn data_files: - split: train path: auc_Latn/_keep.jsonl - config_name: cly_Latn data_files: - split: train path: cly_Latn/_keep.jsonl - config_name: dsh_Latn data_files: - split: train path: dsh_Latn/_keep.jsonl - config_name: gnb_Latn data_files: - split: train path: gnb_Latn/_keep.jsonl - config_name: neb_Latn data_files: - split: train path: neb_Latn/_keep.jsonl - config_name: ttt_Cyrl data_files: - split: train path: ttt_Cyrl/_keep.jsonl - config_name: jic_Latn data_files: - split: train path: jic_Latn/_keep.jsonl - config_name: xtm_Latn data_files: - split: train path: xtm_Latn/_keep.jsonl - config_name: tll_Latn data_files: - split: train path: tll_Latn/_keep.jsonl - config_name: apt_Latn data_files: - split: train path: apt_Latn/_keep.jsonl - config_name: kgr_Latn data_files: - split: train path: kgr_Latn/_keep.jsonl - config_name: pio_Latn data_files: - split: train path: pio_Latn/_keep.jsonl - config_name: pmf_Latn data_files: - split: train path: pmf_Latn/_keep.jsonl - config_name: yrk_Latn data_files: - split: train path: yrk_Latn/_keep.jsonl - config_name: akh_Latn data_files: - split: train path: akh_Latn/_keep.jsonl - config_name: box_Latn data_files: - split: train path: box_Latn/_keep.jsonl - config_name: cub_Latn data_files: - split: train path: cub_Latn/_keep.jsonl - config_name: cux_Latn data_files: - split: train path: cux_Latn/_keep.jsonl - config_name: mrq_Latn data_files: - split: train path: mrq_Latn/_keep.jsonl - config_name: inh_Latn data_files: - split: train path: inh_Latn/_keep.jsonl - config_name: bsp_Latn data_files: - split: train path: bsp_Latn/_keep.jsonl - config_name: for_Latn data_files: - split: train path: for_Latn/_keep.jsonl - config_name: kny_Latn data_files: - split: train path: kny_Latn/_keep.jsonl - config_name: uri_Latn data_files: - split: train path: uri_Latn/_keep.jsonl - config_name: zsr_Latn data_files: - split: train path: zsr_Latn/_keep.jsonl - config_name: pce_Mymr data_files: - split: train path: pce_Mymr/_keep.jsonl - config_name: cme_Latn data_files: - split: train path: cme_Latn/_keep.jsonl - config_name: cot_Latn data_files: - split: train path: cot_Latn/_keep.jsonl - config_name: kxw_Latn data_files: - split: train path: kxw_Latn/_keep.jsonl - config_name: omb_Latn data_files: - split: train path: omb_Latn/_keep.jsonl - config_name: srq_Latn data_files: - split: train path: srq_Latn/_keep.jsonl - config_name: vag_Latn data_files: - split: train path: vag_Latn/_keep.jsonl - config_name: cpu_Latn data_files: - split: train path: cpu_Latn/_keep.jsonl - config_name: kmy_Latn data_files: - split: train path: kmy_Latn/_keep.jsonl - config_name: ksc_Latn data_files: - split: train path: ksc_Latn/_keep.jsonl - config_name: lai_Latn data_files: - split: train path: lai_Latn/_keep.jsonl - config_name: nnp_Latn data_files: - split: train path: nnp_Latn/_keep.jsonl - config_name: ruf_Latn data_files: - split: train path: ruf_Latn/_keep.jsonl - config_name: spm_Latn data_files: - split: train path: spm_Latn/_keep.jsonl - config_name: tro_Latn data_files: - split: train path: tro_Latn/_keep.jsonl - config_name: ttj_Latn data_files: - split: train path: ttj_Latn/_keep.jsonl - config_name: waj_Latn data_files: - split: train path: waj_Latn/_keep.jsonl - config_name: raj_Deva data_files: - split: train path: raj_Deva/_keep.jsonl - config_name: ian_Latn data_files: - split: train path: ian_Latn/_keep.jsonl - config_name: ivb_Latn data_files: - split: train path: ivb_Latn/_keep.jsonl - config_name: kmm_Latn data_files: - split: train path: kmm_Latn/_keep.jsonl - config_name: kzf_Latn data_files: - split: train path: kzf_Latn/_keep.jsonl - config_name: maw_Latn data_files: - split: train path: maw_Latn/_keep.jsonl - config_name: tuv_Latn data_files: - split: train path: tuv_Latn/_keep.jsonl - config_name: whk_Latn data_files: - split: train path: whk_Latn/_keep.jsonl - config_name: zsm_Arab data_files: - split: train path: zsm_Arab/_keep.jsonl - config_name: aph_Deva data_files: - split: train path: aph_Deva/_keep.jsonl - config_name: anm_Latn data_files: - split: train path: anm_Latn/_keep.jsonl - config_name: mny_Latn data_files: - split: train path: mny_Latn/_keep.jsonl - config_name: bug_Bugi data_files: - split: train path: bug_Bugi/_keep.jsonl - config_name: trp_Latn data_files: - split: train path: trp_Latn/_keep.jsonl - config_name: are_Latn data_files: - split: train path: are_Latn/_keep.jsonl - config_name: esi_Latn data_files: - split: train path: esi_Latn/_keep.jsonl - config_name: mhi_Latn data_files: - split: train path: mhi_Latn/_keep.jsonl - config_name: obo_Latn data_files: - split: train path: obo_Latn/_keep.jsonl - config_name: bwu_Latn data_files: - split: train path: bwu_Latn/_keep.jsonl - config_name: lwo_Latn data_files: - split: train path: lwo_Latn/_keep.jsonl - config_name: mrg_Latn data_files: - split: train path: mrg_Latn/_keep.jsonl - config_name: old_Latn data_files: - split: train path: old_Latn/_keep.jsonl - config_name: zav_Latn data_files: - split: train path: zav_Latn/_keep.jsonl - config_name: snk_Latn data_files: - split: train path: snk_Latn/_keep.jsonl - config_name: daa_Latn data_files: - split: train path: daa_Latn/_keep.jsonl - config_name: fuq_Latn data_files: - split: train path: fuq_Latn/_keep.jsonl - config_name: lud_Latn data_files: - split: train path: lud_Latn/_keep.jsonl - config_name: nlg_Latn data_files: - split: train path: nlg_Latn/_keep.jsonl - config_name: sck_Deva data_files: - split: train path: sck_Deva/_keep.jsonl - config_name: tbl_Latn data_files: - split: train path: tbl_Latn/_keep.jsonl - config_name: khb_Talu data_files: - split: train path: khb_Talu/_keep.jsonl - config_name: tpu_Khmr data_files: - split: train path: tpu_Khmr/_keep.jsonl - config_name: fue_Latn data_files: - split: train path: fue_Latn/_keep.jsonl - config_name: tmd_Latn data_files: - split: train path: tmd_Latn/_keep.jsonl - config_name: whg_Latn data_files: - split: train path: whg_Latn/_keep.jsonl - config_name: blt_Latn data_files: - split: train path: blt_Latn/_keep.jsonl - config_name: gqr_Latn data_files: - split: train path: gqr_Latn/_keep.jsonl - config_name: kub_Latn data_files: - split: train path: kub_Latn/_keep.jsonl - config_name: ots_Latn data_files: - split: train path: ots_Latn/_keep.jsonl - config_name: tpp_Latn data_files: - split: train path: tpp_Latn/_keep.jsonl - config_name: var_Latn data_files: - split: train path: var_Latn/_keep.jsonl - config_name: hbb_Latn data_files: - split: train path: hbb_Latn/_keep.jsonl - config_name: krr_Khmr data_files: - split: train path: krr_Khmr/_keep.jsonl - config_name: zxx_Zyyy data_files: - split: train path: zxx_Zyyy/_keep.jsonl - config_name: alj_Latn data_files: - split: train path: alj_Latn/_keep.jsonl - config_name: ebk_Latn data_files: - split: train path: ebk_Latn/_keep.jsonl - config_name: goa_Latn data_files: - split: train path: goa_Latn/_keep.jsonl - config_name: hav_Latn data_files: - split: train path: hav_Latn/_keep.jsonl - config_name: kmk_Latn data_files: - split: train path: kmk_Latn/_keep.jsonl - config_name: kqo_Latn data_files: - split: train path: kqo_Latn/_keep.jsonl - config_name: muy_Latn data_files: - split: train path: muy_Latn/_keep.jsonl - config_name: njb_Latn data_files: - split: train path: njb_Latn/_keep.jsonl - config_name: snw_Latn data_files: - split: train path: snw_Latn/_keep.jsonl - config_name: wib_Latn data_files: - split: train path: wib_Latn/_keep.jsonl - config_name: shn_Latn data_files: - split: train path: shn_Latn/_keep.jsonl - config_name: tkr_Latn data_files: - split: train path: tkr_Latn/_keep.jsonl - config_name: ksp_Latn data_files: - split: train path: ksp_Latn/_keep.jsonl - config_name: lip_Latn data_files: - split: train path: lip_Latn/_keep.jsonl - config_name: mog_Latn data_files: - split: train path: mog_Latn/_keep.jsonl - config_name: nla_Latn data_files: - split: train path: nla_Latn/_keep.jsonl - config_name: pss_Latn data_files: - split: train path: pss_Latn/_keep.jsonl - config_name: zad_Latn data_files: - split: train path: zad_Latn/_keep.jsonl - config_name: awi_Latn data_files: - split: train path: awi_Latn/_keep.jsonl - config_name: frd_Latn data_files: - split: train path: frd_Latn/_keep.jsonl - config_name: kei_Latn data_files: - split: train path: kei_Latn/_keep.jsonl - config_name: kmd_Latn data_files: - split: train path: kmd_Latn/_keep.jsonl - config_name: mim_Latn data_files: - split: train path: mim_Latn/_keep.jsonl - config_name: got_Latn data_files: - split: train path: got_Latn/_keep.jsonl - config_name: lbe_Latn data_files: - split: train path: lbe_Latn/_keep.jsonl - config_name: adi_Latn data_files: - split: train path: adi_Latn/_keep.jsonl - config_name: any_Latn data_files: - split: train path: any_Latn/_keep.jsonl - config_name: arp_Latn data_files: - split: train path: arp_Latn/_keep.jsonl - config_name: biu_Latn data_files: - split: train path: biu_Latn/_keep.jsonl - config_name: bvc_Latn data_files: - split: train path: bvc_Latn/_keep.jsonl - config_name: ghs_Latn data_files: - split: train path: ghs_Latn/_keep.jsonl - config_name: ttq_Latn data_files: - split: train path: ttq_Latn/_keep.jsonl - config_name: vmk_Latn data_files: - split: train path: vmk_Latn/_keep.jsonl - config_name: zpj_Latn data_files: - split: train path: zpj_Latn/_keep.jsonl - config_name: crl_Cans data_files: - split: train path: crl_Cans/_keep.jsonl - config_name: dtb_Latn data_files: - split: train path: dtb_Latn/_keep.jsonl - config_name: dug_Latn data_files: - split: train path: dug_Latn/_keep.jsonl - config_name: kam_Latn data_files: - split: train path: kam_Latn/_keep.jsonl - config_name: nmo_Latn data_files: - split: train path: nmo_Latn/_keep.jsonl - config_name: qva_Latn data_files: - split: train path: qva_Latn/_keep.jsonl - config_name: rhg_Latn data_files: - split: train path: rhg_Latn/_keep.jsonl - config_name: taw_Latn data_files: - split: train path: taw_Latn/_keep.jsonl - config_name: tui_Latn data_files: - split: train path: tui_Latn/_keep.jsonl - config_name: uth_Latn data_files: - split: train path: uth_Latn/_keep.jsonl - config_name: wap_Latn data_files: - split: train path: wap_Latn/_keep.jsonl - config_name: zpg_Latn data_files: - split: train path: zpg_Latn/_keep.jsonl - config_name: brb_Khmr data_files: - split: train path: brb_Khmr/_keep.jsonl - config_name: dty_Latn data_files: - split: train path: dty_Latn/_keep.jsonl - config_name: syr_Latn data_files: - split: train path: syr_Latn/_keep.jsonl - config_name: bih_Arab data_files: - split: train path: bih_Arab/_keep.jsonl - config_name: bqj_Latn data_files: - split: train path: bqj_Latn/_keep.jsonl - config_name: cjv_Latn data_files: - split: train path: cjv_Latn/_keep.jsonl - config_name: cnw_Latn data_files: - split: train path: cnw_Latn/_keep.jsonl - config_name: kgf_Latn data_files: - split: train path: kgf_Latn/_keep.jsonl - config_name: mfh_Latn data_files: - split: train path: mfh_Latn/_keep.jsonl - config_name: mns_Cyrl data_files: - split: train path: mns_Cyrl/_keep.jsonl - config_name: nnw_Latn data_files: - split: train path: nnw_Latn/_keep.jsonl - config_name: ntp_Latn data_files: - split: train path: ntp_Latn/_keep.jsonl - config_name: oto_Latn data_files: - split: train path: oto_Latn/_keep.jsonl - config_name: dks_Latn data_files: - split: train path: dks_Latn/_keep.jsonl - config_name: mpt_Latn data_files: - split: train path: mpt_Latn/_keep.jsonl - config_name: nmw_Latn data_files: - split: train path: nmw_Latn/_keep.jsonl - config_name: sba_Latn data_files: - split: train path: sba_Latn/_keep.jsonl - config_name: sfw_Latn data_files: - split: train path: sfw_Latn/_keep.jsonl - config_name: shu_Arab data_files: - split: train path: shu_Arab/_keep.jsonl - config_name: ury_Latn data_files: - split: train path: ury_Latn/_keep.jsonl - config_name: yrl_Latn data_files: - split: train path: yrl_Latn/_keep.jsonl - config_name: arc_Latn data_files: - split: train path: arc_Latn/_keep.jsonl - config_name: cmo_Khmr data_files: - split: train path: cmo_Khmr/_keep.jsonl - config_name: xkg_Latn data_files: - split: train path: xkg_Latn/_keep.jsonl - config_name: iqw_Latn data_files: - split: train path: iqw_Latn/_keep.jsonl - config_name: kpj_Latn data_files: - split: train path: kpj_Latn/_keep.jsonl - config_name: nfa_Latn data_files: - split: train path: nfa_Latn/_keep.jsonl - config_name: nph_Latn data_files: - split: train path: nph_Latn/_keep.jsonl - config_name: nre_Latn data_files: - split: train path: nre_Latn/_keep.jsonl - config_name: wsg_Telu data_files: - split: train path: wsg_Telu/_keep.jsonl - config_name: xsu_Latn data_files: - split: train path: xsu_Latn/_keep.jsonl - config_name: nut_Latn data_files: - split: train path: nut_Latn/_keep.jsonl - config_name: bmk_Latn data_files: - split: train path: bmk_Latn/_keep.jsonl - config_name: cdf_Latn data_files: - split: train path: cdf_Latn/_keep.jsonl - config_name: enl_Latn data_files: - split: train path: enl_Latn/_keep.jsonl - config_name: fuv_Arab data_files: - split: train path: fuv_Arab/_keep.jsonl - config_name: hop_Latn data_files: - split: train path: hop_Latn/_keep.jsonl - config_name: ife_Latn data_files: - split: train path: ife_Latn/_keep.jsonl - config_name: lnd_Latn data_files: - split: train path: lnd_Latn/_keep.jsonl - config_name: mrv_Latn data_files: - split: train path: mrv_Latn/_keep.jsonl - config_name: nzm_Latn data_files: - split: train path: nzm_Latn/_keep.jsonl - config_name: tem_Latn data_files: - split: train path: tem_Latn/_keep.jsonl - config_name: dwr_Ethi data_files: - split: train path: dwr_Ethi/_keep.jsonl - config_name: gwc_Arab data_files: - split: train path: gwc_Arab/_keep.jsonl - config_name: udi_Cyrl data_files: - split: train path: udi_Cyrl/_keep.jsonl - config_name: zha_Hani data_files: - split: train path: zha_Hani/_keep.jsonl - config_name: ajz_Latn data_files: - split: train path: ajz_Latn/_keep.jsonl - config_name: kru_Deva data_files: - split: train path: kru_Deva/_keep.jsonl - config_name: qvo_Latn data_files: - split: train path: qvo_Latn/_keep.jsonl - config_name: sld_Latn data_files: - split: train path: sld_Latn/_keep.jsonl - config_name: yup_Latn data_files: - split: train path: yup_Latn/_keep.jsonl - config_name: anp_Latn data_files: - split: train path: anp_Latn/_keep.jsonl - config_name: kwu_Latn data_files: - split: train path: kwu_Latn/_keep.jsonl - config_name: szy_Hani data_files: - split: train path: szy_Hani/_keep.jsonl - config_name: tdg_Deva data_files: - split: train path: tdg_Deva/_keep.jsonl - config_name: ade_Latn data_files: - split: train path: ade_Latn/_keep.jsonl - config_name: bcw_Latn data_files: - split: train path: bcw_Latn/_keep.jsonl - config_name: bgz_Latn data_files: - split: train path: bgz_Latn/_keep.jsonl - config_name: cul_Latn data_files: - split: train path: cul_Latn/_keep.jsonl - config_name: fmu_Deva data_files: - split: train path: fmu_Deva/_keep.jsonl - config_name: gvc_Latn data_files: - split: train path: gvc_Latn/_keep.jsonl - config_name: ktj_Latn data_files: - split: train path: ktj_Latn/_keep.jsonl - config_name: lis_Lisu data_files: - split: train path: lis_Lisu/_keep.jsonl - config_name: mev_Latn data_files: - split: train path: mev_Latn/_keep.jsonl - config_name: msc_Latn data_files: - split: train path: msc_Latn/_keep.jsonl - config_name: mta_Latn data_files: - split: train path: mta_Latn/_keep.jsonl - config_name: nbc_Latn data_files: - split: train path: nbc_Latn/_keep.jsonl - config_name: ncq_Laoo data_files: - split: train path: ncq_Laoo/_keep.jsonl - config_name: way_Latn data_files: - split: train path: way_Latn/_keep.jsonl - config_name: wlv_Latn data_files: - split: train path: wlv_Latn/_keep.jsonl - config_name: wlx_Latn data_files: - split: train path: wlx_Latn/_keep.jsonl - config_name: jmx_Latn data_files: - split: train path: jmx_Latn/_keep.jsonl - config_name: pli_Latn data_files: - split: train path: pli_Latn/_keep.jsonl - config_name: tkr_Cyrl data_files: - split: train path: tkr_Cyrl/_keep.jsonl - config_name: wni_Latn data_files: - split: train path: wni_Latn/_keep.jsonl - config_name: aim_Latn data_files: - split: train path: aim_Latn/_keep.jsonl - config_name: byv_Latn data_files: - split: train path: byv_Latn/_keep.jsonl - config_name: cgg_Latn data_files: - split: train path: cgg_Latn/_keep.jsonl - config_name: fud_Latn data_files: - split: train path: fud_Latn/_keep.jsonl - config_name: jmc_Latn data_files: - split: train path: jmc_Latn/_keep.jsonl - config_name: ker_Latn data_files: - split: train path: ker_Latn/_keep.jsonl - config_name: kia_Latn data_files: - split: train path: kia_Latn/_keep.jsonl - config_name: lom_Latn data_files: - split: train path: lom_Latn/_keep.jsonl - config_name: ojb_Latn data_files: - split: train path: ojb_Latn/_keep.jsonl - config_name: tnc_Latn data_files: - split: train path: tnc_Latn/_keep.jsonl - config_name: bwx_Latn data_files: - split: train path: bwx_Latn/_keep.jsonl - config_name: cre_Cans data_files: - split: train path: cre_Cans/_keep.jsonl - config_name: skr_Latn data_files: - split: train path: skr_Latn/_keep.jsonl - config_name: xal_Latn data_files: - split: train path: xal_Latn/_keep.jsonl - config_name: gjn_Latn data_files: - split: train path: gjn_Latn/_keep.jsonl - config_name: guq_Latn data_files: - split: train path: guq_Latn/_keep.jsonl - config_name: lap_Latn data_files: - split: train path: lap_Latn/_keep.jsonl - config_name: mip_Latn data_files: - split: train path: mip_Latn/_keep.jsonl - config_name: mkl_Latn data_files: - split: train path: mkl_Latn/_keep.jsonl - config_name: mtg_Latn data_files: - split: train path: mtg_Latn/_keep.jsonl - config_name: mzk_Latn data_files: - split: train path: mzk_Latn/_keep.jsonl - config_name: njm_Latn data_files: - split: train path: njm_Latn/_keep.jsonl - config_name: nse_Latn data_files: - split: train path: nse_Latn/_keep.jsonl - config_name: pne_Latn data_files: - split: train path: pne_Latn/_keep.jsonl - config_name: pww_Thai data_files: - split: train path: pww_Thai/_keep.jsonl - config_name: zam_Latn data_files: - split: train path: zam_Latn/_keep.jsonl - config_name: zca_Latn data_files: - split: train path: zca_Latn/_keep.jsonl - config_name: the_Deva data_files: - split: train path: the_Deva/_keep.jsonl - config_name: dis_Latn data_files: - split: train path: dis_Latn/_keep.jsonl - config_name: lgl_Latn data_files: - split: train path: lgl_Latn/_keep.jsonl - config_name: mbd_Latn data_files: - split: train path: mbd_Latn/_keep.jsonl - config_name: mda_Latn data_files: - split: train path: mda_Latn/_keep.jsonl - config_name: mhy_Latn data_files: - split: train path: mhy_Latn/_keep.jsonl - config_name: nst_Latn data_files: - split: train path: nst_Latn/_keep.jsonl - config_name: pkb_Latn data_files: - split: train path: pkb_Latn/_keep.jsonl - config_name: pmq_Latn data_files: - split: train path: pmq_Latn/_keep.jsonl - config_name: poe_Latn data_files: - split: train path: poe_Latn/_keep.jsonl - config_name: swk_Latn data_files: - split: train path: swk_Latn/_keep.jsonl - config_name: trs_Latn data_files: - split: train path: trs_Latn/_keep.jsonl - config_name: vot_Latn data_files: - split: train path: vot_Latn/_keep.jsonl - config_name: yam_Latn data_files: - split: train path: yam_Latn/_keep.jsonl - config_name: zpq_Latn data_files: - split: train path: zpq_Latn/_keep.jsonl - config_name: atq_Latn data_files: - split: train path: atq_Latn/_keep.jsonl - config_name: bav_Latn data_files: - split: train path: bav_Latn/_keep.jsonl - config_name: cho_Latn data_files: - split: train path: cho_Latn/_keep.jsonl - config_name: chq_Latn data_files: - split: train path: chq_Latn/_keep.jsonl - config_name: cjo_Latn data_files: - split: train path: cjo_Latn/_keep.jsonl - config_name: due_Latn data_files: - split: train path: due_Latn/_keep.jsonl - config_name: duo_Latn data_files: - split: train path: duo_Latn/_keep.jsonl - config_name: etu_Latn data_files: - split: train path: etu_Latn/_keep.jsonl - config_name: ifa_Latn data_files: - split: train path: ifa_Latn/_keep.jsonl - config_name: kby_Latn data_files: - split: train path: kby_Latn/_keep.jsonl - config_name: khq_Latn data_files: - split: train path: khq_Latn/_keep.jsonl - config_name: kno_Latn data_files: - split: train path: kno_Latn/_keep.jsonl - config_name: lem_Latn data_files: - split: train path: lem_Latn/_keep.jsonl - config_name: mcn_Latn data_files: - split: train path: mcn_Latn/_keep.jsonl - config_name: mkz_Latn data_files: - split: train path: mkz_Latn/_keep.jsonl - config_name: mnb_Latn data_files: - split: train path: mnb_Latn/_keep.jsonl - config_name: myb_Latn data_files: - split: train path: myb_Latn/_keep.jsonl - config_name: niy_Latn data_files: - split: train path: niy_Latn/_keep.jsonl - config_name: pxm_Latn data_files: - split: train path: pxm_Latn/_keep.jsonl - config_name: rub_Latn data_files: - split: train path: rub_Latn/_keep.jsonl - config_name: sju_Latn data_files: - split: train path: sju_Latn/_keep.jsonl - config_name: tmc_Latn data_files: - split: train path: tmc_Latn/_keep.jsonl - config_name: tpm_Latn data_files: - split: train path: tpm_Latn/_keep.jsonl - config_name: wob_Latn data_files: - split: train path: wob_Latn/_keep.jsonl - config_name: nxa_Latn data_files: - split: train path: nxa_Latn/_keep.jsonl - config_name: pnt_Latn data_files: - split: train path: pnt_Latn/_keep.jsonl - config_name: sdk_Latn data_files: - split: train path: sdk_Latn/_keep.jsonl - config_name: tcy_Latn data_files: - split: train path: tcy_Latn/_keep.jsonl - config_name: bhz_Latn data_files: - split: train path: bhz_Latn/_keep.jsonl - config_name: bth_Latn data_files: - split: train path: bth_Latn/_keep.jsonl - config_name: crj_Cans data_files: - split: train path: crj_Cans/_keep.jsonl - config_name: eka_Latn data_files: - split: train path: eka_Latn/_keep.jsonl - config_name: khy_Latn data_files: - split: train path: khy_Latn/_keep.jsonl - config_name: led_Latn data_files: - split: train path: led_Latn/_keep.jsonl - config_name: met_Latn data_files: - split: train path: met_Latn/_keep.jsonl - config_name: mgo_Latn data_files: - split: train path: mgo_Latn/_keep.jsonl - config_name: mus_Latn data_files: - split: train path: mus_Latn/_keep.jsonl - config_name: mzm_Latn data_files: - split: train path: mzm_Latn/_keep.jsonl - config_name: naw_Latn data_files: - split: train path: naw_Latn/_keep.jsonl - config_name: sri_Latn data_files: - split: train path: sri_Latn/_keep.jsonl - config_name: tbk_Latn data_files: - split: train path: tbk_Latn/_keep.jsonl - config_name: xbr_Latn data_files: - split: train path: xbr_Latn/_keep.jsonl - config_name: awa_Latn data_files: - split: train path: awa_Latn/_keep.jsonl - config_name: tnl_Latn data_files: - split: train path: tnl_Latn/_keep.jsonl - config_name: tnn_Latn data_files: - split: train path: tnn_Latn/_keep.jsonl - config_name: awb_Latn data_files: - split: train path: awb_Latn/_keep.jsonl - config_name: bsc_Latn data_files: - split: train path: bsc_Latn/_keep.jsonl - config_name: iri_Latn data_files: - split: train path: iri_Latn/_keep.jsonl - config_name: kpq_Latn data_files: - split: train path: kpq_Latn/_keep.jsonl - config_name: ktm_Latn data_files: - split: train path: ktm_Latn/_keep.jsonl - config_name: loe_Latn data_files: - split: train path: loe_Latn/_keep.jsonl - config_name: lun_Latn data_files: - split: train path: lun_Latn/_keep.jsonl - config_name: mfg_Latn data_files: - split: train path: mfg_Latn/_keep.jsonl - config_name: moa_Latn data_files: - split: train path: moa_Latn/_keep.jsonl - config_name: ndj_Latn data_files: - split: train path: ndj_Latn/_keep.jsonl - config_name: otn_Latn data_files: - split: train path: otn_Latn/_keep.jsonl - config_name: sjo_Mong data_files: - split: train path: sjo_Mong/_keep.jsonl - config_name: wat_Latn data_files: - split: train path: wat_Latn/_keep.jsonl - config_name: bkm_Latn data_files: - split: train path: bkm_Latn/_keep.jsonl - config_name: tuz_Latn data_files: - split: train path: tuz_Latn/_keep.jsonl - config_name: ybi_Deva data_files: - split: train path: ybi_Deva/_keep.jsonl - config_name: gbr_Latn data_files: - split: train path: gbr_Latn/_keep.jsonl - config_name: gej_Latn data_files: - split: train path: gej_Latn/_keep.jsonl - config_name: giz_Latn data_files: - split: train path: giz_Latn/_keep.jsonl - config_name: gna_Latn data_files: - split: train path: gna_Latn/_keep.jsonl - config_name: gwr_Latn data_files: - split: train path: gwr_Latn/_keep.jsonl - config_name: kex_Deva data_files: - split: train path: kex_Deva/_keep.jsonl - config_name: kle_Deva data_files: - split: train path: kle_Deva/_keep.jsonl - config_name: knx_Latn data_files: - split: train path: knx_Latn/_keep.jsonl - config_name: ktz_Latn data_files: - split: train path: ktz_Latn/_keep.jsonl - config_name: kvj_Latn data_files: - split: train path: kvj_Latn/_keep.jsonl - config_name: lob_Latn data_files: - split: train path: lob_Latn/_keep.jsonl - config_name: mhw_Latn data_files: - split: train path: mhw_Latn/_keep.jsonl - config_name: mph_Latn data_files: - split: train path: mph_Latn/_keep.jsonl - config_name: pmx_Latn data_files: - split: train path: pmx_Latn/_keep.jsonl - config_name: qus_Latn data_files: - split: train path: qus_Latn/_keep.jsonl - config_name: tcc_Latn data_files: - split: train path: tcc_Latn/_keep.jsonl - config_name: ang_Runr data_files: - split: train path: ang_Runr/_keep.jsonl - config_name: azn_Latn data_files: - split: train path: azn_Latn/_keep.jsonl - config_name: bra_Deva data_files: - split: train path: bra_Deva/_keep.jsonl - config_name: gal_Latn data_files: - split: train path: gal_Latn/_keep.jsonl - config_name: jra_Khmr data_files: - split: train path: jra_Khmr/_keep.jsonl - config_name: nlv_Latn data_files: - split: train path: nlv_Latn/_keep.jsonl - config_name: rki_Latn data_files: - split: train path: rki_Latn/_keep.jsonl - config_name: stk_Latn data_files: - split: train path: stk_Latn/_keep.jsonl - config_name: yux_Cyrl data_files: - split: train path: yux_Cyrl/_keep.jsonl - config_name: dip_Latn data_files: - split: train path: dip_Latn/_keep.jsonl - config_name: ivv_Latn data_files: - split: train path: ivv_Latn/_keep.jsonl - config_name: kdj_Latn data_files: - split: train path: kdj_Latn/_keep.jsonl - config_name: kff_Telu data_files: - split: train path: kff_Telu/_keep.jsonl - config_name: kyu_Kali data_files: - split: train path: kyu_Kali/_keep.jsonl - config_name: mnf_Latn data_files: - split: train path: mnf_Latn/_keep.jsonl - config_name: moc_Latn data_files: - split: train path: moc_Latn/_keep.jsonl - config_name: mpg_Latn data_files: - split: train path: mpg_Latn/_keep.jsonl - config_name: mua_Latn data_files: - split: train path: mua_Latn/_keep.jsonl - config_name: nma_Latn data_files: - split: train path: nma_Latn/_keep.jsonl - config_name: rim_Latn data_files: - split: train path: rim_Latn/_keep.jsonl - config_name: rjs_Deva data_files: - split: train path: rjs_Deva/_keep.jsonl - config_name: rnl_Latn data_files: - split: train path: rnl_Latn/_keep.jsonl - config_name: ssx_Latn data_files: - split: train path: ssx_Latn/_keep.jsonl - config_name: tig_Ethi data_files: - split: train path: tig_Ethi/_keep.jsonl - config_name: urw_Latn data_files: - split: train path: urw_Latn/_keep.jsonl - config_name: idt_Latn data_files: - split: train path: idt_Latn/_keep.jsonl - config_name: mrn_Latn data_files: - split: train path: mrn_Latn/_keep.jsonl - config_name: oki_Latn data_files: - split: train path: oki_Latn/_keep.jsonl - config_name: bbk_Latn data_files: - split: train path: bbk_Latn/_keep.jsonl - config_name: bea_Latn data_files: - split: train path: bea_Latn/_keep.jsonl - config_name: bkq_Latn data_files: - split: train path: bkq_Latn/_keep.jsonl - config_name: btt_Latn data_files: - split: train path: btt_Latn/_keep.jsonl - config_name: cou_Latn data_files: - split: train path: cou_Latn/_keep.jsonl - config_name: ddn_Latn data_files: - split: train path: ddn_Latn/_keep.jsonl - config_name: did_Latn data_files: - split: train path: did_Latn/_keep.jsonl - config_name: diu_Latn data_files: - split: train path: diu_Latn/_keep.jsonl - config_name: ilb_Latn data_files: - split: train path: ilb_Latn/_keep.jsonl - config_name: ksj_Latn data_files: - split: train path: ksj_Latn/_keep.jsonl - config_name: lhi_Latn data_files: - split: train path: lhi_Latn/_keep.jsonl - config_name: ndi_Latn data_files: - split: train path: ndi_Latn/_keep.jsonl - config_name: ngb_Latn data_files: - split: train path: ngb_Latn/_keep.jsonl - config_name: njz_Latn data_files: - split: train path: njz_Latn/_keep.jsonl - config_name: nmz_Latn data_files: - split: train path: nmz_Latn/_keep.jsonl - config_name: npo_Latn data_files: - split: train path: npo_Latn/_keep.jsonl - config_name: nwb_Latn data_files: - split: train path: nwb_Latn/_keep.jsonl - config_name: pbi_Latn data_files: - split: train path: pbi_Latn/_keep.jsonl - config_name: sbd_Latn data_files: - split: train path: sbd_Latn/_keep.jsonl - config_name: soe_Latn data_files: - split: train path: soe_Latn/_keep.jsonl - config_name: tpw_Latn data_files: - split: train path: tpw_Latn/_keep.jsonl - config_name: twb_Latn data_files: - split: train path: twb_Latn/_keep.jsonl - config_name: bfn_Latn data_files: - split: train path: bfn_Latn/_keep.jsonl - config_name: boz_Latn data_files: - split: train path: boz_Latn/_keep.jsonl - config_name: lwl_Thai data_files: - split: train path: lwl_Thai/_keep.jsonl - config_name: psp_Latn data_files: - split: train path: psp_Latn/_keep.jsonl - config_name: sgd_Latn data_files: - split: train path: sgd_Latn/_keep.jsonl - config_name: ymp_Latn data_files: - split: train path: ymp_Latn/_keep.jsonl - config_name: bkl_Latn data_files: - split: train path: bkl_Latn/_keep.jsonl - config_name: bkv_Latn data_files: - split: train path: bkv_Latn/_keep.jsonl - config_name: csk_Latn data_files: - split: train path: csk_Latn/_keep.jsonl - config_name: enx_Latn data_files: - split: train path: enx_Latn/_keep.jsonl - config_name: ess_Latn data_files: - split: train path: ess_Latn/_keep.jsonl - config_name: gof_Ethi data_files: - split: train path: gof_Ethi/_keep.jsonl - config_name: gud_Latn data_files: - split: train path: gud_Latn/_keep.jsonl - config_name: guu_Latn data_files: - split: train path: guu_Latn/_keep.jsonl - config_name: kdh_Latn data_files: - split: train path: kdh_Latn/_keep.jsonl - config_name: krx_Latn data_files: - split: train path: krx_Latn/_keep.jsonl - config_name: kzn_Latn data_files: - split: train path: kzn_Latn/_keep.jsonl - config_name: maf_Latn data_files: - split: train path: maf_Latn/_keep.jsonl - config_name: max_Latn data_files: - split: train path: max_Latn/_keep.jsonl - config_name: mgc_Latn data_files: - split: train path: mgc_Latn/_keep.jsonl - config_name: mvn_Latn data_files: - split: train path: mvn_Latn/_keep.jsonl - config_name: mwm_Latn data_files: - split: train path: mwm_Latn/_keep.jsonl - config_name: nbe_Latn data_files: - split: train path: nbe_Latn/_keep.jsonl - config_name: nlc_Latn data_files: - split: train path: nlc_Latn/_keep.jsonl - config_name: nxd_Latn data_files: - split: train path: nxd_Latn/_keep.jsonl - config_name: pse_Latn data_files: - split: train path: pse_Latn/_keep.jsonl - config_name: sbs_Latn data_files: - split: train path: sbs_Latn/_keep.jsonl - config_name: tlb_Latn data_files: - split: train path: tlb_Latn/_keep.jsonl - config_name: wwa_Latn data_files: - split: train path: wwa_Latn/_keep.jsonl - config_name: yim_Latn data_files: - split: train path: yim_Latn/_keep.jsonl - config_name: bkx_Latn data_files: - split: train path: bkx_Latn/_keep.jsonl - config_name: bze_Latn data_files: - split: train path: bze_Latn/_keep.jsonl - config_name: chu_Latn data_files: - split: train path: chu_Latn/_keep.jsonl - config_name: kbq_Latn data_files: - split: train path: kbq_Latn/_keep.jsonl - config_name: kpy_Armn data_files: - split: train path: kpy_Armn/_keep.jsonl - config_name: mry_Latn data_files: - split: train path: mry_Latn/_keep.jsonl - config_name: tkd_Latn data_files: - split: train path: tkd_Latn/_keep.jsonl - config_name: ybh_Deva data_files: - split: train path: ybh_Deva/_keep.jsonl - config_name: abi_Latn data_files: - split: train path: abi_Latn/_keep.jsonl - config_name: ayo_Latn data_files: - split: train path: ayo_Latn/_keep.jsonl - config_name: bex_Latn data_files: - split: train path: bex_Latn/_keep.jsonl - config_name: bom_Latn data_files: - split: train path: bom_Latn/_keep.jsonl - config_name: bov_Latn data_files: - split: train path: bov_Latn/_keep.jsonl - config_name: dhg_Latn data_files: - split: train path: dhg_Latn/_keep.jsonl - config_name: jaa_Latn data_files: - split: train path: jaa_Latn/_keep.jsonl - config_name: kqs_Latn data_files: - split: train path: kqs_Latn/_keep.jsonl - config_name: kqy_Ethi data_files: - split: train path: kqy_Ethi/_keep.jsonl - config_name: ksb_Latn data_files: - split: train path: ksb_Latn/_keep.jsonl - config_name: ldn_Latn data_files: - split: train path: ldn_Latn/_keep.jsonl - config_name: log_Latn data_files: - split: train path: log_Latn/_keep.jsonl - config_name: lol_Latn data_files: - split: train path: lol_Latn/_keep.jsonl - config_name: mfk_Latn data_files: - split: train path: mfk_Latn/_keep.jsonl - config_name: mtj_Latn data_files: - split: train path: mtj_Latn/_keep.jsonl - config_name: ndz_Latn data_files: - split: train path: ndz_Latn/_keep.jsonl - config_name: ngc_Latn data_files: - split: train path: ngc_Latn/_keep.jsonl - config_name: nio_Cyrl data_files: - split: train path: nio_Cyrl/_keep.jsonl - config_name: nri_Latn data_files: - split: train path: nri_Latn/_keep.jsonl - config_name: nuz_Latn data_files: - split: train path: nuz_Latn/_keep.jsonl - config_name: pps_Latn data_files: - split: train path: pps_Latn/_keep.jsonl - config_name: shk_Latn data_files: - split: train path: shk_Latn/_keep.jsonl - config_name: tlj_Latn data_files: - split: train path: tlj_Latn/_keep.jsonl - config_name: vut_Latn data_files: - split: train path: vut_Latn/_keep.jsonl - config_name: xnn_Latn data_files: - split: train path: xnn_Latn/_keep.jsonl - config_name: bcc_Arab data_files: - split: train path: bcc_Arab/_keep.jsonl - config_name: cuh_Latn data_files: - split: train path: cuh_Latn/_keep.jsonl - config_name: emp_Cyrl data_files: - split: train path: emp_Cyrl/_keep.jsonl - config_name: hro_Latn data_files: - split: train path: hro_Latn/_keep.jsonl - config_name: nco_Latn data_files: - split: train path: nco_Latn/_keep.jsonl - config_name: nxl_Latn data_files: - split: train path: nxl_Latn/_keep.jsonl - config_name: pex_Latn data_files: - split: train path: pex_Latn/_keep.jsonl - config_name: tnp_Latn data_files: - split: train path: tnp_Latn/_keep.jsonl - config_name: trv_Hani data_files: - split: train path: trv_Hani/_keep.jsonl - config_name: vif_Latn data_files: - split: train path: vif_Latn/_keep.jsonl - config_name: aha_Latn data_files: - split: train path: aha_Latn/_keep.jsonl - config_name: avn_Latn data_files: - split: train path: avn_Latn/_keep.jsonl - config_name: bmv_Latn data_files: - split: train path: bmv_Latn/_keep.jsonl - config_name: chj_Latn data_files: - split: train path: chj_Latn/_keep.jsonl - config_name: crt_Latn data_files: - split: train path: crt_Latn/_keep.jsonl - config_name: dos_Latn data_files: - split: train path: dos_Latn/_keep.jsonl - config_name: eto_Latn data_files: - split: train path: eto_Latn/_keep.jsonl - config_name: gya_Latn data_files: - split: train path: gya_Latn/_keep.jsonl - config_name: hlt_Latn data_files: - split: train path: hlt_Latn/_keep.jsonl - config_name: jun_Orya data_files: - split: train path: jun_Orya/_keep.jsonl - config_name: ktb_Ethi data_files: - split: train path: ktb_Ethi/_keep.jsonl - config_name: lgm_Latn data_files: - split: train path: lgm_Latn/_keep.jsonl - config_name: mnx_Latn data_files: - split: train path: mnx_Latn/_keep.jsonl - config_name: mor_Latn data_files: - split: train path: mor_Latn/_keep.jsonl - config_name: mug_Latn data_files: - split: train path: mug_Latn/_keep.jsonl - config_name: nng_Latn data_files: - split: train path: nng_Latn/_keep.jsonl - config_name: nnh_Latn data_files: - split: train path: nnh_Latn/_keep.jsonl - config_name: nsa_Latn data_files: - split: train path: nsa_Latn/_keep.jsonl - config_name: nyk_Latn data_files: - split: train path: nyk_Latn/_keep.jsonl - config_name: otd_Latn data_files: - split: train path: otd_Latn/_keep.jsonl - config_name: oym_Latn data_files: - split: train path: oym_Latn/_keep.jsonl - config_name: phm_Latn data_files: - split: train path: phm_Latn/_keep.jsonl - config_name: prq_Latn data_files: - split: train path: prq_Latn/_keep.jsonl - config_name: saj_Latn data_files: - split: train path: saj_Latn/_keep.jsonl - config_name: szb_Latn data_files: - split: train path: szb_Latn/_keep.jsonl - config_name: tap_Latn data_files: - split: train path: tap_Latn/_keep.jsonl - config_name: tnr_Latn data_files: - split: train path: tnr_Latn/_keep.jsonl - config_name: tzl_Latn data_files: - split: train path: tzl_Latn/_keep.jsonl - config_name: wew_Latn data_files: - split: train path: wew_Latn/_keep.jsonl - config_name: yas_Latn data_files: - split: train path: yas_Latn/_keep.jsonl - config_name: yuz_Latn data_files: - split: train path: yuz_Latn/_keep.jsonl - config_name: avk_Cyrl data_files: - split: train path: avk_Cyrl/_keep.jsonl - config_name: bat_Cyrl data_files: - split: train path: bat_Cyrl/_keep.jsonl - config_name: baw_Latn data_files: - split: train path: baw_Latn/_keep.jsonl - config_name: bwt_Latn data_files: - split: train path: bwt_Latn/_keep.jsonl - config_name: bxa_Latn data_files: - split: train path: bxa_Latn/_keep.jsonl - config_name: cjs_Latn data_files: - split: train path: cjs_Latn/_keep.jsonl - config_name: csw_Cans data_files: - split: train path: csw_Cans/_keep.jsonl - config_name: fli_Latn data_files: - split: train path: fli_Latn/_keep.jsonl - config_name: kqr_Latn data_files: - split: train path: kqr_Latn/_keep.jsonl - config_name: lan_Latn data_files: - split: train path: lan_Latn/_keep.jsonl - config_name: lgr_Latn data_files: - split: train path: lgr_Latn/_keep.jsonl - config_name: lhm_Deva data_files: - split: train path: lhm_Deva/_keep.jsonl - config_name: mlk_Latn data_files: - split: train path: mlk_Latn/_keep.jsonl - config_name: mve_Arab data_files: - split: train path: mve_Arab/_keep.jsonl - config_name: nqo_Latn data_files: - split: train path: nqo_Latn/_keep.jsonl - config_name: odk_Arab data_files: - split: train path: odk_Arab/_keep.jsonl - config_name: olo_Cyrl data_files: - split: train path: olo_Cyrl/_keep.jsonl - config_name: otq_Arab data_files: - split: train path: otq_Arab/_keep.jsonl - config_name: pea_Latn data_files: - split: train path: pea_Latn/_keep.jsonl - config_name: saq_Latn data_files: - split: train path: saq_Latn/_keep.jsonl - config_name: sea_Latn data_files: - split: train path: sea_Latn/_keep.jsonl - config_name: sps_Latn data_files: - split: train path: sps_Latn/_keep.jsonl - config_name: tio_Latn data_files: - split: train path: tio_Latn/_keep.jsonl - config_name: yin_Latn data_files: - split: train path: yin_Latn/_keep.jsonl - config_name: adl_Latn data_files: - split: train path: adl_Latn/_keep.jsonl - config_name: agw_Latn data_files: - split: train path: agw_Latn/_keep.jsonl - config_name: ald_Latn data_files: - split: train path: ald_Latn/_keep.jsonl - config_name: asg_Latn data_files: - split: train path: asg_Latn/_keep.jsonl - config_name: bnj_Latn data_files: - split: train path: bnj_Latn/_keep.jsonl - config_name: brx_Latn data_files: - split: train path: brx_Latn/_keep.jsonl - config_name: bwi_Latn data_files: - split: train path: bwi_Latn/_keep.jsonl - config_name: bwq_Latn data_files: - split: train path: bwq_Latn/_keep.jsonl - config_name: dbq_Latn data_files: - split: train path: dbq_Latn/_keep.jsonl - config_name: dow_Latn data_files: - split: train path: dow_Latn/_keep.jsonl - config_name: fad_Latn data_files: - split: train path: fad_Latn/_keep.jsonl - config_name: hoc_Latn data_files: - split: train path: hoc_Latn/_keep.jsonl - config_name: kql_Latn data_files: - split: train path: kql_Latn/_keep.jsonl - config_name: ksf_Latn data_files: - split: train path: ksf_Latn/_keep.jsonl - config_name: kyu_Mymr data_files: - split: train path: kyu_Mymr/_keep.jsonl - config_name: lea_Latn data_files: - split: train path: lea_Latn/_keep.jsonl - config_name: mse_Latn data_files: - split: train path: mse_Latn/_keep.jsonl - config_name: mzl_Latn data_files: - split: train path: mzl_Latn/_keep.jsonl - config_name: nhd_Latn data_files: - split: train path: nhd_Latn/_keep.jsonl - config_name: nnl_Latn data_files: - split: train path: nnl_Latn/_keep.jsonl - config_name: nwx_Deva data_files: - split: train path: nwx_Deva/_keep.jsonl - config_name: pbc_Latn data_files: - split: train path: pbc_Latn/_keep.jsonl - config_name: pny_Latn data_files: - split: train path: pny_Latn/_keep.jsonl - config_name: tul_Latn data_files: - split: train path: tul_Latn/_keep.jsonl - config_name: aaa_Latn data_files: - split: train path: aaa_Latn/_keep.jsonl - config_name: abc_Latn data_files: - split: train path: abc_Latn/_keep.jsonl - config_name: agq_Latn data_files: - split: train path: agq_Latn/_keep.jsonl - config_name: ags_Latn data_files: - split: train path: ags_Latn/_keep.jsonl - config_name: azo_Latn data_files: - split: train path: azo_Latn/_keep.jsonl - config_name: bag_Latn data_files: - split: train path: bag_Latn/_keep.jsonl - config_name: bax_Latn data_files: - split: train path: bax_Latn/_keep.jsonl - config_name: bce_Latn data_files: - split: train path: bce_Latn/_keep.jsonl - config_name: bfm_Latn data_files: - split: train path: bfm_Latn/_keep.jsonl - config_name: bgf_Latn data_files: - split: train path: bgf_Latn/_keep.jsonl - config_name: bhs_Latn data_files: - split: train path: bhs_Latn/_keep.jsonl - config_name: bkc_Latn data_files: - split: train path: bkc_Latn/_keep.jsonl - config_name: bkh_Latn data_files: - split: train path: bkh_Latn/_keep.jsonl - config_name: blk_Latn data_files: - split: train path: blk_Latn/_keep.jsonl - config_name: bob_Latn data_files: - split: train path: bob_Latn/_keep.jsonl - config_name: bqm_Latn data_files: - split: train path: bqm_Latn/_keep.jsonl - config_name: bri_Latn data_files: - split: train path: bri_Latn/_keep.jsonl - config_name: brv_Laoo data_files: - split: train path: brv_Laoo/_keep.jsonl - config_name: buo_Latn data_files: - split: train path: buo_Latn/_keep.jsonl - config_name: bya_Latn data_files: - split: train path: bya_Latn/_keep.jsonl - config_name: chp_Cans data_files: - split: train path: chp_Cans/_keep.jsonl - config_name: cim_Latn data_files: - split: train path: cim_Latn/_keep.jsonl - config_name: clo_Latn data_files: - split: train path: clo_Latn/_keep.jsonl - config_name: cuv_Latn data_files: - split: train path: cuv_Latn/_keep.jsonl - config_name: dag_Arab data_files: - split: train path: dag_Arab/_keep.jsonl - config_name: dmg_Latn data_files: - split: train path: dmg_Latn/_keep.jsonl - config_name: dtr_Latn data_files: - split: train path: dtr_Latn/_keep.jsonl - config_name: eee_Thai data_files: - split: train path: eee_Thai/_keep.jsonl - config_name: ekm_Latn data_files: - split: train path: ekm_Latn/_keep.jsonl - config_name: enc_Latn data_files: - split: train path: enc_Latn/_keep.jsonl - config_name: fiu_Cyrl data_files: - split: train path: fiu_Cyrl/_keep.jsonl - config_name: gbj_Orya data_files: - split: train path: gbj_Orya/_keep.jsonl - config_name: gou_Latn data_files: - split: train path: gou_Latn/_keep.jsonl - config_name: hao_Latn data_files: - split: train path: hao_Latn/_keep.jsonl - config_name: hna_Latn data_files: - split: train path: hna_Latn/_keep.jsonl - config_name: hre_Latn data_files: - split: train path: hre_Latn/_keep.jsonl - config_name: isu_Latn data_files: - split: train path: isu_Latn/_keep.jsonl - config_name: jgo_Latn data_files: - split: train path: jgo_Latn/_keep.jsonl - config_name: kbx_Latn data_files: - split: train path: kbx_Latn/_keep.jsonl - config_name: kvt_Latn data_files: - split: train path: kvt_Latn/_keep.jsonl - config_name: kxp_Arab data_files: - split: train path: kxp_Arab/_keep.jsonl - config_name: lfa_Latn data_files: - split: train path: lfa_Latn/_keep.jsonl - config_name: lkb_Latn data_files: - split: train path: lkb_Latn/_keep.jsonl - config_name: lns_Latn data_files: - split: train path: lns_Latn/_keep.jsonl - config_name: loh_Latn data_files: - split: train path: loh_Latn/_keep.jsonl - config_name: lrc_Latn data_files: - split: train path: lrc_Latn/_keep.jsonl - config_name: lts_Latn data_files: - split: train path: lts_Latn/_keep.jsonl - config_name: luy_Latn data_files: - split: train path: luy_Latn/_keep.jsonl - config_name: mdr_Latn data_files: - split: train path: mdr_Latn/_keep.jsonl - config_name: mfj_Latn data_files: - split: train path: mfj_Latn/_keep.jsonl - config_name: mgg_Latn data_files: - split: train path: mgg_Latn/_keep.jsonl - config_name: mgq_Latn data_files: - split: train path: mgq_Latn/_keep.jsonl - config_name: mle_Latn data_files: - split: train path: mle_Latn/_keep.jsonl - config_name: mlw_Latn data_files: - split: train path: mlw_Latn/_keep.jsonl - config_name: mmu_Latn data_files: - split: train path: mmu_Latn/_keep.jsonl - config_name: mne_Latn data_files: - split: train path: mne_Latn/_keep.jsonl - config_name: muv_Mlym data_files: - split: train path: muv_Mlym/_keep.jsonl - config_name: mxu_Latn data_files: - split: train path: mxu_Latn/_keep.jsonl - config_name: nge_Latn data_files: - split: train path: nge_Latn/_keep.jsonl - config_name: ngn_Latn data_files: - split: train path: ngn_Latn/_keep.jsonl - config_name: njy_Latn data_files: - split: train path: njy_Latn/_keep.jsonl - config_name: nsk_Cans data_files: - split: train path: nsk_Cans/_keep.jsonl - config_name: nsk_Latn data_files: - split: train path: nsk_Latn/_keep.jsonl - config_name: nwe_Latn data_files: - split: train path: nwe_Latn/_keep.jsonl - config_name: nza_Latn data_files: - split: train path: nza_Latn/_keep.jsonl - config_name: pcg_Mlym data_files: - split: train path: pcg_Mlym/_keep.jsonl - config_name: pdu_Latn data_files: - split: train path: pdu_Latn/_keep.jsonl - config_name: pnz_Latn data_files: - split: train path: pnz_Latn/_keep.jsonl - config_name: pwg_Latn data_files: - split: train path: pwg_Latn/_keep.jsonl - config_name: qaa_Latn data_files: - split: train path: qaa_Latn/_keep.jsonl - config_name: shi_Arab data_files: - split: train path: shi_Arab/_keep.jsonl - config_name: smn_Cyrl data_files: - split: train path: smn_Cyrl/_keep.jsonl - config_name: snk_Arab data_files: - split: train path: snk_Arab/_keep.jsonl - config_name: snl_Latn data_files: - split: train path: snl_Latn/_keep.jsonl - config_name: sox_Latn data_files: - split: train path: sox_Latn/_keep.jsonl - config_name: ssn_Latn data_files: - split: train path: ssn_Latn/_keep.jsonl - config_name: syw_Deva data_files: - split: train path: syw_Deva/_keep.jsonl - config_name: tay_Hani data_files: - split: train path: tay_Hani/_keep.jsonl - config_name: tbj_Latn data_files: - split: train path: tbj_Latn/_keep.jsonl - config_name: tdb_Deva data_files: - split: train path: tdb_Deva/_keep.jsonl - config_name: thy_Thai data_files: - split: train path: thy_Thai/_keep.jsonl - config_name: tnt_Latn data_files: - split: train path: tnt_Latn/_keep.jsonl - config_name: tom_Latn data_files: - split: train path: tom_Latn/_keep.jsonl - config_name: tpl_Latn data_files: - split: train path: tpl_Latn/_keep.jsonl - config_name: tsb_Latn data_files: - split: train path: tsb_Latn/_keep.jsonl - config_name: tvs_Latn data_files: - split: train path: tvs_Latn/_keep.jsonl - config_name: udg_Mlym data_files: - split: train path: udg_Mlym/_keep.jsonl - config_name: unr_Orya data_files: - split: train path: unr_Orya/_keep.jsonl - config_name: wbr_Deva data_files: - split: train path: wbr_Deva/_keep.jsonl - config_name: wms_Latn data_files: - split: train path: wms_Latn/_keep.jsonl - config_name: wnk_Latn data_files: - split: train path: wnk_Latn/_keep.jsonl - config_name: wtk_Latn data_files: - split: train path: wtk_Latn/_keep.jsonl - config_name: xmd_Latn data_files: - split: train path: xmd_Latn/_keep.jsonl - config_name: xmg_Latn data_files: - split: train path: xmg_Latn/_keep.jsonl - config_name: xty_Latn data_files: - split: train path: xty_Latn/_keep.jsonl - config_name: yav_Latn data_files: - split: train path: yav_Latn/_keep.jsonl - config_name: yea_Mlym data_files: - split: train path: yea_Mlym/_keep.jsonl - config_name: zuh_Latn data_files: - split: train path: zuh_Latn/_keep.jsonl language: - eng - rus - cmn - deu - spa - fra - jpn - ita - por - pol - nld - ind - tur - vie - fas - kor - swe - hun - ell - ukr - tha - aze - arb - slv - cat - fin - hbs - ces - fil - guj - nob - mal - bul - kan - hin - tam - ara - kaz - sqi - pan - est - srp - heb - isl - mlt - mkd - bos - lit - kat - hrv - ben - glg - ceb - ron - msa - hye - tgk - mar - bel - nep - urd - slk - mon - swa - dan - eus - azj - sin - lat - als - tel - afr - ekk - ltz - zsm - som - cym - und - kir - nor - uzb - mya - epo - hau - ary - gle - lvs - nno - und - ory - amh - tat - khm - und - und - und - arz - pus - lav - hbs - und - war - und - mlg - uzn - hat - zul - kur - tgl - uzb - div - und - fry - sna - und - fao - sun - und - und - snd - cos - bak - ckb - asm - und - jpn - ast - ibo - mri - und - ars - und - anp - khk - und - lao - ori - und - yid - hmn - jav - nya - und - und - und - tir - uig - wln - und - yor - swh - gla - xho - uzn - bre - sot - che - nan - tel - bew - glk - smo - orm - zho - haw - pnb - und - oci - chv - kin - und - srp - und - und - pcm - kaa - lug - pbt - aze - gsw - min - tuk - lim - kmr - und - roh - und - und - vec - san - und - gmh - nds - sco - und - und - azb - tsn - rus - und - mon - und - tgk - sah - pri - pap - plt - lmo - bod - und - yue - und - und - und - bar - und - hif - und - arg - pms - kat - nrm - vol - aeb - und - und - ido - pam - kal - und - und - und - lus - und - und - und - new - sme - und - und - nso - lld - ina - scn - und - und - und - hyw - abk - bew - und - und - bpy - tgk - lin - oss - que - szl - sdh - mww - mhr - und - und - und - rmy - diq - srd - und - und - ydd - und - run - und - hsb - und - wol - und - urd - und - kiu - ilo - und - cak - und - acm - und - und - grc - xmf - vls - und - und - tso - crh - nav - mwl - und - tat - grn - mui - hin - mvf - udm - mzn - und - und - und - bcl - und - und - ban - und - afb - und - cnh - und - cbk - kaa - tyv - kur - ful - und - zea - frp - frr - pfl - lij - apc - mai - und - und - pon - bak - eml - uzs - nde - hil - mam - gom - dag - nap - bjn - und - hbo - tet - inh - ven - gaz - tpi - und - ajp - sat - wuu - bam - vep - glv - tzo - bik - und - acr - twi - myv - ewe - poh - und - ile - rue - und - und - ace - kha - und - und - und - und - ksh - hui - gor - krc - lfn - tls - fur - und - gag - chk - hmo - kek - fon - ssw - quh - meu - csb - ksd - ext - rop - und - aln - kab - shn - tbz - knv - bqc - und - und - npi - rug - und - kom - kpg - kbd - dzo - wal - zlm - und - mzh - pan - hac - und - tum - sgs - fij - tuc - und - und - jbo - iba - pcd - kjh - ixl - und - und - und - ndo - suz - und - und - mfe - bxr - ava - und - bho - brh - und - ctd - aym - ady - nbl - gom - hus - gug - und - und - bat - guj - hne - srn - ctu - san - ton - bug - aoj - jam - und - lez - xav - luo - ltg - bih - uig - mrj - avk - kos - kbp - alt - cfm - goh - lad - und - cor - quc - und - kpv - und - aka - und - hak - rmn - pls - sag - min - und - rcf - som - gym - und - kik - pag - arn - und - ngu - dsb - tca - mni - naq - pdc - mps - und - olo - fro - fit - crh - cdo - kac - mdf - mad - cab - srm - toj - zai - guc - smn - ote - nch - und - prs - tuk - bis - cuk - bzj - map - djk - ncj - und - mco - shp - und - ang - seh - ikk - qvi - yom - top - awa - ike - mau - kum - mos - tly - und - ayr - tdt - yap - evn - tah - xal - szy - quw - stq - tlh - otq - und - nov - skr - yua - raw - und - fiu - enm - bbc - und - non - und - ber - kea - uig - bua - kua - zza - csy - mnw - dtp - nah - yao - azj - hau - nog - abt - meo - ame - mbf - chm - arb - kas - tam - crs - tcy - lbe - cni - ben - rom - zom - blk - efi - ada - und - koi - und - bbj - trv - ach - mgh - kas - gcr - krl - iso - lki - atj - cmo - chu - gur - mni - iku - sma - lrc - gos - dty - nzi - btx - brx - bts - nyu - ckt - guw - pck - quy - gcf - ksw - nia - bal - nhe - hwc - mup - dyu - ami - tay - gaa - loz - abq - pnt - snd - ium - abs - cmr - shi - tzm - gil - ewo - kon - sms - ape - tzh - bci - acd - tab - fuv - swc - tcz - und - sgc - aaz - tly - tvl - zha - pib - pli - bru - quz - cha - aeu - bjn - nqo - mer - acf - rmc - msi - smj - kng - dhv - doi - zap - hla - cac - pdt - mbt - taq - bgp - tyz - aau - mah - nak - kmb - mjw - fuf - bba - ron - amu - alz - cop - rar - emp - arc - nyn - rut - lub - tzj - fat - lzh - aak - nnb - lhu - bjv - bum - maq - roa - bvr - kcg - tok - yrk - khs - rup - tuk - qub - jac - hmr - sid - chr - amp - qug - mas - fkv - mal - bem - cav - her - kwn - ify - asm - gpe - zpa - agu - ppk - tiv - npi - ahk - pis - hns - sus - hak - bon - sja - kas - mar - kri - dik - wrk - got - dar - gui - mak - jiv - kjb - maz - bsn - dov - cok - rwo - mag - hnj - krj - teo - enq - aom - ffm - din - ubu - pwn - gum - sny - twu - med - acn - rme - cbs - abx - ndc - ibb - pih - zty - rad - aby - zne - cui - lua - yby - bno - niu - agd - nij - agg - yre - fip - qve - tsg - skg - adj - mfq - agx - kmg - umb - cnk - nhw - maa - kwy - jra - syr - inb - pau - xsm - vap - alp - des - syl - kmr - mkn - gan - qwh - jvn - bib - ckt - mpx - bin - klv - xon - jbu - bdh - knj - ptu - mmn - mwq - sop - cgc - rmy - dop - mgr - rmo - tbc - kyq - zpu - kkc - acu - ata - gag - kan - mif - sus - tsz - mbi - imo - fuh - zyp - apr - att - bus - kqp - koo - bas - urh - bbr - msy - mdy - nas - lee - mcu - mrj - dig - izr - nfr - hto - mzw - qxh - chz - guh - ded - bvz - kkj - gux - ikt - bnp - bgt - quf - dwr - nod - yal - bmr - ljp - xla - zyb - gof - niv - nrf - npy - ura - dob - gfk - gdr - sdc - pjt - spp - irk - cpa - knc - gvl - agr - njo - xrb - kao - zpz - bgr - rnd - ntu - aai - gai - dgi - kez - dad - kmh - aii - ifk - aji - noa - bhl - ztq - rmn - gde - dnj - men - miq - mdf - isd - lgg - ncx - gub - itv - tac - cce - kwi - nhu - snd - sml - pah - sas - cwt - spy - enb - fai - cas - sue - yss - ozm - bku - biv - akp - dts - kdr - fal - mmo - byr - cbv - cbu - eza - kgp - sda - gbo - mfi - bdd - boj - blh - ibg - agn - vmy - sua - gul - rap - bmh - sxn - dyi - tdx - car - heh - dgc - sgb - bpr - gbi - avu - udu - yli - cjs - gnn - nhi - urk - kpy - qup - qvh - pir - tsc - bxr - thk - grt - kqn - hay - mqb - tbg - bss - trn - jae - myy - ipk - bao - qvz - dua - mwv - nct - kyc - tuo - tee - mop - mxt - qvm - gkn - lam - ntr - sbe - dyo - lex - smk - coe - kpe - mni - xbi - atb - tcf - bfo - cbc - swg - niv - cnt - izz - knf - mpp - kki - nho - sat - kbr - bmu - hig - qxr - orv - pma - zpl - kpr - sig - ory - mxp - lef - mlp - soq - cre - aey - qvs - sur - knc - suk - cax - alq - chw - dww - gog - viv - qvw - ted - yuj - ziw - kto - mcq - sim - koi - lue - cya - knk - tpt - taj - blz - mil - kde - kpz - hag - vun - kus - lid - tos - bfd - chd - cle - yon - bgs - lsm - msb - ota - guj - mxq - lfn - myw - aso - esu - kdi - bhp - mfz - sgw - xsi - gun - kxc - mux - otw - cjp - nyo - zia - cco - ojb - ktu - cpy - txu - bjr - bud - ken - bzh - ipi - crx - cko - gnd - kix - mmx - esk - kud - toh - byx - mtp - kpv - kyz - lmp - tiy - ccp - sbl - tcs - usp - buk - hvn - amm - kzj - gng - ter - kij - ngl - pab - pad - kca - meq - kas - niq - dah - lia - kss - bch - khz - nop - yle - ain - pem - yml - taq - gaw - kze - tby - cso - ifb - rki - aly - kmu - mhl - kmo - mva - opm - rtm - xtn - dgr - ksr - snp - tvk - zpv - hrx - kwj - muh - kak - kpw - akb - ybb - kjs - wuv - laj - ogo - nim - czt - aoz - rro - yuw - heg - mrw - zac - kpf - leu - nwi - awx - gso - keo - tte - ceg - nhy - bhw - gnw - nin - xmv - crm - mxv - ubr - gld - bzi - ann - lac - mej - zpc - dje - caq - guk - wos - msm - zaw - cap - mox - zab - mca - wrs - hae - nss - rav - uvh - dga - ppo - nog - arq - bim - lwg - kms - kne - tkl - ady - caf - zat - aba - chf - lew - npl - uvl - cdo - rmq - mek - snc - nsn - amn - abz - cek - ong - txq - bjp - gvf - crk - snf - nhg - kqw - mic - mie - nus - plu - idu - sll - thl - bef - kwd - mqy - caa - aia - wer - agm - mbl - mbs - adh - hub - mav - nab - bqp - guo - auy - big - nii - row - kim - mti - otm - prg - icr - mcp - tbo - chy - oji - kpx - lbb - pao - xuo - zgh - wls - aca - apy - wnc - ssg - eve - mee - yut - chr - kxm - mur - lad - mcd - cto - mqj - usa - emi - liv - guz - tgp - ncl - azg - kck - apb - kbm - sgz - wsk - gbm - csw - ctp - eri - vid - bsq - dak - tif - xsr - mwp - roo - wbp - gdn - tgo - zpm - mih - qvc - tod - abn - cao - kbc - kog - moh - leh - nsu - okv - tih - zos - llg - gmv - kyf - mhx - mvp - naf - ino - dng - mnk - oke - omw - tnk - xtd - agt - cbr - eko - nhk - hot - iou - mpm - myx - ndh - pbb - rng - cri - bvd - kmz - cta - blw - clu - cof - kje - nmf - kbh - qxn - ria - wed - zar - huv - lsi - msk - nbq - ati - lww - yva - amr - lmk - tim - bbb - bzd - djr - kwf - nuy - poi - ptp - atd - bps - lcm - mbh - nuj - ayp - cwe - geb - aoi - mto - cbi - gvn - kqf - rkb - xed - zas - apz - cpb - ese - gdg - iws - apu - cag - kdc - nou - too - xmm - beq - hnn - myk - sby - arl - ncu - rml - gam - kvn - mbc - mfy - urt - luc - mio - snn - tar - tku - upv - kjg - btd - cut - mwn - tue - adz - kyg - rel - tew - ttc - nkf - yrb - fub - nsm - nyf - ava - bkd - cpc - lif - mwc - gan - apw - azz - zpo - ace - faa - ood - toc - wmt - ajg - nko - ssd - sxb - zxx - not - amk - hch - kqc - aui - llb - avt - kaq - tna - zpt - mnw - bwd - lif - stn - crk - kgk - mck - bhg - ifu - kkl - zao - huu - sil - trq - tuf - wnu - amf - fan - zdj - bco - kdl - lln - mit - yaq - ake - ige - mna - nhx - njn - wba - zaa - lez - syb - qxo - rgu - wiu - bla - etr - miy - mjc - nif - pov - qxl - sey - bxh - ddg - mks - nki - pot - prf - hra - law - plw - zpi - atg - daf - drg - dru - ngp - boa - cbt - dhm - ikw - kqe - lbj - loq - xsb - yad - kyu - mcb - tks - cnl - far - miz - maj - mgm - mib - mza - nhr - smt - ish - mlu - yka - anv - ign - mir - tav - gyr - klt - apn - wbm - cjk - dln - mcf - twx - ldi - poy - yaa - zae - bdq - con - dnw - gah - lcp - mbj - xog - yan - sdq - sgh - gwi - lbk - ses - ycn - kau - hix - mig - mlh - aer - amx - auc - cly - dsh - gnb - neb - ttt - jic - xtm - tll - apt - kgr - pio - pmf - yrk - akh - box - cub - cux - mrq - inh - bsp - for - kny - uri - zsr - pce - cme - cot - kxw - omb - srq - vag - cpu - kmy - ksc - lai - nnp - ruf - spm - tro - ttj - waj - raj - ian - ivb - kmm - kzf - maw - tuv - whk - zsm - aph - anm - mny - bug - trp - are - esi - mhi - obo - bwu - lwo - mrg - old - zav - snk - daa - fuq - lud - nlg - sck - tbl - khb - tpu - fue - tmd - whg - blt - gqr - kub - ots - tpp - var - hbb - krr - zxx - alj - ebk - goa - hav - kmk - kqo - muy - njb - snw - wib - shn - tkr - ksp - lip - mog - nla - pss - zad - awi - frd - kei - kmd - mim - got - lbe - adi - any - arp - biu - bvc - ghs - ttq - vmk - zpj - crl - dtb - dug - kam - nmo - qva - rhg - taw - tui - uth - wap - zpg - brb - dty - syr - bih - bqj - cjv - cnw - kgf - mfh - mns - nnw - ntp - oto - dks - mpt - nmw - sba - sfw - shu - ury - yrl - arc - cmo - xkg - iqw - kpj - nfa - nph - nre - wsg - xsu - nut - bmk - cdf - enl - fuv - hop - ife - lnd - mrv - nzm - tem - dwr - gwc - udi - zha - ajz - kru - qvo - sld - yup - anp - kwu - szy - tdg - ade - bcw - bgz - cul - fmu - gvc - ktj - lis - mev - msc - mta - nbc - ncq - way - wlv - wlx - jmx - pli - tkr - wni - aim - byv - cgg - fud - jmc - ker - kia - lom - ojb - tnc - bwx - cre - skr - xal - gjn - guq - lap - mip - mkl - mtg - mzk - njm - nse - pne - pww - zam - zca - the - dis - lgl - mbd - mda - mhy - nst - pkb - pmq - poe - swk - trs - vot - yam - zpq - atq - bav - cho - chq - cjo - due - duo - etu - ifa - kby - khq - kno - lem - mcn - mkz - mnb - myb - niy - pxm - rub - sju - tmc - tpm - wob - nxa - pnt - sdk - tcy - bhz - bth - crj - eka - khy - led - met - mgo - mus - mzm - naw - sri - tbk - xbr - awa - tnl - tnn - awb - bsc - iri - kpq - ktm - loe - lun - mfg - moa - ndj - otn - sjo - wat - bkm - tuz - ybi - gbr - gej - giz - gna - gwr - kex - kle - knx - ktz - kvj - lob - mhw - mph - pmx - qus - tcc - ang - azn - bra - gal - jra - nlv - rki - stk - yux - dip - ivv - kdj - kff - kyu - mnf - moc - mpg - mua - nma - rim - rjs - rnl - ssx - tig - urw - idt - mrn - oki - bbk - bea - bkq - btt - cou - ddn - did - diu - ilb - ksj - lhi - ndi - ngb - njz - nmz - npo - nwb - pbi - sbd - soe - tpw - twb - bfn - boz - lwl - psp - sgd - ymp - bkl - bkv - csk - enx - ess - gof - gud - guu - kdh - krx - kzn - maf - max - mgc - mvn - mwm - nbe - nlc - nxd - pse - sbs - tlb - wwa - yim - bkx - bze - chu - kbq - kpy - mry - tkd - ybh - abi - ayo - bex - bom - bov - dhg - jaa - kqs - kqy - ksb - ldn - log - lol - mfk - mtj - ndz - ngc - nio - nri - nuz - pps - shk - tlj - vut - xnn - bcc - cuh - emp - hro - nco - nxl - pex - tnp - trv - vif - aha - avn - bmv - chj - crt - dos - eto - gya - hlt - jun - ktb - lgm - mnx - mor - mug - nng - nnh - nsa - nyk - otd - oym - phm - prq - saj - szb - tap - tnr - tzl - wew - yas - yuz - avk - bat - baw - bwt - bxa - cjs - csw - fli - kqr - lan - lgr - lhm - mlk - mve - nqo - odk - olo - otq - pea - saq - sea - sps - tio - yin - adl - agw - ald - asg - bnj - brx - bwi - bwq - dbq - dow - fad - hoc - kql - ksf - kyu - lea - mse - mzl - nhd - nnl - nwx - pbc - pny - tul - aaa - abc - agq - ags - azo - bag - bax - bce - bfm - bgf - bhs - bkc - bkh - blk - bob - bqm - bri - brv - buo - bya - chp - cim - clo - cuv - dag - dmg - dtr - eee - ekm - enc - fiu - gbj - gou - hao - hna - hre - isu - jgo - kbx - kvt - kxp - lfa - lkb - lns - loh - lrc - lts - luy - mdr - mfj - mgg - mgq - mle - mlw - mmu - mne - muv - mxu - nge - ngn - njy - nsk - nsk - nwe - nza - pcg - pdu - pnz - pwg - qaa - shi - smn - snk - snl - sox - ssn - syw - tay - tbj - tdb - thy - tnt - tom - tpl - tsb - tvs - udg - unr - wbr - wms - wnk - wtk - xmd - xmg - xty - yav - yea - zuh multilinguality: - multilingual pinned: true tags: - multilingual --- ## Dataset Summary DCAD-2000 is a large-scale multilingual corpus built using newly extracted Common Crawl data (CC-MAIN-2024-46) and existing multilingual datasets. It includes over 2,282 languages, 46.72TB of data, and 8.63 billion documents, spanning 155 highand medium-resource languages and 159 writing scripts. We propose reframing data cleaning as an anomaly detection task. This dynamic filtering approach significantly enhances data quality by identifying and removing noisy or anomalous content. + Paper: [A Multilingual Dataset across 2000+ Languages with Data Cleaning as Anomaly Detection](https://www.arxiv.org/abs/2502.11546) + Github: [https://github.com/yl-shen/DCAD-2000](https://github.com/yl-shen/DCAD-2000) + Dataset (HuggingFace): [openbmb/DCAD-2000](https://huggingface.co/datasets/openbmb/DCAD-2000) ## Dataset Overview Comparison of multilingual datasets constructed from Common Crawl (CC) and our constructed DCAD-2000, focusing on the latest CC version used, the total number of languages supported, distribution across resource categories (high, medium, low, very low), and training readiness. The CC version marked with bold indicates an inferred version due to the lack of explicit specification in the original paper. The ``Training-Ready'' column indicates whether the dataset is ready for training LLMs without requiring further data cleaning. \| Dataset \| CC Version \| #Langs (total) \| #Langs (high) \| #Langs (medium) \| #Langs (low) \| #Langs (very low) \| Training-Ready \| \|---------------------------\|--------------------\|--------------------\|-------------------\|---------------------\|------------------\|-----------------------\|--------------------\| \| mC4 (Raffel et al., 2020) \| CC-MAIN-2020-34 \| 101 \| 0 \| 43 \| 52 \| 6 \| ✘ \| \| OSCAR 23.01 (Abadji et al., 2022) \| CC-MAIN-2022-49 \| 153 \| 6 \| 42 \| 25 \| 80 \| ✘ \| \| Glot500 (Imani et al., 2023) \| CC-MAIN-2020-34 \| 511 \| 0 \| 108 \| 79 \| 324 \| ✘ \| \| CulturaX (Nguyen et al., 2024) \| CC-MAIN-2022-49 \| 167 \| 11 \| 47 \| 27 \| 82 \| ✘ \| \| Madlad-400 (Kudugunta et al., 2024) \| CC-MAIN-2022-33 \| 419 \| 7 \| 46 \| 39 \| 327 \| ✘ \| \| MaLA (Ji et al., 2024) \| CC-MAIN-2022-49 \| 939 \| 1 \| 125 \| 78 \| 735 \| ✘ \| \| Glotcc (Kargaran et al., 2024) \| CC-MAIN-2023-50 \| 1331 \| 0 \| 10 \| 52 \| 1269 \| ✘ \| \| HPLT-v1.2 (de Gilbert et al., 2024) \| CC-MAIN-2022-40 \| 191 \| 12 \| 53 \| 38 \| 88 \| ✘ \| \| Fineweb-2 (Penedo et al., 2024) \| CC-MAIN-2024-18 \| 1915 \| 10 \| 62 \| 49 \| 1794 \| ✘ \| \| DCAD-2000 \| CC-MAIN-2024-46 \| 2282 \| 13 \| 142 \| 124 \| 2003 \| ✓ \| ## Dataset Creation + Data Collection: DCAD-2000 integrates data from four main sources: MaLA, Fineweb, Fineweb-2, and newly extracted Common Crawl data. + Data Cleaning as Anomaly Detection: Traditional data cleaning methods rely on fixed thresholds for document-level features, making them less adaptable to the diversity of multilingual data. To address this, we propose a novel framework that formulates data cleaning as an anomaly detection task, which involves the feature extraction and anomaly detection. - Feature Extraction: For each document, we consider the following eight features: (1) Number of Words; (2) Character Repetition Ratio; (3) Word Repetition Ratio; (4) Special Characters Ratio; (5) Stop- words Ratio; (6) Flagged Words Ratio; (7) Language Identification (LID) Score; (8) Perplexity Score. - Anomaly Detection: We evaluate several classical anomaly detection algorithms including (1) Isolation Forest; (2) One Class SVM; (3) Local Outlier Factor and (4) K-Means. - Visualization<br> ![ad_overview](https://github.com/yl-shen/DCAD-2000/raw/master/images/ad_visual.png) ## Data Statistics + [Geographical Distribution](https://github.com/yl-shen/DCAD-2000/blob/master/statistics/geo_group.tsv) + [Script Distribution](https://github.com/yl-shen/DCAD-2000/blob/master/statistics/script_group_detail.tsv) + [Statistical Details](https://github.com/yl-shen/DCAD-2000/blob/master/statistics/statistic_detail.tsv) + [language list](https://github.com/yl-shen/DCAD-2000/blob/master/statistics/statistic_lang_num.tsv) + [language mapping](https://github.com/yl-shen/DCAD-2000/blob/master/lang_mapping/all_mapping.csv) ## Usage (Dataset) ``` from datasets import load_dataset data = load_dataset("openbmb/DCAD-2000") ``` You can also specifiy the language you wanted ``` from datasets import load_dataset data = load_dataset("openbmb/DCAD-2000", name="eng_Latn", split="train") ``` ## Citation Information ``` @article{shen2025dcad, title={DCAD-2000: A Multilingual Dataset across 2000+ Languages with Data Cleaning as Anomaly Detection}, author={Shen, Yingli and Lai, Wen and Wang, Shuo and Zhang, Xueren and Luo, Kangyang and Fraser, Alexander and Sun, Maosong}, journal={arXiv preprint arXiv:2502.11546}, year={2025} } ``` ## Acknowledgements We introduce DCAD-2000, a large- scale multilingual dataset designed to address the increasing demand for high-quality and diverse training data for multilingual LLMs. This work is done by researchers at [Tsinghua NLP group](https://nlp.csai.tsinghua.edu.cn) in collaboration with partners from [TUM](https://wenlai-lavine.github.io/) and [Modelbest Inc.](https://huggingface.co/openbmb) ## Contact Information Yingli Shen ([email protected]) Wen Lai ([email protected])
stanfordnlp/sst2	stanfordnlp	"2024-01-04T16:31:07Z"	15,748	114	[ "task_categories:text-classification", "task_ids:sentiment-classification", "annotations_creators:crowdsourced", "language_creators:found", "multilinguality:monolingual", "source_datasets:original", "language:en", "license:unknown", "size_categories:10K<n<100K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]	[ "text-classification" ]	"2022-06-13T14:01:47Z"	--- annotations_creators: - crowdsourced language_creators: - found language: - en license: - unknown multilinguality: - monolingual size_categories: - 10K<n<100K source_datasets: - original task_categories: - text-classification task_ids: - sentiment-classification paperswithcode_id: sst pretty_name: Stanford Sentiment Treebank v2 dataset_info: features: - name: idx dtype: int32 - name: sentence dtype: string - name: label dtype: class_label: names: '0': negative '1': positive splits: - name: train num_bytes: 4681603 num_examples: 67349 - name: validation num_bytes: 106252 num_examples: 872 - name: test num_bytes: 216640 num_examples: 1821 download_size: 3331058 dataset_size: 5004495 configs: - config_name: default data_files: - split: train path: data/train-* - split: validation path: data/validation-* - split: test path: data/test-* --- # Dataset Card for [Dataset Name] ## Table of Contents - [Table of Contents](#table-of-contents) - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - Homepage: https://nlp.stanford.edu/sentiment/ - Repository: - Paper: [Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank](https://www.aclweb.org/anthology/D13-1170/) - Leaderboard: - Point of Contact: ### Dataset Summary The Stanford Sentiment Treebank is a corpus with fully labeled parse trees that allows for a complete analysis of the compositional effects of sentiment in language. The corpus is based on the dataset introduced by Pang and Lee (2005) and consists of 11,855 single sentences extracted from movie reviews. It was parsed with the Stanford parser and includes a total of 215,154 unique phrases from those parse trees, each annotated by 3 human judges. Binary classification experiments on full sentences (negative or somewhat negative vs somewhat positive or positive with neutral sentences discarded) refer to the dataset as SST-2 or SST binary. ### Supported Tasks and Leaderboards - `sentiment-classification` ### Languages The text in the dataset is in English (`en`). ## Dataset Structure ### Data Instances ``` {'idx': 0, 'sentence': 'hide new secretions from the parental units ', 'label': 0} ``` ### Data Fields - `idx`: Monotonically increasing index ID. - `sentence`: Complete sentence expressing an opinion about a film. - `label`: Sentiment of the opinion, either "negative" (0) or positive (1). The test set labels are hidden (-1). ### Data Splits \| \| train \| validation \| test \| \|--------------------\|---------:\|-----------:\|-----:\| \| Number of examples \| 67349 \| 872 \| 1821 \| ## Dataset Creation ### Curation Rationale [More Information Needed] ### Source Data #### Initial Data Collection and Normalization [More Information Needed] #### Who are the source language producers? Rotten Tomatoes reviewers. ### Annotations #### Annotation process [More Information Needed] #### Who are the annotators? [More Information Needed] ### Personal and Sensitive Information [More Information Needed] ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed] ### Discussion of Biases [More Information Needed] ### Other Known Limitations [More Information Needed] ## Additional Information ### Dataset Curators [More Information Needed] ### Licensing Information Unknown. ### Citation Information ```bibtex @inproceedings{socher-etal-2013-recursive, title = "Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank", author = "Socher, Richard and Perelygin, Alex and Wu, Jean and Chuang, Jason and Manning, Christopher D. and Ng, Andrew and Potts, Christopher", booktitle = "Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing", month = oct, year = "2013", address = "Seattle, Washington, USA", publisher = "Association for Computational Linguistics", url = "https://www.aclweb.org/anthology/D13-1170", pages = "1631--1642", } ``` ### Contributions Thanks to [@albertvillanova](https://github.com/albertvillanova) for adding this dataset.
bigcode/bigcodebench-hard	bigcode	"2025-02-23T16:42:46Z"	15,726	3	[ "size_categories:n<1K", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]	null	"2024-09-14T14:50:33Z"	--- dataset_info: features: - name: task_id dtype: string - name: complete_prompt dtype: string - name: instruct_prompt dtype: string - name: canonical_solution dtype: string - name: code_prompt dtype: string - name: test dtype: string - name: entry_point dtype: string - name: doc_struct dtype: string - name: libs dtype: string - name: q_idx dtype: int64 - name: question dtype: string - name: score dtype: float64 - name: _id dtype: string splits: - name: v0.1.0_hf num_bytes: 1271624 num_examples: 148 - name: v0.1.1 num_bytes: 1271607 num_examples: 148 - name: v0.1.2 num_bytes: 1271812 num_examples: 148 - name: v0.1.3 num_bytes: 1271812 num_examples: 148 - name: v0.1.4 num_bytes: 1272012 num_examples: 148 download_size: 2758366 dataset_size: 6358867 configs: - config_name: default data_files: - split: v0.1.0_hf path: data/v0.1.0_hf-* - split: v0.1.1 path: data/v0.1.1-* - split: v0.1.2 path: data/v0.1.2-* - split: v0.1.3 path: data/v0.1.3-* - split: v0.1.4 path: data/v0.1.4-* ---
andstor/methods2test	andstor	"2023-12-23T03:01:51Z"	15,658	0	[ "task_categories:text-generation", "language:en", "license:mit", "size_categories:10M<n<100M", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "arxiv:2203.12776", "region:us", "unit test", "java", "code" ]	[ "text-generation" ]	"2023-12-07T13:37:44Z"	--- language: - en license: mit task_categories: - text-generation configs: - config_name: fm data_files: - split: train path: data/fm/train-* - split: test path: data/fm/test-* - split: validation path: data/fm/validation-* - config_name: fm_indented data_files: - split: train path: data/fm_indented/train-* - split: test path: data/fm_indented/test-* - split: validation path: data/fm_indented/validation-* - config_name: fm+t data_files: - split: train path: data/fm+t/train-* - split: test path: data/fm+t/test-* - split: validation path: data/fm+t/validation-* - config_name: fm+fc data_files: - split: train path: data/fm+fc/train-* - split: test path: data/fm+fc/test-* - split: validation path: data/fm+fc/validation-* - config_name: fm+fc+t+tc data_files: - split: train path: data/fm+fc+t+tc/train-* - split: test path: data/fm+fc+t+tc/test-* - split: validation path: data/fm+fc+t+tc/validation-* - config_name: fm+fc+c data_files: - split: train path: data/fm+fc+c/train-* - split: test path: data/fm+fc+c/test-* - split: validation path: data/fm+fc+c/validation-* - config_name: fm+fc+c+t+tc data_files: - split: train path: data/fm+fc+c+t+tc/train-* - split: test path: data/fm+fc+c+t+tc/test-* - split: validation path: data/fm+fc+c+t+tc/validation-* - config_name: fm+fc+c+m data_files: - split: train path: data/fm+fc+c+m/train-* - split: test path: data/fm+fc+c+m/test-* - split: validation path: data/fm+fc+c+m/validation-* - config_name: fm+fc+c+m+t+tc data_files: - split: train path: data/fm+fc+c+m+t+tc/train-* - split: test path: data/fm+fc+c+m+t+tc/test-* - split: validation path: data/fm+fc+c+m+t+tc/validation-* - config_name: fm+fc+c+m+f data_files: - split: train path: data/fm+fc+c+m+f/train-* - split: test path: data/fm+fc+c+m+f/test-* - split: validation path: data/fm+fc+c+m+f/validation-* - config_name: fm+fc+c+m+f+t+tc data_files: - split: train path: data/fm+fc+c+m+f+t+tc/train-* - split: test path: data/fm+fc+c+m+f+t+tc/test-* - split: validation path: data/fm+fc+c+m+f+t+tc/validation-* - config_name: t data_files: - split: train path: data/t/train-* - split: test path: data/t/test-* - split: validation path: data/t/validation-* - config_name: t_indented data_files: - split: train path: data/t_indented/train-* - split: test path: data/t_indented/test-* - split: validation path: data/t_indented/validation-* - config_name: t+tc data_files: - split: train path: data/t+tc/train-* - split: test path: data/t+tc/test-* - split: validation path: data/t+tc/validation-* dataset_info: - config_name: fm features: - name: id dtype: string - name: text dtype: string splits: - name: train num_bytes: 440444124 num_examples: 624022 - name: test num_bytes: 59407291 num_examples: 78388 - name: validation num_bytes: 57170315 num_examples: 78534 download_size: 99172217 dataset_size: 557021730 - config_name: fm+fc features: - name: id dtype: string - name: text dtype: string splits: - name: train num_bytes: 506130678 num_examples: 624022 - name: test num_bytes: 68407490 num_examples: 78388 - name: validation num_bytes: 65318956 num_examples: 78534 download_size: 109141139 dataset_size: 639857124 - config_name: fm+fc+c features: - name: id dtype: string - name: text dtype: string splits: - name: train num_bytes: 569209100 num_examples: 624022 - name: test num_bytes: 75552573 num_examples: 78388 - name: validation num_bytes: 73101169 num_examples: 78534 download_size: 117996353 dataset_size: 717862842 - config_name: fm+fc+c+m features: - name: id dtype: string - name: text dtype: string splits: - name: train num_bytes: 1354004338 num_examples: 624022 - name: test num_bytes: 187724929 num_examples: 78388 - name: validation num_bytes: 184349299 num_examples: 78534 download_size: 222922572 dataset_size: 1726078566 - config_name: fm+fc+c+m+f features: - name: id dtype: string - name: text dtype: string splits: - name: train num_bytes: 1476073209 num_examples: 624022 - name: test num_bytes: 201686811 num_examples: 78388 - name: validation num_bytes: 201259950 num_examples: 78534 download_size: 240405885 dataset_size: 1879019970 - config_name: fm+fc+c+m+f+t+tc features: - name: id dtype: string - name: source dtype: string - name: target dtype: string splits: - name: train num_bytes: 2019918359 num_examples: 624022 - name: test num_bytes: 269021331 num_examples: 78388 - name: validation num_bytes: 272958781 num_examples: 78534 download_size: 371500476 dataset_size: 2561898471 - config_name: fm+fc+c+m+t+tc features: - name: id dtype: string - name: source dtype: string - name: target dtype: string splits: - name: train num_bytes: 1897682665 num_examples: 624022 - name: test num_bytes: 255053799 num_examples: 78388 - name: validation num_bytes: 256030595 num_examples: 78534 download_size: 360175965 dataset_size: 2408767059 - config_name: fm+fc+c+t+tc features: - name: id dtype: string - name: source dtype: string - name: target dtype: string splits: - name: train num_bytes: 1109827485 num_examples: 624022 - name: test num_bytes: 142558255 num_examples: 78388 - name: validation num_bytes: 144523616 num_examples: 78534 download_size: 251861137 dataset_size: 1396909356 - config_name: fm+fc+t+tc features: - name: id dtype: string - name: source dtype: string - name: target dtype: string splits: - name: train num_bytes: 1046592848 num_examples: 624022 - name: test num_bytes: 135403379 num_examples: 78388 - name: validation num_bytes: 136729952 num_examples: 78534 download_size: 243052074 dataset_size: 1318726179 - config_name: fm+t features: - name: id dtype: string - name: source dtype: string - name: target dtype: string splits: - name: train num_bytes: 868034154 num_examples: 624022 - name: test num_bytes: 114371187 num_examples: 78388 - name: validation num_bytes: 112688219 num_examples: 78534 download_size: 217267853 dataset_size: 1095093560 - config_name: fm_indented features: - name: id dtype: string - name: text dtype: string splits: - name: train num_bytes: 473170158 num_examples: 624022 - name: test num_bytes: 64280367 num_examples: 78388 - name: validation num_bytes: 61093848 num_examples: 78534 download_size: 103174190 dataset_size: 598544373 - config_name: t features: - name: id dtype: string - name: source dtype: string - name: target dtype: string splits: - name: train num_bytes: 380207303 num_examples: 624022 - name: test num_bytes: 47993188 num_examples: 78388 - name: validation num_bytes: 49808813 num_examples: 78534 download_size: 113820250 dataset_size: 478009304 - config_name: t+tc features: - name: id dtype: string - name: source dtype: string - name: target dtype: string splits: - name: train num_bytes: 550955294 num_examples: 624022 - name: test num_bytes: 68323462 num_examples: 78388 - name: validation num_bytes: 72740770 num_examples: 78534 download_size: 136767271 dataset_size: 692019526 - config_name: t_indented features: - name: id dtype: string - name: source dtype: string - name: target dtype: string splits: - name: train num_bytes: 405853738 num_examples: 624022 - name: test num_bytes: 51457514 num_examples: 78388 - name: validation num_bytes: 52970428 num_examples: 78534 download_size: 117732776 dataset_size: 510281680 tags: - unit test - java - code --- ## Dataset Description Microsoft created the methods2test dataset, consisting of Java Junit test cases with its corresponding focal methods. It contains 780k pairs of JUnit test cases and focal methods which were extracted from a total of 91K Java open source project hosted on GitHub. This is an assembled version of the methods2test dataset. It provides convenient access to the different context levels based on the raw source code (e.g. newlines are preserved). The test cases and associated classes are also made available. The mapping between test case and focal methods are based heuristics rules and Java developer's best practice. More information could be found here: - [methods2test Github repo](https://github.com/microsoft/methods2test) - [Methods2Test: A dataset of focal methods mapped to test cases](https://arxiv.org/pdf/2203.12776.pdf) ## Dataset Schema ``` t: <TEST_CASE> t_tc: <TEST_CASE> <TEST_CLASS_NAME> fm: <FOCAL_METHOD> fm_fc: <FOCAL_CLASS_NAME> <FOCAL_METHOD> fm_fc_c: <FOCAL_CLASS_NAME> <FOCAL_METHOD> <CONTRSUCTORS> fm_fc_c_m: <FOCAL_CLASS_NAME> <FOCAL_METHOD> <CONTRSUCTORS> <METHOD_SIGNATURES> fm_fc_c_m_f: <FOCAL_CLASS_NAME> <FOCAL_METHOD> <CONTRSUCTORS> <METHOD_SIGNATURES> <FIELDS> ``` ## Focal Context - fm: this representation incorporates exclusively the source code of the focal method. Intuitively, this contains the most important information for generating accurate test cases for the given method. - fm+fc: this representations adds the focal class name, which can provide meaningful semantic information to the model. - fm+fc+c: this representation adds the signatures of the constructor methods of the focal class. The idea behind this augmentation is that the test case may require instantiating an object of the focal class in order to properly test the focal method. - fm+fc+c+m: this representation adds the signatures of the other public methods in the focal class. The rationale which motivated this inclusion is that the test case may need to invoke other auxiliary methods within the class (e.g., getters, setters) to set up or tear down the testing environment. - fm+fc+c+m+f : this representation adds the public fields of the focal class. The motivation is that test cases may need to inspect the status of the public fields to properly test a focal method. ![image/png](https://huggingface.co/datasets/andstor/methods2test/resolve/main/figure-1-focal-context.png) The different levels of focal contexts are the following: ``` T: test case T_TC: test case + test class name FM: focal method FM_FC: focal method + focal class name FM_FC_C: focal method + focal class name + constructor signatures FM_FC_C_M: focal method + focal class name + constructor signatures + public method signatures FM_FC_C_M_F: focal method + focal class name + constructor signatures + public method signatures + public fields ``` ## Limitations The original authors validate the heuristics by inspecting a statistically significant sample (confidence level of 95% within 10% margin of error) of 97 samples from the training set. Two authors independently evaluated the sample, then met to discuss the disagreements. We found that 90.72% of the samples have a correct link between the test case and the corresponding focal method ## Contribution All thanks to the original authors.
zh-plus/tiny-imagenet	zh-plus	"2022-07-12T09:04:30Z"	15,447	72	[ "task_categories:image-classification", "task_ids:multi-class-image-classification", "annotations_creators:crowdsourced", "language_creators:crowdsourced", "multilinguality:monolingual", "source_datasets:extended\|imagenet-1k", "language:en", "size_categories:100K<n<1M", "format:parquet", "modality:image", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]	[ "image-classification" ]	"2022-07-01T03:33:16Z"	--- annotations_creators: - crowdsourced extra_gated_prompt: "By clicking on \u201CAccess repository\u201D below, you also\ \ agree to ImageNet Terms of Access:\n[RESEARCHER_FULLNAME] (the \"Researcher\"\ ) has requested permission to use the ImageNet database (the \"Database\") at Princeton\ \ University and Stanford University. In exchange for such permission, Researcher\ \ hereby agrees to the following terms and conditions:\n1. Researcher shall use\ \ the Database only for non-commercial research and educational purposes.\n2. Princeton\ \ University, Stanford University and Hugging Face make no representations or warranties\ \ regarding the Database, including but not limited to warranties of non-infringement\ \ or fitness for a particular purpose.\n3. Researcher accepts full responsibility\ \ for his or her use of the Database and shall defend and indemnify the ImageNet\ \ team, Princeton University, Stanford University and Hugging Face, including their\ \ employees, Trustees, officers and agents, against any and all claims arising from\ \ Researcher's use of the Database, including but not limited to Researcher's use\ \ of any copies of copyrighted images that he or she may create from the Database.\n\ 4. Researcher may provide research associates and colleagues with access to the\ \ Database provided that they first agree to be bound by these terms and conditions.\n\ 5. Princeton University, Stanford University and Hugging Face reserve the right\ \ to terminate Researcher's access to the Database at any time.\n6. If Researcher\ \ is employed by a for-profit, commercial entity, Researcher's employer shall also\ \ be bound by these terms and conditions, and Researcher hereby represents that\ \ he or she is fully authorized to enter into this agreement on behalf of such employer.\n\ 7. The law of the State of New Jersey shall apply to all disputes under this agreement." language: - en language_creators: - crowdsourced license: [] multilinguality: - monolingual paperswithcode_id: imagenet pretty_name: Tiny-ImageNet size_categories: - 100K<n<1M source_datasets: - extended\|imagenet-1k task_categories: - image-classification task_ids: - multi-class-image-classification --- # Dataset Card for tiny-imagenet ## Dataset Description - Homepage: https://www.kaggle.com/c/tiny-imagenet - Repository: [Needs More Information] - Paper: http://cs231n.stanford.edu/reports/2017/pdfs/930.pdf - Leaderboard: https://paperswithcode.com/sota/image-classification-on-tiny-imagenet-1 ### Dataset Summary Tiny ImageNet contains 100000 images of 200 classes (500 for each class) downsized to 64×64 colored images. Each class has 500 training images, 50 validation images, and 50 test images. ### Languages The class labels in the dataset are in English. ## Dataset Structure ### Data Instances ```json { 'image': <PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=64x64 at 0x1A800E8E190, 'label': 15 } ``` ### Data Fields - image: A PIL.Image.Image object containing the image. Note that when accessing the image column: dataset[0]["image"] the image file is automatically decoded. Decoding of a large number of image files might take a significant amount of time. Thus it is important to first query the sample index before the "image" column, i.e. dataset[0]["image"] should always be preferred over dataset["image"][0]. - label: an int classification label. -1 for test set as the labels are missing. Check `classes.py` for the map of numbers & labels. ### Data Splits \| \| Train \| Valid \| \| ------------ \| ------ \| ----- \| \| # of samples \| 100000 \| 10000 \| ## Usage ### Example #### Load Dataset ```python def example_usage(): tiny_imagenet = load_dataset('Maysee/tiny-imagenet', split='train') print(tiny_imagenet[0]) if __name__ == '__main__': example_usage() ```
Multimodal-Fatima/SNLI-VE_train	Multimodal-Fatima	"2023-02-07T23:21:35Z"	15,368	1	[ "size_categories:100K<n<1M", "format:parquet", "modality:image", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]	null	"2023-02-07T00:32:32Z"	--- dataset_info: features: - name: image dtype: image - name: filename dtype: string - name: premise dtype: string - name: hypothesis dtype: string - name: label dtype: class_label: names: '0': entailment '1': neutral '2': contradiction - name: id dtype: int64 - name: id_image dtype: int64 - name: clip_tags_ViT_L_14 sequence: string - name: blip_caption dtype: string - name: LLM_Description_gpt3_downstream_tasks_visual_genome_ViT_L_14 sequence: string splits: - name: train num_bytes: 73634118251.385 num_examples: 529527 download_size: 27853612384 dataset_size: 73634118251.385 --- # Dataset Card for "SNLI-VE_train" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
Avelina/smollm-corpus-cleaned	Avelina	"2025-02-26T23:03:34Z"	15,329	0	[ "task_categories:text-generation", "language:en", "license:odc-by", "size_categories:100M<n<1B", "format:json", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "region:us" ]	[ "text-generation" ]	"2025-02-26T20:55:01Z"	--- license: odc-by dataset_info: - config_name: default features: - name: text dtype: string configs: - config_name: default data_files: - split: train path: data/train- task_categories: - text-generation language: - en size_categories: - 100M<n<1B --- # SmolLM-Corpus: Now shuffled and sharded (and Cleaned)! This is a version of the SmolLM-Corpus where the 3 subsets have been interleved, shuffled and sharded as 23698 `jsonl.zst` files for easy streaming! The dataset is comprised of the `cosmopedia-v2` and `fineweb-edu-dedup` subsets from the original [SmolLM-Corpus repo](https://huggingface.co/datasets/HuggingFaceTB/smollm-corpus), with the `python-edu` subset being pulled from my [python-edu-cleaned repo](https://huggingface.co/datasets/Avelina/python-edu-cleaned). ## Dataset Structure The dataset is split into 24 subdirectories, with the first 23 containing 1000 shards and the 24th containing the final 698. The repository is structured as follows: ``` data00/ ├── train-00000-of-23698.jsonl.zst ├── ... └── train-00999-of-23698.jsonl.zst data01/ ├── train-01000-of-23698.jsonl.zst ├── ... └── train-01999-of-23698.jsonl.zst ... data22/ ├── train-22000-of-23698.jsonl.zst ├── ... └── train-22999-of-23698.jsonl.zst data23/ ├── train-23000-of-23698.jsonl.zst ├── ... └── train-23697-of-23698.jsonl.zst ``` In general, you can obtain the exact download URL for all shards using the following python function: ```py def get_url_from_shard( index: int ) -> str: if index >= 23_698: raise ValueError( f'Shard index must be less than 23,698 but received {index}' ) group = index // 1000 return f'https://huggingface.co/datasets/Avelina/smollm-corpus/resolve/main/data{group:02d}/train-{index:05d}-of-23698.jsonl.zst' ``` ## Generation Code Here is the code which was used to generate the shuffled shards. Note the use of non-contiguous interleaving in attempt to uniformly pull documents from across entire subsets to loosely decouple shard index from original document position. Please make sure you `pip install zstandard`!!! ```py import tqdm import datasets from datasets import load_dataset # Output directory and file format. Note that the file extension enforces zst compression is used. OUTPUT_FMT = '/YOUR/FILE/PATH/HERE/data/train-{index:05d}-of-{num_shards:05d}.jsonl.zst' # Total number of shards giving approximately 10,000 documents per shard OUTPUT_NUM_SHARDS = 23698 # Grab the three datasets ds_python = load_dataset( 'Avelina/python-edu-cleaned' ) ds_cosmo = load_dataset( 'HuggingFaceTB/smollm-corpus', 'cosmopedia-v2' ) ds_edu = load_dataset( 'HuggingFaceTB/smollm-corpus', 'fineweb-edu-dedup' ) # Retain only the text columns and the train splits ds_python = ds_python.select_columns( 'text' )[ 'train' ] ds_cosmo = ds_cosmo.select_columns( 'text' )[ 'train' ] ds_edu = ds_edu.select_columns( 'text' )[ 'train' ] # Iterate over all shards with a nice progbar for index in tqdm.tqdm( range( OUTPUT_NUM_SHARDS ) ): # Get non-contiguous in-memory sub-shards for the three datasets curr_python = ds_python.shard( num_shards=OUTPUT_NUM_SHARDS, index=index, contiguous=False, keep_in_memory=True ) curr_cosmo = ds_cosmo.shard( num_shards=OUTPUT_NUM_SHARDS, index=index, contiguous=False, keep_in_memory=True ) curr_edu = ds_edu.shard( num_shards=OUTPUT_NUM_SHARDS, index=index, contiguous=False, keep_in_memory=True ) # Concatenate the sub-shards curr_shard = datasets.concatenate_datasets( [ curr_python, curr_cosmo, curr_edu ] ) # Deterministically shuffle using the current shard index for reproducibility curr_shard = curr_shard.shuffle( seed=index, keep_in_memory=True ) # Dump the shards to .jsonl.zst curr_shard.to_json( OUTPUT_FMT.format( index=index, num_shards=OUTPUT_NUM_SHARDS ) ) ``` ## In-Memory Decompression Zstandard was chosen as it enables trivial in-memory decompression to minimise the storage impact of the dataset. Here is some example code which creates a python generator that yields each json line from a compressed shard stored at `file_name`, and a second function which creates a python generator that parses and yields the compressed shard. ```py import json from json import JSONDecodeError import zstandard def read_lines_zst( file_name ): # Open the file for reading in binary mode with open( file_name, 'rb' ) as file_handle: # Initialise an empty buffer buffer = '' # Create a reader for the opened file reader = zstandard.ZstdDecompressor( max_window_size=231 ).stream_reader( file_handle ) while True: # Read a chunk of up to 128MB chunk = reader.read( 227 ).decode() # If chunk is empty we've reached the end of the file and can break out if not chunk: break # Combine any prior buffer with the current chunk and split by newline lines = ( buffer + chunk ).split( '\n' ) # Yield the full lines so far for line in lines[ : -1 ]: yield line # The last 'line' is incomplete, so place in buffer for next chunk buffer = lines[ -1 ] # Always remember to close your reader! reader.close() def parse_jsonl_zst( file_name ): # Iterate over the yielded lines of the compressed shard for i, line in enumerate( read_lines_zst( file_name ) ): try: # Convert the line into a python dict and yield the text field yield json.loads( line )[ 'text' ] except ( KeyError, JSONDecodeError ): # Catch KeyError for 'text' not present in dict # Catch JSONDecodeError for malformed line print( f'JSON error @ shard={file_name}, line={i}' ) ``` Of course you could use HuggingFace's in-built streaming mechanics to handle things for you, but in my experience that approach is less reliable, doesn't handle `JSONDecodeError`s if there are malformed lines, can cause memory leaks, and has forced sharding behaviour when used inside a multi-worker PyTorch `DataLoader` which I've not yet found a way to disable!
fixie-ai/librispeech_asr	fixie-ai	"2024-08-05T18:38:33Z"	15,326	3	[ "language:en", "size_categories:100K<n<1M", "format:parquet", "modality:audio", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]	null	"2024-07-19T02:34:30Z"	--- language: - en dataset_info: - config_name: clean features: - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: text dtype: string - name: speaker_id dtype: int64 - name: chapter_id dtype: int64 - name: id dtype: string - name: continuation dtype: string splits: - name: test num_bytes: 623948478.48 num_examples: 2620 - name: validation num_bytes: 622190064.956 num_examples: 2703 - name: train.360 num_bytes: 41953890926.124 num_examples: 104014 - name: train.100 num_bytes: 11606313661.774 num_examples: 28539 download_size: 53886816833 dataset_size: 54806343131.334 - config_name: other features: - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: text dtype: string - name: speaker_id dtype: int64 - name: chapter_id dtype: int64 - name: id dtype: string - name: continuation dtype: string splits: - name: train.500 num_bytes: 57330687390.808 num_examples: 148688 - name: validation num_bytes: 591511495.496 num_examples: 2864 - name: test num_bytes: 616939198.113 num_examples: 2939 download_size: 57019309170 dataset_size: 58539138084.417 configs: - config_name: clean data_files: - split: test path: clean/test-* - split: validation path: clean/validation-* - split: train.360 path: clean/train.360-* - split: train.100 path: clean/train.100-* - config_name: other data_files: - split: train.500 path: other/train.500-* - split: validation path: other/validation-* - split: test path: other/test-* ---
parrotzone/sdxl-1.0	parrotzone	"2023-09-20T12:27:51Z"	15,274	12	[ "license:openrail++", "size_categories:1K<n<10K", "format:imagefolder", "modality:image", "library:datasets", "library:mlcroissant", "region:us" ]	null	"2023-07-31T07:18:18Z"	--- license: openrail++ --- # check [sdxl.parrotzone.art](https://sdxl.parrotzone.art) for easy viewing ⋆｡°✩ --- ## all images were made with SDXL 1.0 + the 0.9 VAE - steps: 20 - cfg scale: 7 - no refiner - random seeds
emozilla/Long-Data-Collections-Pretrain-Without-Books	emozilla	"2023-10-09T14:32:21Z"	15,251	1	[ "size_categories:1M<n<10M", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]	null	"2023-10-07T05:31:23Z"	--- configs: - config_name: default data_files: - split: train path: data/train-* dataset_info: features: - name: text dtype: string splits: - name: train num_bytes: 236565210292 num_examples: 9383848 download_size: 25749677954 dataset_size: 236565210292 --- # Dataset Card for "Long-Data-Collections-Pretrain-Without-Books" Paraquet version of the pretrain split of [togethercomputer/Long-Data-Collections](https://huggingface.co/datasets/togethercomputer/Long-Data-Collections) WITHOUT books Statistics (in # of characters): `total_len: 236088622215, average_len: 25159.041601590307`
Helsinki-NLP/opus_infopankki	Helsinki-NLP	"2024-02-22T15:10:55Z"	15,247	4	[ "task_categories:translation", "annotations_creators:found", "language_creators:found", "multilinguality:multilingual", "source_datasets:original", "language:ar", "language:en", "language:es", "language:et", "language:fa", "language:fi", "language:fr", "language:ru", "language:so", "language:sv", "language:tr", "language:zh", "license:cc-by-4.0", "size_categories:1M<n<10M", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]	[ "translation" ]	"2022-03-02T23:29:22Z"	--- annotations_creators: - found language_creators: - found language: - ar - en - es - et - fa - fi - fr - ru - so - sv - tr - zh license: cc-by-4.0 multilinguality: - multilingual size_categories: - 10K<n<100K source_datasets: - original task_categories: - translation task_ids: [] pretty_name: OpusInfopankki config_names: - ar-en - ar-es - ar-et - ar-fa - ar-fi - ar-fr - ar-ru - ar-so - ar-sv - ar-tr - ar-zh - en-es - en-et - en-fa - en-fi - en-fr - en-ru - en-so - en-sv - en-tr - en-zh - es-et - es-fa - es-fi - es-fr - es-ru - es-so - es-sv - es-tr - es-zh - et-fa - et-fi - et-fr - et-ru - et-so - et-sv - et-tr - et-zh - fa-fi - fa-fr - fa-ru - fa-so - fa-sv - fa-tr - fa-zh - fi-fr - fi-ru - fi-so - fi-sv - fi-tr - fi-zh - fr-ru - fr-so - fr-sv - fr-tr - fr-zh - ru-so - ru-sv - ru-tr - ru-zh - so-sv - so-tr - so-zh - sv-tr - sv-zh - tr-zh dataset_info: - config_name: ar-en features: - name: translation dtype: translation: languages: - ar - en splits: - name: train num_bytes: 10133337 num_examples: 50769 download_size: 2775475 dataset_size: 10133337 - config_name: ar-es features: - name: translation dtype: translation: languages: - ar - es splits: - name: train num_bytes: 8665355 num_examples: 40514 download_size: 2366264 dataset_size: 8665355 - config_name: ar-et features: - name: translation dtype: translation: languages: - ar - et splits: - name: train num_bytes: 9087555 num_examples: 46573 download_size: 2475165 dataset_size: 9087555 - config_name: ar-fa features: - name: translation dtype: translation: languages: - ar - fa splits: - name: train num_bytes: 12220196 num_examples: 47007 download_size: 3017006 dataset_size: 12220196 - config_name: ar-fi features: - name: translation dtype: translation: languages: - ar - fi splits: - name: train num_bytes: 9524265 num_examples: 49608 download_size: 2704144 dataset_size: 9524265 - config_name: ar-fr features: - name: translation dtype: translation: languages: - ar - fr splits: - name: train num_bytes: 8877629 num_examples: 41061 download_size: 2434048 dataset_size: 8877629 - config_name: ar-ru features: - name: translation dtype: translation: languages: - ar - ru splits: - name: train num_bytes: 13648194 num_examples: 50286 download_size: 3393441 dataset_size: 13648194 - config_name: ar-so features: - name: translation dtype: translation: languages: - ar - so splits: - name: train num_bytes: 9555548 num_examples: 44736 download_size: 2614055 dataset_size: 9555548 - config_name: ar-sv features: - name: translation dtype: translation: languages: - ar - sv splits: - name: train num_bytes: 8585135 num_examples: 43085 download_size: 2312217 dataset_size: 8585135 - config_name: ar-tr features: - name: translation dtype: translation: languages: - ar - tr splits: - name: train num_bytes: 8691077 num_examples: 41710 download_size: 2417172 dataset_size: 8691077 - config_name: ar-zh features: - name: translation dtype: translation: languages: - ar - zh splits: - name: train num_bytes: 5973634 num_examples: 29943 download_size: 1523722 dataset_size: 5973634 - config_name: en-es features: - name: translation dtype: translation: languages: - en - es splits: - name: train num_bytes: 6933983 num_examples: 42657 download_size: 2108422 dataset_size: 6933983 - config_name: en-et features: - name: translation dtype: translation: languages: - en - et splits: - name: train num_bytes: 8211562 num_examples: 58410 download_size: 2473732 dataset_size: 8211562 - config_name: en-fa features: - name: translation dtype: translation: languages: - en - fa splits: - name: train num_bytes: 10166305 num_examples: 48277 download_size: 2696051 dataset_size: 10166305 - config_name: en-fi features: - name: translation dtype: translation: languages: - en - fi splits: - name: train num_bytes: 10913601 num_examples: 84645 download_size: 3183398 dataset_size: 10913601 - config_name: en-fr features: - name: translation dtype: translation: languages: - en - fr splits: - name: train num_bytes: 8903183 num_examples: 56120 download_size: 2522185 dataset_size: 8903183 - config_name: en-ru features: - name: translation dtype: translation: languages: - en - ru splits: - name: train num_bytes: 15918195 num_examples: 75305 download_size: 3834067 dataset_size: 15918195 - config_name: en-so features: - name: translation dtype: translation: languages: - en - so splits: - name: train num_bytes: 7602290 num_examples: 47220 download_size: 2317274 dataset_size: 7602290 - config_name: en-sv features: - name: translation dtype: translation: languages: - en - sv splits: - name: train num_bytes: 7410975 num_examples: 51749 download_size: 2214196 dataset_size: 7410975 - config_name: en-tr features: - name: translation dtype: translation: languages: - en - tr splits: - name: train num_bytes: 6929154 num_examples: 44030 download_size: 2158897 dataset_size: 6929154 - config_name: en-zh features: - name: translation dtype: translation: languages: - en - zh splits: - name: train num_bytes: 4666963 num_examples: 29907 download_size: 1313255 dataset_size: 4666963 - config_name: es-et features: - name: translation dtype: translation: languages: - es - et splits: - name: train num_bytes: 6611956 num_examples: 42342 download_size: 2109076 dataset_size: 6611956 - config_name: es-fa features: - name: translation dtype: translation: languages: - es - fa splits: - name: train num_bytes: 9338210 num_examples: 41218 download_size: 2535729 dataset_size: 9338210 - config_name: es-fi features: - name: translation dtype: translation: languages: - es - fi splits: - name: train num_bytes: 6436298 num_examples: 41479 download_size: 2052254 dataset_size: 6436298 - config_name: es-fr features: - name: translation dtype: translation: languages: - es - fr splits: - name: train num_bytes: 7368724 num_examples: 41940 download_size: 2234633 dataset_size: 7368724 - config_name: es-ru features: - name: translation dtype: translation: languages: - es - ru splits: - name: train num_bytes: 9844937 num_examples: 41061 download_size: 2638368 dataset_size: 9844937 - config_name: es-so features: - name: translation dtype: translation: languages: - es - so splits: - name: train num_bytes: 7257038 num_examples: 41752 download_size: 2261851 dataset_size: 7257038 - config_name: es-sv features: - name: translation dtype: translation: languages: - es - sv splits: - name: train num_bytes: 6650652 num_examples: 41256 download_size: 2027874 dataset_size: 6650652 - config_name: es-tr features: - name: translation dtype: translation: languages: - es - tr splits: - name: train num_bytes: 7144065 num_examples: 42191 download_size: 2206245 dataset_size: 7144065 - config_name: es-zh features: - name: translation dtype: translation: languages: - es - zh splits: - name: train num_bytes: 4358751 num_examples: 26004 download_size: 1176333 dataset_size: 4358751 - config_name: et-fa features: - name: translation dtype: translation: languages: - et - fa splits: - name: train num_bytes: 9795996 num_examples: 47633 download_size: 2680445 dataset_size: 9795996 - config_name: et-fi features: - name: translation dtype: translation: languages: - et - fi splits: - name: train num_bytes: 7656989 num_examples: 57353 download_size: 2419554 dataset_size: 7656989 - config_name: et-fr features: - name: translation dtype: translation: languages: - et - fr splits: - name: train num_bytes: 7012430 num_examples: 44753 download_size: 2193006 dataset_size: 7012430 - config_name: et-ru features: - name: translation dtype: translation: languages: - et - ru splits: - name: train num_bytes: 12001391 num_examples: 55901 download_size: 3160673 dataset_size: 12001391 - config_name: et-so features: - name: translation dtype: translation: languages: - et - so splits: - name: train num_bytes: 7260797 num_examples: 46933 download_size: 2319211 dataset_size: 7260797 - config_name: et-sv features: - name: translation dtype: translation: languages: - et - sv splits: - name: train num_bytes: 6523041 num_examples: 46775 download_size: 2074448 dataset_size: 6523041 - config_name: et-tr features: - name: translation dtype: translation: languages: - et - tr splits: - name: train num_bytes: 6621665 num_examples: 43729 download_size: 2123880 dataset_size: 6621665 - config_name: et-zh features: - name: translation dtype: translation: languages: - et - zh splits: - name: train num_bytes: 4305273 num_examples: 27826 download_size: 1201275 dataset_size: 4305273 - config_name: fa-fi features: - name: translation dtype: translation: languages: - fa - fi splits: - name: train num_bytes: 9579257 num_examples: 46924 download_size: 2618699 dataset_size: 9579257 - config_name: fa-fr features: - name: translation dtype: translation: languages: - fa - fr splits: - name: train num_bytes: 9574254 num_examples: 41975 download_size: 2588917 dataset_size: 9574254 - config_name: fa-ru features: - name: translation dtype: translation: languages: - fa - ru splits: - name: train num_bytes: 13544451 num_examples: 47814 download_size: 3351553 dataset_size: 13544451 - config_name: fa-so features: - name: translation dtype: translation: languages: - fa - so splits: - name: train num_bytes: 10254723 num_examples: 45571 download_size: 2813443 dataset_size: 10254723 - config_name: fa-sv features: - name: translation dtype: translation: languages: - fa - sv splits: - name: train num_bytes: 9153752 num_examples: 43510 download_size: 2512908 dataset_size: 9153752 - config_name: fa-tr features: - name: translation dtype: translation: languages: - fa - tr splits: - name: train num_bytes: 9393209 num_examples: 42708 download_size: 2599794 dataset_size: 9393209 - config_name: fa-zh features: - name: translation dtype: translation: languages: - fa - zh splits: - name: train num_bytes: 5792439 num_examples: 27748 download_size: 1413779 dataset_size: 5792439 - config_name: fi-fr features: - name: translation dtype: translation: languages: - fi - fr splits: - name: train num_bytes: 8310851 num_examples: 55087 download_size: 2455971 dataset_size: 8310851 - config_name: fi-ru features: - name: translation dtype: translation: languages: - fi - ru splits: - name: train num_bytes: 15188168 num_examples: 74699 download_size: 3842831 dataset_size: 15188168 - config_name: fi-so features: - name: translation dtype: translation: languages: - fi - so splits: - name: train num_bytes: 7076221 num_examples: 46032 download_size: 2219872 dataset_size: 7076221 - config_name: fi-sv features: - name: translation dtype: translation: languages: - fi - sv splits: - name: train num_bytes: 6947224 num_examples: 51506 download_size: 2137629 dataset_size: 6947224 - config_name: fi-tr features: - name: translation dtype: translation: languages: - fi - tr splits: - name: train num_bytes: 6438716 num_examples: 42781 download_size: 2081615 dataset_size: 6438716 - config_name: fi-zh features: - name: translation dtype: translation: languages: - fi - zh splits: - name: train num_bytes: 4434168 num_examples: 29503 download_size: 1312557 dataset_size: 4434168 - config_name: fr-ru features: - name: translation dtype: translation: languages: - fr - ru splits: - name: train num_bytes: 12564196 num_examples: 54213 download_size: 3159587 dataset_size: 12564196 - config_name: fr-so features: - name: translation dtype: translation: languages: - fr - so splits: - name: train num_bytes: 7473559 num_examples: 42652 download_size: 2344399 dataset_size: 7473559 - config_name: fr-sv features: - name: translation dtype: translation: languages: - fr - sv splits: - name: train num_bytes: 7027563 num_examples: 43524 download_size: 2107653 dataset_size: 7027563 - config_name: fr-tr features: - name: translation dtype: translation: languages: - fr - tr splits: - name: train num_bytes: 7341078 num_examples: 43036 download_size: 2279611 dataset_size: 7341078 - config_name: fr-zh features: - name: translation dtype: translation: languages: - fr - zh splits: - name: train num_bytes: 4525109 num_examples: 26654 download_size: 1211652 dataset_size: 4525109 - config_name: ru-so features: - name: translation dtype: translation: languages: - ru - so splits: - name: train num_bytes: 10809193 num_examples: 45430 download_size: 2932790 dataset_size: 10809193 - config_name: ru-sv features: - name: translation dtype: translation: languages: - ru - sv splits: - name: train num_bytes: 10517433 num_examples: 47672 download_size: 2724280 dataset_size: 10517433 - config_name: ru-tr features: - name: translation dtype: translation: languages: - ru - tr splits: - name: train num_bytes: 9930592 num_examples: 42587 download_size: 2727600 dataset_size: 9930592 - config_name: ru-zh features: - name: translation dtype: translation: languages: - ru - zh splits: - name: train num_bytes: 6417808 num_examples: 29523 download_size: 1582749 dataset_size: 6417808 - config_name: so-sv features: - name: translation dtype: translation: languages: - so - sv splits: - name: train num_bytes: 6763754 num_examples: 42384 download_size: 2098877 dataset_size: 6763754 - config_name: so-tr features: - name: translation dtype: translation: languages: - so - tr splits: - name: train num_bytes: 7272349 num_examples: 43242 download_size: 2279999 dataset_size: 7272349 - config_name: so-zh features: - name: translation dtype: translation: languages: - so - zh splits: - name: train num_bytes: 4535955 num_examples: 27090 download_size: 1267321 dataset_size: 4535955 - config_name: sv-tr features: - name: translation dtype: translation: languages: - sv - tr splits: - name: train num_bytes: 6637744 num_examples: 42555 download_size: 2045078 dataset_size: 6637744 - config_name: sv-zh features: - name: translation dtype: translation: languages: - sv - zh splits: - name: train num_bytes: 4216405 num_examples: 26898 download_size: 1149609 dataset_size: 4216405 - config_name: tr-zh features: - name: translation dtype: translation: languages: - tr - zh splits: - name: train num_bytes: 4494071 num_examples: 27323 download_size: 1221951 dataset_size: 4494071 configs: - config_name: ar-en data_files: - split: train path: ar-en/train-* - config_name: ar-es data_files: - split: train path: ar-es/train-* - config_name: ar-et data_files: - split: train path: ar-et/train-* - config_name: ar-fa data_files: - split: train path: ar-fa/train-* - config_name: ar-fi data_files: - split: train path: ar-fi/train-* - config_name: ar-fr data_files: - split: train path: ar-fr/train-* - config_name: ar-ru data_files: - split: train path: ar-ru/train-* - config_name: ar-so data_files: - split: train path: ar-so/train-* - config_name: ar-sv data_files: - split: train path: ar-sv/train-* - config_name: ar-tr data_files: - split: train path: ar-tr/train-* - config_name: ar-zh data_files: - split: train path: ar-zh/train-* - config_name: en-es data_files: - split: train path: en-es/train-* - config_name: en-et data_files: - split: train path: en-et/train-* - config_name: en-fa data_files: - split: train path: en-fa/train-* - config_name: en-fi data_files: - split: train path: en-fi/train-* - config_name: en-fr data_files: - split: train path: en-fr/train-* - config_name: en-ru data_files: - split: train path: en-ru/train-* - config_name: en-so data_files: - split: train path: en-so/train-* - config_name: en-sv data_files: - split: train path: en-sv/train-* - config_name: en-tr data_files: - split: train path: en-tr/train-* - config_name: en-zh data_files: - split: train path: en-zh/train-* - config_name: es-et data_files: - split: train path: es-et/train-* - config_name: es-fa data_files: - split: train path: es-fa/train-* - config_name: es-fi data_files: - split: train path: es-fi/train-* - config_name: es-fr data_files: - split: train path: es-fr/train-* - config_name: es-ru data_files: - split: train path: es-ru/train-* - config_name: es-so data_files: - split: train path: es-so/train-* - config_name: es-sv data_files: - split: train path: es-sv/train-* - config_name: es-tr data_files: - split: train path: es-tr/train-* - config_name: es-zh data_files: - split: train path: es-zh/train-* - config_name: et-fa data_files: - split: train path: et-fa/train-* - config_name: et-fi data_files: - split: train path: et-fi/train-* - config_name: et-fr data_files: - split: train path: et-fr/train-* - config_name: et-ru data_files: - split: train path: et-ru/train-* - config_name: et-so data_files: - split: train path: et-so/train-* - config_name: et-sv data_files: - split: train path: et-sv/train-* - config_name: et-tr data_files: - split: train path: et-tr/train-* - config_name: et-zh data_files: - split: train path: et-zh/train-* - config_name: fa-fi data_files: - split: train path: fa-fi/train-* - config_name: fa-fr data_files: - split: train path: fa-fr/train-* - config_name: fa-ru data_files: - split: train path: fa-ru/train-* - config_name: fa-so data_files: - split: train path: fa-so/train-* - config_name: fa-sv data_files: - split: train path: fa-sv/train-* - config_name: fa-tr data_files: - split: train path: fa-tr/train-* - config_name: fa-zh data_files: - split: train path: fa-zh/train-* - config_name: fi-fr data_files: - split: train path: fi-fr/train-* - config_name: fi-ru data_files: - split: train path: fi-ru/train-* - config_name: fi-so data_files: - split: train path: fi-so/train-* - config_name: fi-sv data_files: - split: train path: fi-sv/train-* - config_name: fi-tr data_files: - split: train path: fi-tr/train-* - config_name: fi-zh data_files: - split: train path: fi-zh/train-* - config_name: fr-ru data_files: - split: train path: fr-ru/train-* - config_name: fr-so data_files: - split: train path: fr-so/train-* - config_name: fr-sv data_files: - split: train path: fr-sv/train-* - config_name: fr-tr data_files: - split: train path: fr-tr/train-* - config_name: fr-zh data_files: - split: train path: fr-zh/train-* - config_name: ru-so data_files: - split: train path: ru-so/train-* - config_name: ru-sv data_files: - split: train path: ru-sv/train-* - config_name: ru-tr data_files: - split: train path: ru-tr/train-* - config_name: ru-zh data_files: - split: train path: ru-zh/train-* - config_name: so-sv data_files: - split: train path: so-sv/train-* - config_name: so-tr data_files: - split: train path: so-tr/train-* - config_name: so-zh data_files: - split: train path: so-zh/train-* - config_name: sv-tr data_files: - split: train path: sv-tr/train-* - config_name: sv-zh data_files: - split: train path: sv-zh/train-* - config_name: tr-zh data_files: - split: train path: tr-zh/train-* --- # Dataset Card for infopankki ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - Homepage: https://opus.nlpl.eu/infopankki/corpus/version/infopankki - Repository: [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - Paper: [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - Leaderboard: [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - Point of Contact: [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Dataset Summary A parallel corpus of 12 languages, 66 bitexts. ### Supported Tasks and Leaderboards The underlying task is machine translation. ### Languages [More Information Needed] ## Dataset Structure ### Data Instances [More Information Needed] ### Data Fields [More Information Needed] ### Data Splits [More Information Needed] ## Dataset Creation ### Curation Rationale [More Information Needed] ### Source Data #### Initial Data Collection and Normalization Source: http://www.infopankki.fi via the Open Data API #### Who are the source language producers? [More Information Needed] ### Annotations #### Annotation process [More Information Needed] #### Who are the annotators? [More Information Needed] ### Personal and Sensitive Information [More Information Needed] ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed] ### Discussion of Biases [More Information Needed] ### Other Known Limitations [More Information Needed] ## Additional Information ### Dataset Curators [More Information Needed] ### Licensing Information Licensed under [CC-BY 4.0](https://creativecommons.org/licenses/by/4.0/). ### Citation Information If you use any part of the corpus in your own work, please cite the following article: ``` @inproceedings{tiedemann-2012-parallel, title = "Parallel Data, Tools and Interfaces in {OPUS}", author = {Tiedemann, J{\"o}rg}, editor = "Calzolari, Nicoletta and Choukri, Khalid and Declerck, Thierry and Do{\u{g}}an, Mehmet U{\u{g}}ur and Maegaard, Bente and Mariani, Joseph and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios", booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)", month = may, year = "2012", address = "Istanbul, Turkey", publisher = "European Language Resources Association (ELRA)", url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/463_Paper.pdf", pages = "2214--2218", abstract = "This paper presents the current status of OPUS, a growing language resource of parallel corpora and related tools. The focus in OPUS is to provide freely available data sets in various formats together with basic annotation to be useful for applications in computational linguistics, translation studies and cross-linguistic corpus studies. In this paper, we report about new data sets and their features, additional annotation tools and models provided from the website and essential interfaces and on-line services included in the project.", } ``` ### Contributions Thanks to [@patil-suraj](https://github.com/patil-suraj) for adding this dataset.
pietrolesci/pythia-deduped-stats-raw	pietrolesci	"2025-04-09T19:26:24Z"	15,193	0	[ "language:en", "size_categories:10M<n<100M", "format:parquet", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "arxiv:2406.04327", "region:us" ]	null	"2024-02-12T01:19:05Z"	--- language: - en --- This dataset has been created as an artefact of the paper [Causal Estimation of Memorisation Profiles (Lesci et al., 2024)](https://arxiv.org/abs/2406.04327). More info about this dataset in the related collection [Memorisation-Profiles](https://huggingface.co/collections/pietrolesci/memorisation-profiles-6619604c4594c878cd9d451f). Collection of data statistics computed using the intermediate checkpoints (step0, step1000, ..., step143k) of all Pythia deduped versions. This folder contains the model evaluations (or "stats") for each model size included in the study. This is the "raw" version where we have stats at the token level. We gathered these statistics "just in case" since the inference process was expensive. However, we provide the sequence-level statistics in the `pietrolesci/pythia-deduped-stats` dataset.
jxie/camelyon17	jxie	"2023-06-22T09:10:17Z"	15,192	0	[ "size_categories:1M<n<10M", "format:parquet", "modality:image", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]	null	"2023-06-20T19:19:23Z"	--- dataset_info: features: - name: image dtype: image - name: label dtype: class_label: names: '0': '0' '1': '1' splits: - name: id_train num_bytes: 1028118482.46 num_examples: 302436 - name: id_val num_bytes: 114778024.28 num_examples: 33560 - name: unlabeled_train num_bytes: 2167898085.29 num_examples: 600030 - name: ood_val num_bytes: 129021135.128 num_examples: 34904 - name: ood_test num_bytes: 276517018.354 num_examples: 85054 download_size: 2858780601 dataset_size: 3716332745.5119996 --- # Dataset Card for "camelyon17" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
Yelp/yelp_review_full	Yelp	"2024-01-04T17:14:53Z"	15,147	118	[ "task_categories:text-classification", "task_ids:sentiment-classification", "annotations_creators:crowdsourced", "language_creators:crowdsourced", "multilinguality:monolingual", "source_datasets:original", "language:en", "license:other", "size_categories:100K<n<1M", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "arxiv:1509.01626", "region:us" ]	[ "text-classification" ]	"2022-03-02T23:29:22Z"	--- annotations_creators: - crowdsourced language_creators: - crowdsourced language: - en license: - other multilinguality: - monolingual size_categories: - 100K<n<1M source_datasets: - original task_categories: - text-classification task_ids: - sentiment-classification pretty_name: YelpReviewFull license_details: yelp-licence dataset_info: config_name: yelp_review_full features: - name: label dtype: class_label: names: '0': 1 star '1': 2 star '2': 3 stars '3': 4 stars '4': 5 stars - name: text dtype: string splits: - name: train num_bytes: 483811554 num_examples: 650000 - name: test num_bytes: 37271188 num_examples: 50000 download_size: 322952369 dataset_size: 521082742 configs: - config_name: yelp_review_full data_files: - split: train path: yelp_review_full/train-* - split: test path: yelp_review_full/test-* default: true train-eval-index: - config: yelp_review_full task: text-classification task_id: multi_class_classification splits: train_split: train eval_split: test col_mapping: text: text label: target metrics: - type: accuracy name: Accuracy - type: f1 name: F1 macro args: average: macro - type: f1 name: F1 micro args: average: micro - type: f1 name: F1 weighted args: average: weighted - type: precision name: Precision macro args: average: macro - type: precision name: Precision micro args: average: micro - type: precision name: Precision weighted args: average: weighted - type: recall name: Recall macro args: average: macro - type: recall name: Recall micro args: average: micro - type: recall name: Recall weighted args: average: weighted --- --- # Dataset Card for YelpReviewFull ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - Homepage: [Yelp](https://www.yelp.com/dataset) - Repository: [Crepe](https://github.com/zhangxiangxiao/Crepe) - Paper: [Character-level Convolutional Networks for Text Classification](https://arxiv.org/abs/1509.01626) - Point of Contact: [Xiang Zhang](mailto:[email protected]) ### Dataset Summary The Yelp reviews dataset consists of reviews from Yelp. It is extracted from the Yelp Dataset Challenge 2015 data. ### Supported Tasks and Leaderboards - `text-classification`, `sentiment-classification`: The dataset is mainly used for text classification: given the text, predict the sentiment. ### Languages The reviews were mainly written in english. ## Dataset Structure ### Data Instances A typical data point, comprises of a text and the corresponding label. An example from the YelpReviewFull test set looks as follows: ``` { 'label': 0, 'text': 'I got \'new\' tires from them and within two weeks got a flat. I took my car to a local mechanic to see if i could get the hole patched, but they said the reason I had a flat was because the previous patch had blown - WAIT, WHAT? I just got the tire and never needed to have it patched? This was supposed to be a new tire. \\nI took the tire over to Flynn\'s and they told me that someone punctured my tire, then tried to patch it. So there are resentful tire slashers? I find that very unlikely. After arguing with the guy and telling him that his logic was far fetched he said he\'d give me a new tire \\"this time\\". \\nI will never go back to Flynn\'s b/c of the way this guy treated me and the simple fact that they gave me a used tire!' } ``` ### Data Fields - 'text': The review texts are escaped using double quotes ("), and any internal double quote is escaped by 2 double quotes (""). New lines are escaped by a backslash followed with an "n" character, that is "\n". - 'label': Corresponds to the score associated with the review (between 1 and 5). ### Data Splits The Yelp reviews full star dataset is constructed by randomly taking 130,000 training samples and 10,000 testing samples for each review star from 1 to 5. In total there are 650,000 trainig samples and 50,000 testing samples. ## Dataset Creation ### Curation Rationale The Yelp reviews full star dataset is constructed by Xiang Zhang ([email protected]) from the Yelp Dataset Challenge 2015. It is first used as a text classification benchmark in the following paper: Xiang Zhang, Junbo Zhao, Yann LeCun. Character-level Convolutional Networks for Text Classification. Advances in Neural Information Processing Systems 28 (NIPS 2015). ### Source Data #### Initial Data Collection and Normalization [More Information Needed] #### Who are the source language producers? [More Information Needed] ### Annotations #### Annotation process [More Information Needed] #### Who are the annotators? [More Information Needed] ### Personal and Sensitive Information [More Information Needed] ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed] ### Discussion of Biases [More Information Needed] ### Other Known Limitations [More Information Needed] ## Additional Information ### Dataset Curators [More Information Needed] ### Licensing Information You can check the official [yelp-dataset-agreement](https://s3-media3.fl.yelpcdn.com/assets/srv0/engineering_pages/bea5c1e92bf3/assets/vendor/yelp-dataset-agreement.pdf). ### Citation Information Xiang Zhang, Junbo Zhao, Yann LeCun. Character-level Convolutional Networks for Text Classification. Advances in Neural Information Processing Systems 28 (NIPS 2015). ### Contributions Thanks to [@hfawaz](https://github.com/hfawaz) for adding this dataset.
laion/strategic_game_chess	laion	"2023-10-20T04:14:20Z"	15,087	28	[ "license:cc-by-4.0", "size_categories:1M<n<10M", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us", "game" ]	null	"2023-06-06T02:09:13Z"	--- tags: - game pretty_name: The Chess Dataset license: cc-by-4.0 --- # Chess > Recent advancements in artificial intelligence (AI) underscore the progress of reasoning and planning shown by recent generalist machine learning (ML) models. The progress can be boosted by datasets that can further boost these generic capabilities when used for training foundation models of various kind. This research initiative has generated extensive synthetic datasets from complex games — chess, Rubik's Cube, and mazes — to study facilitation and the advancement of these critical generic skills in AI models. This dataset contains 3.2 billion games, equating to approximately 608 billion individual moves. it is generated through self-play by Stockfish engine using Fugaku and we add initial moves to expand its diversity. Each game has three columns: 'Moves', 'Termination' and 'Result', - 'Move': recorded chess moves of the whole game. - 'Termination': include CHECKMATE, INSUFFICIENT_MATERIAL, ... etc. - Please check this for detail information https://python-chess.readthedocs.io/en/latest/core.html#chess.Outcome.termination - 'Result': result of this game, 1-0, 1/2-1/2, 0-1. ### Call for Collaboration We invite interested researchers and ML practitioners to explore these datasets' potential. Whether training GPT models from scratch or fine-tuning pre-existing models, we encourage the exploration of various pre-training and fine-tuning strategies using these game-based datasets standalone or as enhancement of other already composed large-scale data. Our team is prepared to assist in securing necessary GPU resources for these explorations. We are particularly interested in collaborators eager to pre-train models of small to medium scale on our game data, subsequently transition to standard text-based training, and then perform comparative analyses against models of similar architecture trained exclusively on text data. Conclusively, this initiative marks a significant stride toward intricate problem-solving and strategic planning in AI, extending an open invitation to the research community for collaborative advancement in this domain.
taesiri/arxiv_audio	taesiri	"2023-12-22T04:56:39Z"	15,073	2	[ "license:cc-by-4.0", "size_categories:1K<n<10K", "format:text", "modality:audio", "modality:text", "library:datasets", "library:mlcroissant", "region:us" ]	null	"2023-07-03T03:46:57Z"	--- license: cc-by-4.0 ---
MERaLiON/Multitask-National-Speech-Corpus-v1	MERaLiON	"2025-01-21T03:54:47Z"	15,053	9	[ "size_categories:10M<n<100M", "format:parquet", "modality:audio", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "arxiv:2501.01034", "region:us" ]	null	"2024-11-28T02:20:03Z"	--- dataset_info: - config_name: ASR-PART1-Test features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 571211945.0 num_examples: 3000 download_size: 559850838 dataset_size: 571211945.0 - config_name: ASR-PART1-Train features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 385418198300.75 num_examples: 2258301 download_size: 377045178322 dataset_size: 385418198300.75 - config_name: ASR-PART2-Test features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 465911787.0 num_examples: 3000 download_size: 453955477 dataset_size: 465911787.0 - config_name: ASR-PART2-Train features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 363327397513.5 num_examples: 2473990 download_size: 353295436382 dataset_size: 363327397513.5 - config_name: ASR-PART3-Test features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 888128151.0 num_examples: 1000 download_size: 869839634 dataset_size: 888128151.0 - config_name: ASR-PART3-Train features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 85425161802.75 num_examples: 96245 download_size: 83617613004 dataset_size: 85425161802.75 - config_name: ASR-PART4-Test features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 840669815.0 num_examples: 1000 download_size: 840073363 dataset_size: 840669815.0 - config_name: ASR-PART4-Train features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 8086630962.75 num_examples: 9629 download_size: 8080765859 dataset_size: 8086630962.75 - config_name: ASR-PART5-Test features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 796429463.0 num_examples: 1000 download_size: 793697822 dataset_size: 796429463.0 - config_name: ASR-PART5-Train features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 19368760964.0 num_examples: 24320 download_size: 19307168143 dataset_size: 19368760964.0 - config_name: ASR-PART6-Test features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 778918943.0 num_examples: 1000 download_size: 776120504 dataset_size: 778918943.0 - config_name: ASR-PART6-Train features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 80452740634.25 num_examples: 103935 download_size: 80163834483 dataset_size: 80452740634.25 - config_name: PQA-AR-Dialogue-Test features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 2524213101.0 num_examples: 3000 download_size: 2502881430 dataset_size: 2524213101.0 - config_name: PQA-AR-Dialogue-Train features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 112833638040.5 num_examples: 130194 download_size: 110972595941 dataset_size: 112833638040.5 - config_name: PQA-AR-Sentence-Test features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 1037448188.0 num_examples: 6000 download_size: 1013575979 dataset_size: 1037448188.0 - config_name: PQA-AR-Sentence-Train features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 748962171712.25 num_examples: 4732291 download_size: 730150284902 dataset_size: 748962171712.25 - config_name: PQA-GR-Dialogue-Test features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 2524070317.0 num_examples: 3000 download_size: 2502849279 dataset_size: 2524070317.0 - config_name: PQA-GR-Dialogue-Train features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 112828111831.5 num_examples: 130194 download_size: 110971280799 dataset_size: 112828111831.5 - config_name: PQA-GR-Sentence-Test features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 1037310373.0 num_examples: 6000 download_size: 1013567377 dataset_size: 1037310373.0 - config_name: PQA-GR-Sentence-Train features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 748852926219.25 num_examples: 4732291 download_size: 730143237881 dataset_size: 748852926219.25 - config_name: SDS-PART3-Test features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 90554299.0 num_examples: 100 download_size: 89690527 dataset_size: 90554299.0 - config_name: SDS-PART3-Train features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 85422319098.75 num_examples: 96245 download_size: 83614162476 dataset_size: 85422319098.75 - config_name: SDS-PART4-Test features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 88940350.0 num_examples: 100 download_size: 88911005 dataset_size: 88940350.0 - config_name: SDS-PART4-Train features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 8085687190.75 num_examples: 9629 download_size: 8079929577 dataset_size: 8085687190.75 - config_name: SDS-PART5-Test features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 88124206.0 num_examples: 100 download_size: 87803731 dataset_size: 88124206.0 - config_name: SDS-PART5-Train features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 19367349094.0 num_examples: 24320 download_size: 19305847065 dataset_size: 19367349094.0 - config_name: SDS-PART6-Test features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 87732392.0 num_examples: 100 download_size: 87551938 dataset_size: 87732392.0 - config_name: SDS-PART6-Train features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 80449120699.25 num_examples: 103935 download_size: 80159781897 dataset_size: 80449120699.25 - config_name: SQA-PART3-Test features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 90552574.0 num_examples: 100 download_size: 89693755 dataset_size: 90552574.0 - config_name: SQA-PART3-Train features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 85376993587.0 num_examples: 96232 download_size: 83585944443 dataset_size: 85376993587.0 - config_name: SQA-PART4-Test features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 88935324.0 num_examples: 100 download_size: 88913332 dataset_size: 88935324.0 - config_name: SQA-PART4-Train features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 8080383599.5 num_examples: 9626 download_size: 8076488125 dataset_size: 8080383599.5 - config_name: SQA-PART5-Test features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 88115583.0 num_examples: 100 download_size: 87803336 dataset_size: 88115583.0 - config_name: SQA-PART5-Train features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 19354344382.25 num_examples: 24311 download_size: 19296773516 dataset_size: 19354344382.25 - config_name: SQA-PART6-Test features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 87727131.0 num_examples: 100 download_size: 87554027 dataset_size: 87727131.0 - config_name: SQA-PART6-Train features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 80401794701.0 num_examples: 103908 download_size: 80128135250 dataset_size: 80401794701.0 configs: - config_name: ASR-PART1-Test data_files: - split: train path: ASR-PART1-Test/train-* - config_name: ASR-PART1-Train data_files: - split: train path: ASR-PART1-Train/train-* - config_name: ASR-PART2-Test data_files: - split: train path: ASR-PART2-Test/train-* - config_name: ASR-PART2-Train data_files: - split: train path: ASR-PART2-Train/train-* - config_name: ASR-PART3-Test data_files: - split: train path: ASR-PART3-Test/train-* - config_name: ASR-PART3-Train data_files: - split: train path: ASR-PART3-Train/train-* - config_name: ASR-PART4-Test data_files: - split: train path: ASR-PART4-Test/train-* - config_name: ASR-PART4-Train data_files: - split: train path: ASR-PART4-Train/train-* - config_name: ASR-PART5-Test data_files: - split: train path: ASR-PART5-Test/train-* - config_name: ASR-PART5-Train data_files: - split: train path: ASR-PART5-Train/train-* - config_name: ASR-PART6-Test data_files: - split: train path: ASR-PART6-Test/train-* - config_name: ASR-PART6-Train data_files: - split: train path: ASR-PART6-Train/train-* - config_name: PQA-AR-Dialogue-Test data_files: - split: train path: PQA-AR-Dialogue-Test/train-* - config_name: PQA-AR-Dialogue-Train data_files: - split: train path: PQA-AR-Dialogue-Train/train-* - config_name: PQA-AR-Sentence-Test data_files: - split: train path: PQA-AR-Sentence-Test/train-* - config_name: PQA-AR-Sentence-Train data_files: - split: train path: PQA-AR-Sentence-Train/train-* - config_name: PQA-GR-Dialogue-Test data_files: - split: train path: PQA-GR-Dialogue-Test/train-* - config_name: PQA-GR-Dialogue-Train data_files: - split: train path: PQA-GR-Dialogue-Train/train-* - config_name: PQA-GR-Sentence-Test data_files: - split: train path: PQA-GR-Sentence-Test/train-* - config_name: PQA-GR-Sentence-Train data_files: - split: train path: PQA-GR-Sentence-Train/train-* - config_name: SDS-PART3-Test data_files: - split: train path: SDS-PART3-Test/train-* - config_name: SDS-PART3-Train data_files: - split: train path: SDS-PART3-Train/train-* - config_name: SDS-PART4-Test data_files: - split: train path: SDS-PART4-Test/train-* - config_name: SDS-PART4-Train data_files: - split: train path: SDS-PART4-Train/train-* - config_name: SDS-PART5-Test data_files: - split: train path: SDS-PART5-Test/train-* - config_name: SDS-PART5-Train data_files: - split: train path: SDS-PART5-Train/train-* - config_name: SDS-PART6-Test data_files: - split: train path: SDS-PART6-Test/train-* - config_name: SDS-PART6-Train data_files: - split: train path: SDS-PART6-Train/train-* - config_name: SQA-PART3-Test data_files: - split: train path: SQA-PART3-Test/train-* - config_name: SQA-PART3-Train data_files: - split: train path: SQA-PART3-Train/train-* - config_name: SQA-PART4-Test data_files: - split: train path: SQA-PART4-Test/train-* - config_name: SQA-PART4-Train data_files: - split: train path: SQA-PART4-Train/train-* - config_name: SQA-PART5-Test data_files: - split: train path: SQA-PART5-Test/train-* - config_name: SQA-PART5-Train data_files: - split: train path: SQA-PART5-Train/train-* - config_name: SQA-PART6-Test data_files: - split: train path: SQA-PART6-Test/train-* - config_name: SQA-PART6-Train data_files: - split: train path: SQA-PART6-Train/train-* --- Multitask-National-Speech-Corpus (MNSC v1) is derived from [IMDA's NSC Corpus](https://www.imda.gov.sg/how-we-can-help/national-speech-corpus). MNSC is a multitask speech understanding dataset derived and further annotated from IMDA NSC Corpus. It focuses on the knowledge of Singapore's local accent, localised terms, and code-switching. - ASR: Automatic Speech Recognition - SQA: Speech Question Answering - SDS: Spoken Dialogue Summarization - PQA: Paralinguistic Question Answering ``` from datasets import load_dataset data = load_dataset('MERaLiON/Multitask-National-Speech-Corpus-v1', data_dir='ASR-PART1-Train')['train'] ``` ``` @article{wang2025advancing, title={Advancing Singlish Understanding: Bridging the Gap with Datasets and Multimodal Models}, author={Wang, Bin and Zou, Xunlong and Sun, Shuo and Zhang, Wenyu and He, Yingxu and Liu, Zhuohan and Wei, Chengwei and Chen, Nancy F and Aw, AiTi}, journal={arXiv preprint arXiv:2501.01034}, year={2025} } ```
laion/LAION-Audio-300M	laion	"2025-01-10T21:33:57Z"	15,032	28	[ "license:apache-2.0", "size_categories:100M<n<1B", "format:webdataset", "modality:audio", "modality:text", "library:datasets", "library:webdataset", "library:mlcroissant", "region:us" ]	null	"2024-12-29T09:50:41Z"	--- license: apache-2.0 ---
davanstrien/AmericanStories-parquet	davanstrien	"2023-10-20T15:09:54Z"	15,026	2	[ "size_categories:10M<n<100M", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]	null	"2023-10-20T14:07:00Z"	--- configs: - config_name: default data_files: - split: '1774' path: data/1774-* - split: '1798' path: data/1798-* - split: '1799' path: data/1799-* - split: '1800' path: data/1800-* - split: '1801' path: data/1801-* - split: '1802' path: data/1802-* - split: '1803' path: data/1803-* - split: '1804' path: data/1804-* - split: '1805' path: data/1805-* - split: '1806' path: data/1806-* - split: '1807' path: data/1807-* - split: '1808' path: data/1808-* - split: '1809' path: data/1809-* - split: '1810' path: data/1810-* - split: '1811' path: data/1811-* - split: '1812' path: data/1812-* - split: '1813' path: data/1813-* - split: '1814' path: data/1814-* - split: '1815' path: data/1815-* - split: '1816' path: data/1816-* - split: '1817' path: data/1817-* - split: '1818' path: data/1818-* - split: '1819' path: data/1819-* - split: '1820' path: data/1820-* - split: '1821' path: data/1821-* - split: '1822' path: data/1822-* - split: '1823' path: data/1823-* - split: '1824' path: data/1824-* - split: '1825' path: data/1825-* - split: '1826' path: data/1826-* - split: '1827' path: data/1827-* - split: '1828' path: data/1828-* - split: '1829' path: data/1829-* - split: '1830' path: data/1830-* - split: '1831' path: data/1831-* - split: '1832' path: data/1832-* - split: '1833' path: data/1833-* - split: '1834' path: data/1834-* - split: '1835' path: data/1835-* - split: '1836' path: data/1836-* - split: '1837' path: data/1837-* - split: '1838' path: data/1838-* - split: '1839' path: data/1839-* - split: '1840' path: data/1840-* - split: '1841' path: data/1841-* - split: '1842' path: data/1842-* - split: '1843' path: data/1843-* - split: '1844' path: data/1844-* - split: '1845' path: data/1845-* - split: '1846' path: data/1846-* - split: '1847' path: data/1847-* - split: '1848' path: data/1848-* - split: '1849' path: data/1849-* - split: '1850' path: data/1850-* - split: '1851' path: data/1851-* - split: '1852' path: data/1852-* - split: '1853' path: data/1853-* - split: '1854' path: data/1854-* - split: '1855' path: data/1855-* - split: '1856' path: data/1856-* - split: '1857' path: data/1857-* - split: '1858' path: data/1858-* - split: '1859' path: data/1859-* - split: '1860' path: data/1860-* - split: '1861' path: data/1861-* - split: '1862' path: data/1862-* - split: '1863' path: data/1863-* - split: '1864' path: data/1864-* - split: '1865' path: data/1865-* - split: '1866' path: data/1866-* - split: '1867' path: data/1867-* - split: '1868' path: data/1868-* - split: '1869' path: data/1869-* - split: '1870' path: data/1870-* - split: '1871' path: data/1871-* - split: '1872' path: data/1872-* - split: '1873' path: data/1873-* - split: '1874' path: data/1874-* - split: '1875' path: data/1875-* - split: '1876' path: data/1876-* - split: '1877' path: data/1877-* - split: '1878' path: data/1878-* - split: '1879' path: data/1879-* - split: '1880' path: data/1880-* - split: '1881' path: data/1881-* - split: '1882' path: data/1882-* - split: '1883' path: data/1883-* - split: '1884' path: data/1884-* - split: '1885' path: data/1885-* - split: '1886' path: data/1886-* - split: '1887' path: data/1887-* - split: '1888' path: data/1888-* - split: '1889' path: data/1889-* - split: '1890' path: data/1890-* - split: '1891' path: data/1891-* - split: '1892' path: data/1892-* - split: '1893' path: data/1893-* - split: '1894' path: data/1894-* - split: '1895' path: data/1895-* - split: '1896' path: data/1896-* - split: '1897' path: data/1897-* - split: '1898' path: data/1898-* - split: '1899' path: data/1899-* - split: '1900' path: data/1900-* - split: '1901' path: data/1901-* - split: '1902' path: data/1902-* - split: '1903' path: data/1903-* - split: '1904' path: data/1904-* - split: '1905' path: data/1905-* - split: '1906' path: data/1906-* - split: '1907' path: data/1907-* - split: '1908' path: data/1908-* - split: '1909' path: data/1909-* - split: '1910' path: data/1910-* - split: '1911' path: data/1911-* - split: '1912' path: data/1912-* - split: '1913' path: data/1913-* - split: '1914' path: data/1914-* - split: '1915' path: data/1915-* - split: '1916' path: data/1916-* - split: '1917' path: data/1917-* - split: '1918' path: data/1918-* - split: '1919' path: data/1919-* - split: '1920' path: data/1920-* - split: '1921' path: data/1921-* - split: '1922' path: data/1922-* - split: '1923' path: data/1923-* - split: '1924' path: data/1924-* - split: '1925' path: data/1925-* - split: '1926' path: data/1926-* - split: '1927' path: data/1927-* - split: '1928' path: data/1928-* - split: '1929' path: data/1929-* - split: '1930' path: data/1930-* - split: '1931' path: data/1931-* - split: '1932' path: data/1932-* - split: '1933' path: data/1933-* - split: '1934' path: data/1934-* - split: '1935' path: data/1935-* - split: '1936' path: data/1936-* - split: '1937' path: data/1937-* - split: '1938' path: data/1938-* - split: '1939' path: data/1939-* - split: '1940' path: data/1940-* - split: '1941' path: data/1941-* - split: '1942' path: data/1942-* - split: '1943' path: data/1943-* - split: '1944' path: data/1944-* - split: '1945' path: data/1945-* - split: '1946' path: data/1946-* - split: '1947' path: data/1947-* - split: '1948' path: data/1948-* - split: '1949' path: data/1949-* - split: '1950' path: data/1950-* - split: '1951' path: data/1951-* - split: '1952' path: data/1952-* - split: '1953' path: data/1953-* - split: '1954' path: data/1954-* - split: '1955' path: data/1955-* - split: '1956' path: data/1956-* - split: '1957' path: data/1957-* - split: '1958' path: data/1958-* - split: '1959' path: data/1959-* - split: '1960' path: data/1960-* - split: '1961' path: data/1961-* - split: '1962' path: data/1962-* - split: '1963' path: data/1963-* dataset_info: features: - name: article_id dtype: string - name: newspaper_name dtype: string - name: edition dtype: string - name: date dtype: string - name: page dtype: string - name: headline dtype: string - name: byline dtype: string - name: article dtype: string splits: - name: '1774' num_bytes: 22245 num_examples: 12 - name: '1798' num_bytes: 72288 num_examples: 73 - name: '1799' num_bytes: 946373 num_examples: 623 - name: '1800' num_bytes: 38139 num_examples: 45 - name: '1801' num_bytes: 94991 num_examples: 93 - name: '1802' num_bytes: 1463322 num_examples: 1158 - name: '1803' num_bytes: 799797 num_examples: 654 - name: '1804' num_bytes: 120141 num_examples: 103 - name: '1805' num_bytes: 2475205 num_examples: 2303 - name: '1806' num_bytes: 2043729 num_examples: 1860 - name: '1807' num_bytes: 310568 num_examples: 315 - name: '1808' num_bytes: 75639 num_examples: 45 - name: '1809' num_bytes: 430706 num_examples: 422 - name: '1810' num_bytes: 1319755 num_examples: 982 - name: '1811' num_bytes: 117701 num_examples: 110 - name: '1812' num_bytes: 75299 num_examples: 67 - name: '1813' num_bytes: 290966 num_examples: 242 - name: '1814' num_bytes: 378212 num_examples: 379 - name: '1815' num_bytes: 185179 num_examples: 160 - name: '1816' num_bytes: 495706 num_examples: 409 - name: '1817' num_bytes: 446354 num_examples: 394 - name: '1818' num_bytes: 1257916 num_examples: 1108 - name: '1819' num_bytes: 2476297 num_examples: 1997 - name: '1820' num_bytes: 611884 num_examples: 433 - name: '1821' num_bytes: 347361 num_examples: 270 - name: '1822' num_bytes: 286227 num_examples: 264 - name: '1823' num_bytes: 2030816 num_examples: 1113 - name: '1824' num_bytes: 5171191 num_examples: 3110 - name: '1825' num_bytes: 6341915 num_examples: 4005 - name: '1826' num_bytes: 10462258 num_examples: 7079 - name: '1827' num_bytes: 11634621 num_examples: 7213 - name: '1828' num_bytes: 10253681 num_examples: 6350 - name: '1829' num_bytes: 4021832 num_examples: 2296 - name: '1830' num_bytes: 8321949 num_examples: 4232 - name: '1831' num_bytes: 16796125 num_examples: 9699 - name: '1832' num_bytes: 9982722 num_examples: 6565 - name: '1833' num_bytes: 6653515 num_examples: 4108 - name: '1834' num_bytes: 7099875 num_examples: 4632 - name: '1835' num_bytes: 9066392 num_examples: 6168 - name: '1836' num_bytes: 10473366 num_examples: 7375 - name: '1837' num_bytes: 21002773 num_examples: 13609 - name: '1838' num_bytes: 13735809 num_examples: 8492 - name: '1839' num_bytes: 12512339 num_examples: 8938 - name: '1840' num_bytes: 12647911 num_examples: 8052 - name: '1841' num_bytes: 39146669 num_examples: 30019 - name: '1842' num_bytes: 26218700 num_examples: 21290 - name: '1843' num_bytes: 50447372 num_examples: 41657 - name: '1844' num_bytes: 79351064 num_examples: 61373 - name: '1845' num_bytes: 131632573 num_examples: 95921 - name: '1846' num_bytes: 81086068 num_examples: 70331 - name: '1847' num_bytes: 32733527 num_examples: 24354 - name: '1848' num_bytes: 44577825 num_examples: 32531 - name: '1849' num_bytes: 53877014 num_examples: 42711 - name: '1850' num_bytes: 76697622 num_examples: 49992 - name: '1851' num_bytes: 128372084 num_examples: 90184 - name: '1852' num_bytes: 67005975 num_examples: 51172 - name: '1853' num_bytes: 54210932 num_examples: 48130 - name: '1854' num_bytes: 150406197 num_examples: 118825 - name: '1855' num_bytes: 115893679 num_examples: 99390 - name: '1856' num_bytes: 188859881 num_examples: 157592 - name: '1857' num_bytes: 152841585 num_examples: 129179 - name: '1858' num_bytes: 214657030 num_examples: 171877 - name: '1859' num_bytes: 178711188 num_examples: 160924 - name: '1860' num_bytes: 163889573 num_examples: 150590 - name: '1861' num_bytes: 215595661 num_examples: 173990 - name: '1862' num_bytes: 228323685 num_examples: 171021 - name: '1863' num_bytes: 197294365 num_examples: 151485 - name: '1864' num_bytes: 125113713 num_examples: 94415 - name: '1865' num_bytes: 133515217 num_examples: 99728 - name: '1866' num_bytes: 180768118 num_examples: 135316 - name: '1867' num_bytes: 213571876 num_examples: 161180 - name: '1868' num_bytes: 202156635 num_examples: 140521 - name: '1869' num_bytes: 236506656 num_examples: 171455 - name: '1870' num_bytes: 242779857 num_examples: 174061 - name: '1871' num_bytes: 203189927 num_examples: 151652 - name: '1872' num_bytes: 242624062 num_examples: 194784 - name: '1873' num_bytes: 302626176 num_examples: 241902 - name: '1874' num_bytes: 280814742 num_examples: 213813 - name: '1875' num_bytes: 319815222 num_examples: 274269 - name: '1876' num_bytes: 381483980 num_examples: 288199 - name: '1877' num_bytes: 317703263 num_examples: 254946 - name: '1878' num_bytes: 381274032 num_examples: 307865 - name: '1879' num_bytes: 371703798 num_examples: 287784 - name: '1880' num_bytes: 296465631 num_examples: 272352 - name: '1881' num_bytes: 294568051 num_examples: 270228 - name: '1882' num_bytes: 340511400 num_examples: 311920 - name: '1883' num_bytes: 419078041 num_examples: 387589 - name: '1884' num_bytes: 329666364 num_examples: 304242 - name: '1885' num_bytes: 348144660 num_examples: 318732 - name: '1886' num_bytes: 431746663 num_examples: 423718 - name: '1887' num_bytes: 493647568 num_examples: 494559 - name: '1888' num_bytes: 564523528 num_examples: 547165 - name: '1889' num_bytes: 558168324 num_examples: 536750 - name: '1890' num_bytes: 566964770 num_examples: 540615 - name: '1891' num_bytes: 641124243 num_examples: 620461 - name: '1892' num_bytes: 524812242 num_examples: 527044 - name: '1893' num_bytes: 645853680 num_examples: 656805 - name: '1894' num_bytes: 790577208 num_examples: 795408 - name: '1895' num_bytes: 890097151 num_examples: 897766 - name: '1896' num_bytes: 1235234882 num_examples: 1175701 - name: '1897' num_bytes: 1252347746 num_examples: 1275895 - name: '1898' num_bytes: 1286411001 num_examples: 1323842 - name: '1899' num_bytes: 1176418162 num_examples: 1218682 - name: '1900' num_bytes: 1069983237 num_examples: 1118970 - name: '1901' num_bytes: 1478945214 num_examples: 1468648 - name: '1902' num_bytes: 1376703767 num_examples: 1417935 - name: '1903' num_bytes: 1255538379 num_examples: 1319686 - name: '1904' num_bytes: 1232185827 num_examples: 1340868 - name: '1905' num_bytes: 1563178627 num_examples: 1635134 - name: '1906' num_bytes: 1632815247 num_examples: 1683643 - name: '1907' num_bytes: 1647491794 num_examples: 1714613 - name: '1908' num_bytes: 1771267430 num_examples: 1842874 - name: '1909' num_bytes: 1844179657 num_examples: 1926228 - name: '1910' num_bytes: 1589052587 num_examples: 1684263 - name: '1911' num_bytes: 1402309564 num_examples: 1510259 - name: '1912' num_bytes: 1621648367 num_examples: 1774149 - name: '1913' num_bytes: 1613599136 num_examples: 1822206 - name: '1914' num_bytes: 1736284455 num_examples: 1931901 - name: '1915' num_bytes: 1690248452 num_examples: 1878654 - name: '1916' num_bytes: 1633563499 num_examples: 1838797 - name: '1917' num_bytes: 1605677226 num_examples: 1810757 - name: '1918' num_bytes: 1803695589 num_examples: 1920102 - name: '1919' num_bytes: 1831703767 num_examples: 1981192 - name: '1920' num_bytes: 1901882705 num_examples: 2041192 - name: '1921' num_bytes: 2264618667 num_examples: 2334112 - name: '1922' num_bytes: 2372137567 num_examples: 2405974 - name: '1923' num_bytes: 812177597 num_examples: 880372 - name: '1924' num_bytes: 800835690 num_examples: 845520 - name: '1925' num_bytes: 601426023 num_examples: 662322 - name: '1926' num_bytes: 565307890 num_examples: 623765 - name: '1927' num_bytes: 460501197 num_examples: 504835 - name: '1928' num_bytes: 452526140 num_examples: 487302 - name: '1929' num_bytes: 366246066 num_examples: 421909 - name: '1930' num_bytes: 437657836 num_examples: 492695 - name: '1931' num_bytes: 441972257 num_examples: 493816 - name: '1932' num_bytes: 640501746 num_examples: 664615 - name: '1933' num_bytes: 634373318 num_examples: 642380 - name: '1934' num_bytes: 641841040 num_examples: 654342 - name: '1935' num_bytes: 612406176 num_examples: 635554 - name: '1936' num_bytes: 621035178 num_examples: 662015 - name: '1937' num_bytes: 625107933 num_examples: 676549 - name: '1938' num_bytes: 616370880 num_examples: 665274 - name: '1939' num_bytes: 525913265 num_examples: 556283 - name: '1940' num_bytes: 471830118 num_examples: 496662 - name: '1941' num_bytes: 599694786 num_examples: 637200 - name: '1942' num_bytes: 508785410 num_examples: 523923 - name: '1943' num_bytes: 452079475 num_examples: 467200 - name: '1944' num_bytes: 442871777 num_examples: 433769 - name: '1945' num_bytes: 588623743 num_examples: 588477 - name: '1946' num_bytes: 526027876 num_examples: 470895 - name: '1947' num_bytes: 461281363 num_examples: 393086 - name: '1948' num_bytes: 442999943 num_examples: 396660 - name: '1949' num_bytes: 421752000 num_examples: 419854 - name: '1950' num_bytes: 403717616 num_examples: 415416 - name: '1951' num_bytes: 409600217 num_examples: 419622 - name: '1952' num_bytes: 397051717 num_examples: 396420 - name: '1953' num_bytes: 366253682 num_examples: 358332 - name: '1954' num_bytes: 263197428 num_examples: 266338 - name: '1955' num_bytes: 268993926 num_examples: 273576 - name: '1956' num_bytes: 85126796 num_examples: 98035 - name: '1957' num_bytes: 83757036 num_examples: 93543 - name: '1958' num_bytes: 85807593 num_examples: 98688 - name: '1959' num_bytes: 112707174 num_examples: 129452 - name: '1960' num_bytes: 300484826 num_examples: 344550 - name: '1961' num_bytes: 297225753 num_examples: 339076 - name: '1962' num_bytes: 231525869 num_examples: 264724 - name: '1963' num_bytes: 197520960 num_examples: 226859 download_size: 48388744959 dataset_size: 76303058024 --- # Dataset Card for "AmericanStories-parquet" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
Avelina/smollm-corpus	Avelina	"2025-01-11T16:41:28Z"	15,023	5	[ "task_categories:text-generation", "language:en", "license:odc-by", "size_categories:100M<n<1B", "region:us" ]	[ "text-generation" ]	"2025-01-11T01:39:39Z"	--- license: odc-by dataset_info: - config_name: default features: - name: text dtype: string configs: - config_name: default data_files: - split: train path: data/train- task_categories: - text-generation language: - en size_categories: - 100M<n<1B --- # SmolLM-Corpus: Now shuffled and sharded! This is a version of the SmolLM-Corpus where the 3 subsets have been interleved, shuffled and sharded as 23698 `jsonl.zst` files for easy streaming! The dataset is comprised of the `cosmopedia-v2` and `fineweb-edu-dedup` subsets from the original [SmolLM-Corpus repo](https://huggingface.co/datasets/HuggingFaceTB/smollm-corpus), with the `python-edu` subset being pulled from my [python-edu repo](https://huggingface.co/datasets/Avelina/python-edu). ## Dataset Structure The dataset is split into 24 subdirectories, with the first 23 containing 1000 shards and the 24th containing the final 698. The repository is structured as follows: ``` data00/ ├── train-00000-of-23698.jsonl.zst ├── ... └── train-00999-of-23698.jsonl.zst data01/ ├── train-01000-of-23698.jsonl.zst ├── ... └── train-01999-of-23698.jsonl.zst ... data22/ ├── train-22000-of-23698.jsonl.zst ├── ... └── train-22999-of-23698.jsonl.zst data23/ ├── train-23000-of-23698.jsonl.zst ├── ... └── train-23697-of-23698.jsonl.zst ``` In general, you can obtain the exact download URL for all shards using the following python function: ```py def get_url_from_shard( index: int ) -> str: if index >= 23_698: raise ValueError( f'Shard index must be less than 23,698 but received {index}' ) group = index // 1000 return f'https://huggingface.co/datasets/Avelina/smollm-corpus/resolve/main/data{group:02d}/train-{index:05d}-of-23698.jsonl.zst' ``` ## Generation Code Here is the code which was used to generate the shuffled shards. Note the use of non-contiguous interleaving in attempt to uniformly pull documents from across entire subsets to loosely decouple shard index from original document position. Please make sure you `pip install zstandard`!!! ```py import tqdm import datasets from datasets import load_dataset # Output directory and file format. Note that the file extension enforces zst compression is used. OUTPUT_FMT = '/YOUR/FILE/PATH/HERE/data/train-{index:05d}-of-{num_shards:05d}.jsonl.zst' # Total number of shards giving approximately 10,000 documents per shard OUTPUT_NUM_SHARDS = 23698 # Grab the three datasets ds_python = load_dataset( 'Avelina/python-edu' ) ds_cosmo = load_dataset( 'HuggingFaceTB/smollm-corpus', 'cosmopedia-v2' ) ds_edu = load_dataset( 'HuggingFaceTB/smollm-corpus', 'fineweb-edu-dedup' ) # Retain only the text columns and the train splits ds_python = ds_python.select_columns( 'text' )[ 'train' ] ds_cosmo = ds_cosmo.select_columns( 'text' )[ 'train' ] ds_edu = ds_edu.select_columns( 'text' )[ 'train' ] # Iterate over all shards with a nice progbar for index in tqdm.tqdm( range( OUTPUT_NUM_SHARDS ) ): # Get non-contiguous in-memory sub-shards for the three datasets curr_python = ds_python.shard( num_shards=OUTPUT_NUM_SHARDS, index=index, contiguous=False, keep_in_memory=True ) curr_cosmo = ds_cosmo.shard( num_shards=OUTPUT_NUM_SHARDS, index=index, contiguous=False, keep_in_memory=True ) curr_edu = ds_edu.shard( num_shards=OUTPUT_NUM_SHARDS, index=index, contiguous=False, keep_in_memory=True ) # Concatenate the sub-shards curr_shard = datasets.concatenate_datasets( [ curr_python, curr_cosmo, curr_edu ] ) # Deterministically shuffle using the current shard index for reproducibility curr_shard = curr_shard.shuffle( seed=index, keep_in_memory=True ) # Dump the shards to .jsonl.zst curr_shard.to_json( OUTPUT_FMT.format( index=index, num_shards=OUTPUT_NUM_SHARDS ) ) ``` ## In-Memory Decompression Zstandard was chosen as it enables trivial in-memory decompression to minimise the storage impact of the dataset. Here is some example code which creates a python generator that yields each json line from a compressed shard stored at `file_name`, and a second function which creates a python generator that parses and yields the compressed shard. ```py import json from json import JSONDecodeError import zstandard def read_lines_zst( file_name ): # Open the file for reading in binary mode with open( file_name, 'rb' ) as file_handle: # Initialise an empty buffer buffer = '' # Create a reader for the opened file reader = zstandard.ZstdDecompressor( max_window_size=231 ).stream_reader( file_handle ) while True: # Read a chunk of up to 128MB chunk = reader.read( 227 ).decode() # If chunk is empty we've reached the end of the file and can break out if not chunk: break # Combine any prior buffer with the current chunk and split by newline lines = ( buffer + chunk ).split( '\n' ) # Yield the full lines so far for line in lines[ : -1 ]: yield line # The last 'line' is incomplete, so place in buffer for next chunk buffer = lines[ -1 ] # Always remember to close your reader! reader.close() def parse_jsonl_zst( file_name ): # Iterate over the yielded lines of the compressed shard for i, line in enumerate( read_lines_zst( file_name ) ): try: # Convert the line into a python dict and yield the text field yield json.loads( line )[ 'text' ] except ( KeyError, JSONDecodeError ): # Catch KeyError for 'text' not present in dict # Catch JSONDecodeError for malformed line print( f'JSON error @ shard={file_name}, line={i}' ) ``` Of course you could use HuggingFace's in-built streaming mechanics to handle things for you, but in my experience that approach is less reliable, doesn't handle `JSONDecodeError`s if there are malformed lines, can cause memory leaks, and has forced sharding behaviour when used inside a multi-worker PyTorch `DataLoader` which I've not yet found a way to disable!
INo0121/low_quality_call_voice_preprocessed	INo0121	"2023-09-21T13:25:07Z"	14,949	0	[ "size_categories:10K<n<100K", "format:parquet", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]	null	"2023-09-08T05:10:37Z"	--- configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* - split: valid path: data/valid-* dataset_info: features: - name: input_features sequence: sequence: float32 - name: labels sequence: int64 splits: - name: train num_bytes: 64088254376 num_examples: 66720 - name: test num_bytes: 7476961712 num_examples: 7784 - name: valid num_bytes: 7476975416 num_examples: 7784 download_size: 521083513 dataset_size: 79042191504 --- # Dataset Card for "low_quality_call_voice_preprocessed" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
Anthropic/hh-rlhf	Anthropic	"2023-05-26T18:47:34Z"	14,898	1,314	[ "license:mit", "size_categories:100K<n<1M", "format:json", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "arxiv:2204.05862", "region:us", "human-feedback" ]	null	"2022-12-08T20:11:33Z"	--- license: mit tags: - human-feedback --- # Dataset Card for HH-RLHF ## Dataset Summary This repository provides access to two different kinds of data: 1. Human preference data about helpfulness and harmlessness from [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://arxiv.org/abs/2204.05862). These data are meant to train preference (or reward) models for subsequent RLHF training. These data are not meant for supervised training of dialogue agents. Training dialogue agents on these data is likely to lead to harmful models and this shold be avoided. 2. Human-generated and annotated red teaming dialogues from [Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned](https://www.anthropic.com/red_teaming.pdf). These data are meant to understand how crowdworkers red team models and what types of red team attacks are succesful or not. The data are not meant for fine-tuning or preference modeling (use the data above for preference modeling). These data are entire transcripts of conversations that are derived from the harmlessness preference modeling data described above, where only the chosen response is incorporated into the overall transcript. Furthermore, the transcripts are annotated with human and automated measurements of how harmful the overall dialogues are. Disclaimer: The data (especially the harmlessness preference data and the red team data) contain content that may be offensive or upsetting. Topics include, but are not limited to, discriminatory language and discussions of abuse, violence, self-harm, exploitation, and other potentially upsetting subject matter. Please only engage with the data in accordance with your own personal risk tolerance. The data are intended for research purposes, especially research that can make models less harmful. The views expressed in the data do not reflect the views of Anthropic or any of its employees. As mentioned above, these data are not intended for training dialogue agents as this will likely lead to harmful model behavior. Each of these datasets are described further below. ## Human preference data about helpfulness and harmlessness (PM Data) The data are described in the paper: [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://arxiv.org/abs/2204.05862). If you find the data useful, please cite the paper. The data format is very simple -- each line of the jsonl files contains a pair of texts, one "chosen" and one "rejected". For helpfulness, the data are grouped into train/test splits in three tranches: from our base models (context-distilled 52B language models), via rejection sampling (mostly with best-of-16 sampling) against an early preference model, and a dataset sampled during our iterated "online" process. For harmlessness, the data are only collected for our base models, but otherwise formatted in the same way. Details about the data collection process and crowdworker population can be found in the paper, specifically in section 2 and appendix D. ## Red teaming data (not PM Data) The data are described in the paper: [Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned](https://www.anthropic.com/red_teaming.pdf). If you find the data useful, please cite the paper. At a high level these data can be examined to understand what succesful red team attempts look like. Details about the data and data collection procedures can be found in the Datasheet in the appendix of the paper. Each line of the jsonl file contains a dictionary with the following fields: - `transcript` a text transcript of a conversation between a human adversary (red team member) and an AI assistant - `min_harmlessness_score_transcript` a real value score of the harmlessness of the AI assistant (lower is more harmful) as obtained from a preference model - `num_params` number of parameters in the language model powering the AI assistant - `model_type` type of model powering the AI assistant - `rating` the red team member's rating of how successful they were at breaking the AI assistant (Likert scale, higher is more successful) - `task_description` a short text description written by the red team member about how they tried to red team the AI assistant - `task_description_harmlessness_score` a real value score of the harmlessness of the task description (lower is more harmful) as obtained from a preference model - `red_team_member_id` an arbitrary identifier of the red team member. one red team member can generate multiple red team attacks - `is_upworker` a binary indicator that is true if the red team member was from the crowd platform Upwork or false if they were from MTurk - `tags` a list of up to 6 tags per transcript. tags are short descriptions of the red team attempts generated by crowdworkers who reviewed red team data post-hoc. tags were only provided for a random sample of 1000 red team attempts for two of four model types. ## Usage Each of the above datasets is located in a separate sub-directory. To load an individual subset, use the `data_dir` argument of the `load_dataset()` function as follows: ```python from datasets import load_dataset # Load all helpfulness/harmless subsets (share the same schema) dataset = load_dataset("Anthropic/hh-rlhf") # Load one of the harmless subsets dataset = load_dataset("Anthropic/hh-rlhf", data_dir="harmless-base") # Load the red teaming subset dataset = load_dataset("Anthropic/hh-rlhf", data_dir="red-team-attempts") ``` ## Contact The original authors host this dataset on GitHub here: https://github.com/anthropics/hh-rlhf You can submit inquiries to: [email protected]
spdenisov/tokenized_udtree	spdenisov	"2023-03-28T21:56:12Z"	14,872	0	[ "size_categories:1M<n<10M", "format:parquet", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]	null	"2023-03-28T21:50:04Z"	--- dataset_info: features: - name: input_ids sequence: int32 - name: attention_mask sequence: int8 splits: - name: cs_0 num_bytes: 73985244 num_examples: 102133 - name: cs_1 num_bytes: 95459594 num_examples: 102133 - name: cs_2 num_bytes: 95354064 num_examples: 102133 - name: cs_3 num_bytes: 128817619 num_examples: 102133 - name: cs_4 num_bytes: 236925044 num_examples: 102133 - name: cs_5 num_bytes: 115688159 num_examples: 102133 - name: cs_6 num_bytes: 132404489 num_examples: 102133 - name: tr_0 num_bytes: 28666902 num_examples: 60089 - name: tr_1 num_bytes: 31887742 num_examples: 60089 - name: tr_2 num_bytes: 31749302 num_examples: 60089 - name: tr_3 num_bytes: 28498032 num_examples: 60089 - name: tr_4 num_bytes: 57177672 num_examples: 60089 - name: tr_5 num_bytes: 37804587 num_examples: 60089 - name: tr_6 num_bytes: 28280762 num_examples: 60089 - name: ar_0 num_bytes: 32848442 num_examples: 21864 - name: ar_1 num_bytes: 49955197 num_examples: 21864 - name: ar_2 num_bytes: 49285292 num_examples: 21864 - name: ar_3 num_bytes: 69585617 num_examples: 21864 - name: ar_4 num_bytes: 91649737 num_examples: 21864 - name: ar_5 num_bytes: 59303592 num_examples: 21864 - name: ar_6 num_bytes: 50935047 num_examples: 21864 - name: de_0 num_bytes: 112997417 num_examples: 166849 - name: de_1 num_bytes: 149332477 num_examples: 166849 - name: de_2 num_bytes: 157628127 num_examples: 166849 - name: de_3 num_bytes: 155444887 num_examples: 166849 - name: de_4 num_bytes: 309419752 num_examples: 166849 - name: de_5 num_bytes: 191783977 num_examples: 166849 - name: de_6 num_bytes: 138689312 num_examples: 166849 - name: fr_0 num_bytes: 27905013 num_examples: 34921 - name: fr_1 num_bytes: 41237113 num_examples: 34921 - name: fr_2 num_bytes: 45655098 num_examples: 34921 - name: fr_3 num_bytes: 39973853 num_examples: 34921 - name: fr_4 num_bytes: 76420558 num_examples: 34921 - name: fr_5 num_bytes: 56197173 num_examples: 34921 - name: fr_6 num_bytes: 39938223 num_examples: 34921 - name: no_0 num_bytes: 19584526 num_examples: 33282 - name: no_1 num_bytes: 25823376 num_examples: 33282 - name: no_2 num_bytes: 26954416 num_examples: 33282 - name: no_3 num_bytes: 23459636 num_examples: 33282 - name: no_4 num_bytes: 43762856 num_examples: 33282 - name: no_5 num_bytes: 32578281 num_examples: 33282 - name: no_6 num_bytes: 23459636 num_examples: 33282 - name: pt_0 num_bytes: 12627085 num_examples: 30720 - name: pt_1 num_bytes: 16475005 num_examples: 30720 - name: pt_2 num_bytes: 17295815 num_examples: 30720 - name: pt_3 num_bytes: 16917200 num_examples: 30720 - name: pt_4 num_bytes: 24168495 num_examples: 30720 - name: pt_5 num_bytes: 20520155 num_examples: 30720 - name: pt_6 num_bytes: 15115165 num_examples: 30720 - name: es_0 num_bytes: 27551907 num_examples: 28474 - name: es_1 num_bytes: 39391152 num_examples: 28474 - name: es_2 num_bytes: 42349787 num_examples: 28474 - name: es_3 num_bytes: 43743597 num_examples: 28474 - name: es_4 num_bytes: 69878787 num_examples: 28474 - name: es_5 num_bytes: 51203677 num_examples: 28474 - name: es_6 num_bytes: 46914367 num_examples: 28474 - name: ru_0 num_bytes: 57566900 num_examples: 89525 - name: ru_1 num_bytes: 74853550 num_examples: 89525 - name: ru_2 num_bytes: 76555950 num_examples: 89525 - name: ru_3 num_bytes: 67072565 num_examples: 89525 - name: ru_4 num_bytes: 155012405 num_examples: 89525 - name: ru_5 num_bytes: 92396515 num_examples: 89525 - name: ru_6 num_bytes: 98333345 num_examples: 89525 - name: en_0 num_bytes: 14945668 num_examples: 28686 - name: en_1 num_bytes: 20836733 num_examples: 28686 - name: en_2 num_bytes: 23313373 num_examples: 28686 - name: en_3 num_bytes: 21978133 num_examples: 28686 - name: en_4 num_bytes: 32732303 num_examples: 28686 - name: en_5 num_bytes: 28539183 num_examples: 28686 - name: en_6 num_bytes: 28399343 num_examples: 28686 - name: fi_0 num_bytes: 14729969 num_examples: 27198 - name: fi_1 num_bytes: 17656509 num_examples: 27198 - name: fi_2 num_bytes: 16915489 num_examples: 27198 - name: fi_3 num_bytes: 18732354 num_examples: 27198 - name: fi_4 num_bytes: 29894674 num_examples: 27198 - name: fi_5 num_bytes: 20079089 num_examples: 27198 - name: fi_6 num_bytes: 18874279 num_examples: 27198 - name: gd_0 num_bytes: 2829948 num_examples: 3541 - name: gd_1 num_bytes: 3700318 num_examples: 3541 - name: gd_2 num_bytes: 3798313 num_examples: 3541 - name: gd_3 num_bytes: 3907648 num_examples: 3541 - name: gd_4 num_bytes: 5359963 num_examples: 3541 - name: gd_5 num_bytes: 4693368 num_examples: 3541 - name: gd_6 num_bytes: 3383253 num_examples: 3541 - name: gv_0 num_bytes: 456221 num_examples: 1172 - name: gv_1 num_bytes: 597391 num_examples: 1172 - name: gv_2 num_bytes: 609501 num_examples: 1172 - name: gv_3 num_bytes: 542486 num_examples: 1172 - name: gv_4 num_bytes: 785231 num_examples: 1172 - name: gv_5 num_bytes: 729026 num_examples: 1172 - name: gv_6 num_bytes: 542486 num_examples: 1172 - name: ga_0 num_bytes: 3928820 num_examples: 4005 - name: ga_1 num_bytes: 5021230 num_examples: 4005 - name: ga_2 num_bytes: 5059580 num_examples: 4005 - name: ga_3 num_bytes: 4843745 num_examples: 4005 - name: ga_4 num_bytes: 9085760 num_examples: 4005 - name: ga_5 num_bytes: 6197075 num_examples: 4005 - name: ga_6 num_bytes: 4483365 num_examples: 4005 - name: cop_0 num_bytes: 4660032 num_examples: 1379 - name: cop_1 num_bytes: 5726842 num_examples: 1379 - name: cop_2 num_bytes: 4508942 num_examples: 1379 - name: cop_3 num_bytes: 4496787 num_examples: 1379 - name: cop_4 num_bytes: 5425137 num_examples: 1379 - name: cop_5 num_bytes: 4907442 num_examples: 1379 - name: cop_6 num_bytes: 4284382 num_examples: 1379 - name: it_0 num_bytes: 17989232 num_examples: 21724 - name: it_1 num_bytes: 25839627 num_examples: 21724 - name: it_2 num_bytes: 27448052 num_examples: 21724 - name: it_3 num_bytes: 24875027 num_examples: 21724 - name: it_4 num_bytes: 43731272 num_examples: 21724 - name: it_5 num_bytes: 33091747 num_examples: 21724 - name: it_6 num_bytes: 30955017 num_examples: 21724 - name: cy_0 num_bytes: 907518 num_examples: 1111 - name: cy_1 num_bytes: 1180383 num_examples: 1111 - name: cy_2 num_bytes: 1192068 num_examples: 1111 - name: cy_3 num_bytes: 1123428 num_examples: 1111 - name: cy_4 num_bytes: 1834888 num_examples: 1111 - name: cy_5 num_bytes: 1439843 num_examples: 1111 - name: cy_6 num_bytes: 1055223 num_examples: 1111 - name: hu_0 num_bytes: 858340 num_examples: 910 - name: hu_1 num_bytes: 1088085 num_examples: 910 - name: hu_2 num_bytes: 1086220 num_examples: 910 - name: hu_3 num_bytes: 957490 num_examples: 910 - name: hu_4 num_bytes: 1964920 num_examples: 910 - name: hu_5 num_bytes: 1370660 num_examples: 910 - name: hu_6 num_bytes: 957490 num_examples: 910 - name: zh_0 num_bytes: 9051347 num_examples: 7994 - name: zh_1 num_bytes: 12537582 num_examples: 7994 - name: zh_2 num_bytes: 11419717 num_examples: 7994 - name: zh_3 num_bytes: 10888407 num_examples: 7994 - name: zh_4 num_bytes: 10558847 num_examples: 7994 - name: zh_5 num_bytes: 13867342 num_examples: 7994 - name: zh_6 num_bytes: 10167967 num_examples: 7994 - name: hy_0 num_bytes: 5120790 num_examples: 3200 - name: hy_1 num_bytes: 5762195 num_examples: 3200 - name: hy_2 num_bytes: 4712195 num_examples: 3200 - name: hy_3 num_bytes: 4260805 num_examples: 3200 - name: hy_4 num_bytes: 8546900 num_examples: 3200 - name: hy_5 num_bytes: 5442440 num_examples: 3200 - name: hy_6 num_bytes: 4260805 num_examples: 3200 - name: ro_0 num_bytes: 6894274 num_examples: 8043 - name: ro_1 num_bytes: 9156564 num_examples: 8043 - name: ro_2 num_bytes: 9493574 num_examples: 8043 - name: ro_3 num_bytes: 10830604 num_examples: 8043 - name: ro_4 num_bytes: 20320209 num_examples: 8043 - name: ro_5 num_bytes: 11507314 num_examples: 8043 - name: ro_6 num_bytes: 8300564 num_examples: 8043 - name: da_0 num_bytes: 2963139 num_examples: 4383 - name: da_1 num_bytes: 3945104 num_examples: 4383 - name: da_2 num_bytes: 4115634 num_examples: 4383 - name: da_3 num_bytes: 3583269 num_examples: 4383 - name: da_4 num_bytes: 7089004 num_examples: 4383 - name: da_5 num_bytes: 4981724 num_examples: 4383 - name: da_6 num_bytes: 3583269 num_examples: 4383 - name: nl_0 num_bytes: 6741817 num_examples: 12289 - name: nl_1 num_bytes: 8989392 num_examples: 12289 - name: nl_2 num_bytes: 9389757 num_examples: 12289 - name: nl_3 num_bytes: 16004832 num_examples: 12289 - name: nl_4 num_bytes: 12089687 num_examples: 12289 - name: nl_5 num_bytes: 11410547 num_examples: 12289 - name: nl_6 num_bytes: 12631912 num_examples: 12289 download_size: 934434422 dataset_size: 5264208717 --- # Dataset Card for "tokenized_udtree" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
Azathothas/temp	Azathothas	"2025-04-08T06:14:56Z"	14,862	0	[ "license:unlicense", "region:us" ]	null	"2025-03-18T03:49:14Z"	--- license: unlicense --- > [!NOTE] > This serves as way to quickly share temp files with other devs, so the files here are ephemeral & often removed
fixie-ai/covost2	fixie-ai	"2024-08-27T20:58:08Z"	14,834	2	[ "size_categories:1M<n<10M", "format:parquet", "modality:audio", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]	null	"2024-07-16T23:40:52Z"	--- dataset_info: - config_name: ar_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 61607709.192 num_examples: 2283 - name: validation num_bytes: 56223234.024 num_examples: 1758 - name: test num_bytes: 54650910.41 num_examples: 1695 download_size: 160468333 dataset_size: 172481853.626 - config_name: ca_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 4397026262.322 num_examples: 95854 - name: validation num_bytes: 544108371.96 num_examples: 12730 - name: test num_bytes: 604755238.63 num_examples: 12730 download_size: 4957773433 dataset_size: 5545889872.912 - config_name: cy_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 51478765.087 num_examples: 1241 - name: validation num_bytes: 26992697.0 num_examples: 690 - name: test num_bytes: 28772216.0 num_examples: 690 download_size: 102604972 dataset_size: 107243678.087 - config_name: de_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 5680326209.222 num_examples: 127834 - name: validation num_bytes: 631442490.202 num_examples: 13511 - name: test num_bytes: 637042944.685 num_examples: 13511 download_size: 6490850158 dataset_size: 6948811644.108999 - config_name: en_ar features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14105902817.18 num_examples: 289430 - name: validation num_bytes: 718527564.808 num_examples: 15531 - name: test num_bytes: 729114452.301 num_examples: 15531 download_size: 13815709729 dataset_size: 15553544834.289001 - config_name: en_ca features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14099092976.18 num_examples: 289430 - name: validation num_bytes: 718171719.808 num_examples: 15531 - name: test num_bytes: 728790610.301 num_examples: 15531 download_size: 13814365593 dataset_size: 15546055306.289001 - config_name: en_cy features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14098487703.18 num_examples: 289430 - name: validation num_bytes: 718141953.808 num_examples: 15531 - name: test num_bytes: 728793811.301 num_examples: 15531 download_size: 13813953593 dataset_size: 15545423468.289001 - config_name: en_de features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14099886814.18 num_examples: 289430 - name: validation num_bytes: 718219105.808 num_examples: 15531 - name: test num_bytes: 728857067.301 num_examples: 15531 download_size: 13815103686 dataset_size: 15546962987.289001 - config_name: en_et features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14096877545.18 num_examples: 289430 - name: validation num_bytes: 718057559.808 num_examples: 15531 - name: test num_bytes: 728710692.301 num_examples: 15531 download_size: 13813410823 dataset_size: 15543645797.289001 - config_name: en_fa features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14108661241.18 num_examples: 289430 - name: validation num_bytes: 718670909.808 num_examples: 15531 - name: test num_bytes: 729271000.301 num_examples: 15531 download_size: 13816798013 dataset_size: 15556603151.289001 - config_name: en_id features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14098627451.18 num_examples: 289430 - name: validation num_bytes: 718144327.808 num_examples: 15531 - name: test num_bytes: 728802322.301 num_examples: 15531 download_size: 13813201260 dataset_size: 15545574101.289001 - config_name: en_ja features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14103911774.18 num_examples: 289430 - name: validation num_bytes: 718409304.808 num_examples: 15531 - name: test num_bytes: 729050991.301 num_examples: 15531 download_size: 13815875328 dataset_size: 15551372070.289001 - config_name: en_lv features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14098703097.18 num_examples: 289430 - name: validation num_bytes: 718152571.808 num_examples: 15531 - name: test num_bytes: 728792572.301 num_examples: 15531 download_size: 13814849886 dataset_size: 15545648241.289001 - config_name: en_mn features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14113120657.18 num_examples: 289430 - name: validation num_bytes: 718940418.808 num_examples: 15531 - name: test num_bytes: 729461016.301 num_examples: 15531 download_size: 13819427515 dataset_size: 15561522092.289001 - config_name: en_sl features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14097158381.18 num_examples: 289430 - name: validation num_bytes: 718085673.808 num_examples: 15531 - name: test num_bytes: 728705188.301 num_examples: 15531 download_size: 13813603812 dataset_size: 15543949243.289001 - config_name: en_sv-SE features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14097728051.18 num_examples: 289430 - name: validation num_bytes: 718093292.808 num_examples: 15531 - name: test num_bytes: 728747422.301 num_examples: 15531 download_size: 13813332908 dataset_size: 15544568766.289001 - config_name: en_ta features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14135489205.18 num_examples: 289430 - name: validation num_bytes: 720191394.808 num_examples: 15531 - name: test num_bytes: 730578783.301 num_examples: 15531 download_size: 13825121271 dataset_size: 15586259383.289001 - config_name: en_tr features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14098644786.18 num_examples: 289430 - name: validation num_bytes: 718161996.808 num_examples: 15531 - name: test num_bytes: 728786654.301 num_examples: 15531 download_size: 13814279798 dataset_size: 15545593437.289001 - config_name: en_zh-CN features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14095661460.18 num_examples: 289430 - name: validation num_bytes: 717982705.808 num_examples: 15531 - name: test num_bytes: 728655191.301 num_examples: 15531 download_size: 13812699892 dataset_size: 15542299357.289001 - config_name: es_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: validation num_bytes: 630615357.241 num_examples: 13221 - name: test num_bytes: 666447063.067 num_examples: 13221 - name: train num_bytes: 3769457359.8 num_examples: 79015 download_size: 4531969416 dataset_size: 5066519780.108 - config_name: et_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 97124727.544 num_examples: 1782 - name: validation num_bytes: 80290798.168 num_examples: 1576 - name: test num_bytes: 81970364.51 num_examples: 1571 download_size: 257604448 dataset_size: 259385890.222 - config_name: fa_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 1872724297.149 num_examples: 53949 - name: validation num_bytes: 140067911.23 num_examples: 3445 - name: test num_bytes: 149319550.35 num_examples: 3445 download_size: 1679853440 dataset_size: 2162111758.729 - config_name: fr_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: validation num_bytes: 632191608.84 num_examples: 14760 - name: test num_bytes: 698178059.08 num_examples: 14760 - name: train num_bytes: 8128016830.77 num_examples: 207374 download_size: 8900934523 dataset_size: 9458386498.69 - config_name: id_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 36136135.768 num_examples: 1243 - name: validation num_bytes: 25058845.0 num_examples: 792 - name: test num_bytes: 26577467.0 num_examples: 844 download_size: 86110062 dataset_size: 87772447.768 - config_name: it_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 1517510665.568 num_examples: 31698 - name: validation num_bytes: 422409218.1 num_examples: 8940 - name: test num_bytes: 454569171.595 num_examples: 8951 download_size: 2125529183 dataset_size: 2394489055.2630005 - config_name: ja_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 38181610.624 num_examples: 1119 - name: validation num_bytes: 24623052.0 num_examples: 635 - name: test num_bytes: 25558787.0 num_examples: 684 download_size: 88228548 dataset_size: 88363449.624 - config_name: lv_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 66152116.328 num_examples: 2337 - name: validation num_bytes: 32655276.0 num_examples: 1125 - name: test num_bytes: 50997551.638 num_examples: 1629 download_size: 137700207 dataset_size: 149804943.96600002 - config_name: mn_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 87891433.547 num_examples: 2067 - name: validation num_bytes: 77519039.943 num_examples: 1761 - name: test num_bytes: 83667460.167 num_examples: 1759 download_size: 242638800 dataset_size: 249077933.657 - config_name: nl_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 216102081.4 num_examples: 7108 - name: validation num_bytes: 55386349.319 num_examples: 1699 - name: test num_bytes: 60219179.711 num_examples: 1699 download_size: 320267264 dataset_size: 331707610.43 - config_name: pt_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 274723273.528 num_examples: 9158 - name: validation num_bytes: 118345891.704 num_examples: 3318 - name: test num_bytes: 166247624.001 num_examples: 4023 download_size: 540891735 dataset_size: 559316789.233 - config_name: ru_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 557219472.672 num_examples: 12112 - name: validation num_bytes: 290218427.6 num_examples: 6110 - name: test num_bytes: 312622838.0 num_examples: 6300 download_size: 1112848246 dataset_size: 1160060738.272 - config_name: sl_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 55992153.0 num_examples: 1843 - name: validation num_bytes: 15074155.0 num_examples: 509 - name: test num_bytes: 10209711.0 num_examples: 360 download_size: 83863293 dataset_size: 81276019.0 - config_name: sv-SE_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 48298330.64 num_examples: 2160 - name: validation num_bytes: 32544646.416 num_examples: 1349 - name: test num_bytes: 46894324.615 num_examples: 1595 download_size: 121860373 dataset_size: 127737301.671 - config_name: ta_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 47757197.616 num_examples: 1358 - name: validation num_bytes: 13670695.0 num_examples: 384 - name: test num_bytes: 29891516.0 num_examples: 786 download_size: 87791516 dataset_size: 91319408.616 - config_name: tr_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 119299427.798 num_examples: 3966 - name: validation num_bytes: 52552534.232 num_examples: 1624 - name: test num_bytes: 59106253.862 num_examples: 1629 download_size: 224018260 dataset_size: 230958215.89200002 - config_name: zh-CN_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: validation num_bytes: 231018998.33 num_examples: 4843 - name: test num_bytes: 243850956.45 num_examples: 4898 - name: train num_bytes: 341425113.6 num_examples: 7085 download_size: 766660661 dataset_size: 816295068.38 configs: - config_name: ar_en data_files: - split: train path: ar_en/train-* - split: validation path: ar_en/validation-* - split: test path: ar_en/test-* - config_name: ca_en data_files: - split: train path: ca_en/train-* - split: validation path: ca_en/validation-* - split: test path: ca_en/test-* - config_name: cy_en data_files: - split: train path: cy_en/train-* - split: validation path: cy_en/validation-* - split: test path: cy_en/test-* - config_name: de_en data_files: - split: train path: de_en/train-* - split: validation path: de_en/validation-* - split: test path: de_en/test-* - config_name: en_ar data_files: - split: train path: en_ar/train-* - split: validation path: en_ar/validation-* - split: test path: en_ar/test-* - config_name: en_ca data_files: - split: train path: en_ca/train-* - split: validation path: en_ca/validation-* - split: test path: en_ca/test-* - config_name: en_cy data_files: - split: train path: en_cy/train-* - split: validation path: en_cy/validation-* - split: test path: en_cy/test-* - config_name: en_de data_files: - split: train path: en_de/train-* - split: validation path: en_de/validation-* - split: test path: en_de/test-* - config_name: en_et data_files: - split: train path: en_et/train-* - split: validation path: en_et/validation-* - split: test path: en_et/test-* - config_name: en_fa data_files: - split: train path: en_fa/train-* - split: validation path: en_fa/validation-* - split: test path: en_fa/test-* - config_name: en_id data_files: - split: train path: en_id/train-* - split: validation path: en_id/validation-* - split: test path: en_id/test-* - config_name: en_ja data_files: - split: train path: en_ja/train-* - split: validation path: en_ja/validation-* - split: test path: en_ja/test-* - config_name: en_lv data_files: - split: train path: en_lv/train-* - split: validation path: en_lv/validation-* - split: test path: en_lv/test-* - config_name: en_mn data_files: - split: train path: en_mn/train-* - split: validation path: en_mn/validation-* - split: test path: en_mn/test-* - config_name: en_sl data_files: - split: train path: en_sl/train-* - split: validation path: en_sl/validation-* - split: test path: en_sl/test-* - config_name: en_sv-SE data_files: - split: train path: en_sv-SE/train-* - split: validation path: en_sv-SE/validation-* - split: test path: en_sv-SE/test-* - config_name: en_ta data_files: - split: train path: en_ta/train-* - split: validation path: en_ta/validation-* - split: test path: en_ta/test-* - config_name: en_tr data_files: - split: train path: en_tr/train-* - split: validation path: en_tr/validation-* - split: test path: en_tr/test-* - config_name: en_zh-CN data_files: - split: train path: en_zh-CN/train-* - split: validation path: en_zh-CN/validation-* - split: test path: en_zh-CN/test-* - config_name: es_en data_files: - split: validation path: es_en/validation-* - split: test path: es_en/test-* - split: train path: es_en/train-* - config_name: et_en data_files: - split: train path: et_en/train-* - split: validation path: et_en/validation-* - split: test path: et_en/test-* - config_name: fa_en data_files: - split: train path: fa_en/train-* - split: validation path: fa_en/validation-* - split: test path: fa_en/test-* - config_name: fr_en data_files: - split: validation path: fr_en/validation-* - split: test path: fr_en/test-* - split: train path: fr_en/train-* - config_name: id_en data_files: - split: train path: id_en/train-* - split: validation path: id_en/validation-* - split: test path: id_en/test-* - config_name: it_en data_files: - split: train path: it_en/train-* - split: validation path: it_en/validation-* - split: test path: it_en/test-* - config_name: ja_en data_files: - split: train path: ja_en/train-* - split: validation path: ja_en/validation-* - split: test path: ja_en/test-* - config_name: lv_en data_files: - split: train path: lv_en/train-* - split: validation path: lv_en/validation-* - split: test path: lv_en/test-* - config_name: mn_en data_files: - split: train path: mn_en/train-* - split: validation path: mn_en/validation-* - split: test path: mn_en/test-* - config_name: nl_en data_files: - split: train path: nl_en/train-* - split: validation path: nl_en/validation-* - split: test path: nl_en/test-* - config_name: pt_en data_files: - split: train path: pt_en/train-* - split: validation path: pt_en/validation-* - split: test path: pt_en/test-* - config_name: ru_en data_files: - split: train path: ru_en/train-* - split: validation path: ru_en/validation-* - split: test path: ru_en/test-* - config_name: sl_en data_files: - split: train path: sl_en/train-* - split: validation path: sl_en/validation-* - split: test path: sl_en/test-* - config_name: sv-SE_en data_files: - split: train path: sv-SE_en/train-* - split: validation path: sv-SE_en/validation-* - split: test path: sv-SE_en/test-* - config_name: ta_en data_files: - split: train path: ta_en/train-* - split: validation path: ta_en/validation-* - split: test path: ta_en/test-* - config_name: tr_en data_files: - split: train path: tr_en/train-* - split: validation path: tr_en/validation-* - split: test path: tr_en/test-* - config_name: zh-CN_en data_files: - split: validation path: zh-CN_en/validation-* - split: test path: zh-CN_en/test-* - split: train path: zh-CN_en/train-* --- This is a partial copy of [CoVoST2](https://huggingface.co/datasets/facebook/covost2) dataset. The main difference is that the audio data is included in the dataset, which makes usage easier and allows browsing the samples using HF Dataset Viewer. The limitation of this method is that all audio samples of the `EN_XX` subsets are duplicated, as such the size of the dataset is larger. As such, not all the data is included: Only the `validation` and `test` subsets are available. From the `XX_EN` subsets, only `fr`, `es`, and `zh-CN` are included.
HAERAE-HUB/KMMLU-HARD	HAERAE-HUB	"2024-03-09T23:46:06Z"	14,798	8	[ "task_categories:question-answering", "language:ko", "license:cc-by-nd-4.0", "size_categories:1K<n<10K", "format:csv", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "arxiv:2402.11548", "region:us", "haerae", "mmlu" ]	[ "question-answering" ]	"2024-01-12T05:49:07Z"	--- configs: - config_name: maritime_engineering data_files: - split: dev path: data/maritime_engineering-dev.csv - split: test path: data/maritime_engineering-hard-test.csv - config_name: materials_engineering data_files: - split: dev path: data/materials_engineering-dev.csv - split: test path: data/materials_engineering-hard-test.csv - config_name: railway_and_automotive_engineering data_files: - split: dev path: data/railway_and_automotive_engineering-dev.csv - split: test path: data/railway_and_automotive_engineering-hard-test.csv - config_name: biology data_files: - split: dev path: data/biology-dev.csv - split: test path: data/biology-hard-test.csv - config_name: public_safety data_files: - split: dev path: data/public_safety-dev.csv - split: test path: data/public_safety-hard-test.csv - config_name: criminal_law data_files: - split: dev path: data/criminal_law-dev.csv - split: test path: data/criminal_law-hard-test.csv - config_name: information_technology data_files: - split: dev path: data/information_technology-dev.csv - split: test path: data/information_technology-hard-test.csv - config_name: geomatics data_files: - split: dev path: data/geomatics-dev.csv - split: test path: data/geomatics-hard-test.csv - config_name: management data_files: - split: dev path: data/management-dev.csv - split: test path: data/management-hard-test.csv - config_name: math data_files: - split: dev path: data/math-dev.csv - split: test path: data/math-hard-test.csv - config_name: accounting data_files: - split: dev path: data/accounting-dev.csv - split: test path: data/accounting-hard-test.csv - config_name: chemistry data_files: - split: dev path: data/chemistry-dev.csv - split: test path: data/chemistry-hard-test.csv - config_name: nondestructive_testing data_files: - split: dev path: data/nondestructive_testing-dev.csv - split: test path: data/nondestructive_testing-hard-test.csv - config_name: computer_science data_files: - split: dev path: data/computer_science-dev.csv - split: test path: data/computer_science-hard-test.csv - config_name: ecology data_files: - split: dev path: data/ecology-dev.csv - split: test path: data/ecology-hard-test.csv - config_name: health data_files: - split: dev path: data/health-dev.csv - split: test path: data/health-hard-test.csv - config_name: political_science_and_sociology data_files: - split: dev path: data/political_science_and_sociology-dev.csv - split: test path: data/political_science_and_sociology-hard-test.csv - config_name: patent data_files: - split: dev path: data/patent-dev.csv - split: test path: data/patent-hard-test.csv - config_name: electrical_engineering data_files: - split: dev path: data/electrical_engineering-dev.csv - split: test path: data/electrical_engineering-hard-test.csv - config_name: electronics_engineering data_files: - split: dev path: data/electronics_engineering-dev.csv - split: test path: data/electronics_engineering-hard-test.csv - config_name: korean_history data_files: - split: dev path: data/korean_history-dev.csv - split: test path: data/korean_history-hard-test.csv - config_name: gas_technology_and_engineering data_files: - split: dev path: data/gas_technology_and_engineering-dev.csv - split: test path: data/gas_technology_and_engineering-hard-test.csv - config_name: machine_design_and_manufacturing data_files: - split: dev path: data/machine_design_and_manufacturing-dev.csv - split: test path: data/machine_design_and_manufacturing-hard-test.csv - config_name: chemical_engineering data_files: - split: dev path: data/chemical_engineering-dev.csv - split: test path: data/chemical_engineering-hard-test.csv - config_name: telecommunications_and_wireless_technology data_files: - split: dev path: data/telecommunications_and_wireless_technology-dev.csv - split: test path: data/telecommunications_and_wireless_technology-hard-test.csv - config_name: food_processing data_files: - split: dev path: data/food_processing-dev.csv - split: test path: data/food_processing-hard-test.csv - config_name: social_welfare data_files: - split: dev path: data/social_welfare-dev.csv - split: test path: data/social_welfare-hard-test.csv - config_name: real_estate data_files: - split: dev path: data/real_estate-dev.csv - split: test path: data/real_estate-hard-test.csv - config_name: marketing data_files: - split: dev path: data/marketing-dev.csv - split: test path: data/marketing-hard-test.csv - config_name: mechanical_engineering data_files: - split: dev path: data/mechanical_engineering-dev.csv - split: test path: data/mechanical_engineering-hard-test.csv - config_name: fashion data_files: - split: dev path: data/fashion-dev.csv - split: test path: data/fashion-hard-test.csv - config_name: psychology data_files: - split: dev path: data/psychology-dev.csv - split: test path: data/psychology-hard-test.csv - config_name: taxation data_files: - split: dev path: data/taxation-dev.csv - split: test path: data/taxation-hard-test.csv - config_name: environmental_science data_files: - split: dev path: data/environmental_science-dev.csv - split: test path: data/environmental_science-hard-test.csv - config_name: refrigerating_machinery data_files: - split: dev path: data/refrigerating_machinery-dev.csv - split: test path: data/refrigerating_machinery-hard-test.csv - config_name: education data_files: - split: dev path: data/education-dev.csv - split: test path: data/education-hard-test.csv - config_name: industrial_engineer data_files: - split: dev path: data/industrial_engineer-dev.csv - split: test path: data/industrial_engineer-hard-test.csv - config_name: civil_engineering data_files: - split: dev path: data/civil_engineering-dev.csv - split: test path: data/civil_engineering-hard-test.csv - config_name: energy_management data_files: - split: dev path: data/energy_management-dev.csv - split: test path: data/energy_management-hard-test.csv - config_name: law data_files: - split: dev path: data/law-dev.csv - split: test path: data/law-hard-test.csv - config_name: agricultural_sciences data_files: - split: dev path: data/agricultural_sciences-dev.csv - split: test path: data/agricultural_sciences-hard-test.csv - config_name: interior_architecture_and_design data_files: - split: dev path: data/interior_architecture_and_design-dev.csv - split: test path: data/interior_architecture_and_design-hard-test.csv - config_name: aviation_engineering_and_maintenance data_files: - split: dev path: data/aviation_engineering_and_maintenance-dev.csv - split: test path: data/aviation_engineering_and_maintenance-hard-test.csv - config_name: construction data_files: - split: dev path: data/construction-dev.csv - split: test path: data/construction-hard-test.csv - config_name: economics data_files: - split: dev path: data/economics-dev.csv - split: test path: data/economics-hard-test.csv license: cc-by-nd-4.0 task_categories: - question-answering language: - ko tags: - haerae - mmlu size_categories: - 100K<n<1M --- ### KMMLU (Korean-MMLU) We propose KMMLU, a new Korean benchmark with 35,030 expert-level multiple-choice questions across 45 subjects ranging from humanities to STEM. Unlike previous Korean benchmarks that are translated from existing English benchmarks, KMMLU is collected from original Korean exams, capturing linguistic and cultural aspects of the Korean language. We test 26 publically available and proprietary LLMs, identifying significant room for improvement. The best publicly available model achieves 50.54% on KMMLU, far below the average human performance of 62.6%. This model was primarily trained for English and Chinese, not Korean. Current LLMs tailored to Korean, such as Polyglot-Ko, perform far worse. Surprisingly, even the most capable proprietary LLMs, e.g., GPT-4 and HyperCLOVA X, achieve 59.95% and 53.40%, respectively. This suggests that further work is needed to improve Korean LLMs, and KMMLU offers the right tool to track this progress. We make our dataset publicly available on the Hugging Face Hub and integrate the benchmark into EleutherAI's Language Model Evaluation Harness. Link to Paper: [KMMLU: Measuring Massive Multitask Language Understanding in Korean](https://arxiv.org/abs/2402.11548) ### KMMLU Statistics \| Category \| # Questions \| \|------------------------------\|-------------\| \| Prerequisites \| \| \| None \| 59,909 \| \| 1 Prerequisite Test \| 12,316 \| \| 2 Prerequisite Tests \| 776 \| \| 2+ Years of Experience \| 65,135 \| \| 4+ Years of Experience \| 98,678 \| \| 9+ Years of Experience \| 6,963 \| \| Question Type \| \| \| Positive \| 207,030 \| \| Negation \| 36,777 \| \| Split \| \| \| Train \| 208,522 \| \| Validation \| 225 \| \| Test \| 35,030 \| \| Total \| 243,777 \| ### Categories To reimplement the categories in the paper, refer to the following: ``` supercategories = { "accounting": "HUMSS", "agricultural_sciences": "Other", "aviation_engineering_and_maintenance": "Applied Science", "biology": "STEM", "chemical_engineering": "STEM", "chemistry": "STEM", "civil_engineering": "STEM", "computer_science": "STEM", "construction": "Other", "criminal_law": "HUMSS", "ecology": "STEM", "economics": "HUMSS", "education": "HUMSS", "electrical_engineering": "STEM", "electronics_engineering": "Applied Science", "energy_management": "Applied Science", "environmental_science": "Applied Science", "fashion": "Other", "food_processing": "Other", "gas_technology_and_engineering": "Applied Science", "geomatics": "Applied Science", "health": "Other", "industrial_engineer": "Applied Science", "information_technology": "STEM", "interior_architecture_and_design": "Other", "law": "HUMSS", "machine_design_and_manufacturing": "Applied Science", "management": "HUMSS", "maritime_engineering": "Applied Science", "marketing": "Other", "materials_engineering": "STEM", "mechanical_engineering": "STEM", "nondestructive_testing": "Applied Science", "patent": "Other", "political_science_and_sociology": "HUMSS", "psychology": "HUMSS", "public_safety": "Other", "railway_and_automotive_engineering": "Applied Science", "real_estate": "Other", "refrigerating_machinery": "Other", "social_welfare": "HUMSS", "taxation": "HUMSS", "telecommunications_and_wireless_technology": "Applied Science", "korean_history": "HUMSS", "math": "STEM" } ``` ### Point of Contact For any questions contact us via the following email:) ``` [email protected] ```
amitness/logits-mt-it-en-128	amitness	"2023-09-27T10:27:21Z"	14,792	0	[ "size_categories:10M<n<100M", "format:parquet", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]	null	"2023-09-25T19:22:48Z"	--- configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* dataset_info: features: - name: input_ids sequence: int32 - name: token_type_ids sequence: int8 - name: attention_mask sequence: int8 - name: labels sequence: int64 - name: teacher_logits sequence: sequence: float64 - name: teacher_indices sequence: sequence: int64 - name: teacher_mask_indices sequence: int64 splits: - name: train num_bytes: 184467361976 num_examples: 40721350 - name: test num_bytes: 32556394204 num_examples: 7186121 download_size: 0 dataset_size: 217023756180 --- # Dataset Card for "logits-mt-it-en-128" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
distil-whisper/librispeech_long	distil-whisper	"2023-11-02T14:22:54Z"	14,753	2	[ "size_categories:n<1K", "format:parquet", "modality:audio", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]	null	"2023-11-02T14:22:51Z"	--- dataset_info: config_name: clean features: - name: audio dtype: audio splits: - name: validation num_bytes: 1998609.0 num_examples: 1 download_size: 1984721 dataset_size: 1998609.0 configs: - config_name: clean data_files: - split: validation path: clean/validation-* --- # Dataset Card for "librispeech_long" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
alvations/c4p0-x1-es-en	alvations	"2024-03-24T03:52:27Z"	14,723	0	[ "size_categories:n<1K", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]	null	"2024-03-23T10:16:40Z"	--- dataset_info: features: - name: source dtype: string - name: target dtype: string - name: target_backto_source dtype: string - name: raw_target list: - name: generated_text dtype: string - name: raw_target_backto_source list: - name: generated_text dtype: string - name: prompt dtype: string - name: reverse_prompt dtype: string - name: source_langid dtype: string - name: target_langid dtype: string - name: target_backto_source_langid dtype: string - name: doc_id dtype: int64 - name: sent_id dtype: int64 - name: timestamp dtype: timestamp[us] - name: url dtype: string - name: doc_hash dtype: string splits: - name: train num_bytes: 3583 num_examples: 4 download_size: 14029 dataset_size: 3583 configs: - config_name: default data_files: - split: train path: d595973734f0a325/train-* ---
KShivendu/dbpedia-entities-openai-1M	KShivendu	"2024-02-19T08:24:43Z"	14,680	20	[ "task_categories:feature-extraction", "language:en", "license:mit", "size_categories:1M<n<10M", "format:parquet", "modality:text", "modality:timeseries", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]	[ "feature-extraction" ]	"2023-06-20T22:29:43Z"	--- license: mit dataset_info: features: - name: _id dtype: string - name: title dtype: string - name: text dtype: string - name: openai sequence: float32 splits: - name: train num_bytes: 12383152 num_examples: 1000000 download_size: 12383152 dataset_size: 1000000 language: - en task_categories: - feature-extraction pretty_name: OpenAI 1M with DBPedia Entities size_categories: - 1M<n<10M --- 1M OpenAI Embeddings -- 1536 dimensions Created: June 2023. Text used for Embedding: title (string) + text (string) Embedding Model: text-embedding-ada-002 First used for the pgvector vs VectorDB (Qdrant) benchmark: https://nirantk.com/writing/pgvector-vs-qdrant/ ### Future work We are planning to take this up to 10M (and possibly 100M) vectors. Contact [@KShivendu_](https://twitter.com/KShivendu_) on Twitter or mail to [email protected] if you want to help :) ### Credits: This dataset was generated from the first 1M entries of https://huggingface.co/datasets/BeIR/dbpedia-entity
hoskinson-center/proof-pile	hoskinson-center	"2023-08-19T03:24:11Z"	14,644	59	[ "task_categories:text-generation", "task_ids:language-modeling", "annotations_creators:no-annotation", "language_creators:found", "multilinguality:monolingual", "language:en", "license:apache-2.0", "size_categories:100K<n<1M", "modality:text", "library:datasets", "library:mlcroissant", "region:us", "math", "mathematics", "formal-mathematics" ]	[ "text-generation" ]	"2022-08-08T20:57:56Z"	--- annotations_creators: - no-annotation language: - en language_creators: - found license: [apache-2.0] multilinguality: - monolingual pretty_name: proof-pile size_categories: [] source_datasets: [] tags: - math - mathematics - formal-mathematics task_categories: - text-generation task_ids: - language-modeling --- # Dataset Description The `proof-pile` is a 13GB pre-training dataset of mathematical text that comprises 8.3 billion tokens (using the `gpt-neox` tokenizer). Models trained on this dataset are coming soon :) The dataset is composed of diverse sources of both informal and formal mathematics, namely - ArXiv.math (10GB) - Open-source math textbooks (50MB) - Formal mathematics libraries (500MB) - Lean mathlib and other Lean repositories - Isabelle AFP - Coq mathematical components and other Coq repositories - HOL Light - set.mm - Mizar Mathematical Library - Math Overflow and Math Stack Exchange (2.5GB) - Wiki-style sources (50MB) - ProofWiki - Wikipedia math articles - MATH dataset (6MB) The construction of the dataset is reproducible using the code and instructions in the [proof-pile Github repo](https://github.com/zhangir-azerbayev/proof-pile). # Supported Tasks This dataset is intended to be used for pre-training and fine-tuning language models. We envision models trained on the `proof-pile` will have many downstream applications, including informal quantitative reasoning, formal theorem proving, semantic search for formal mathematics, and autoformalization. # Languages All informal mathematics in the `proof-pile` is written in English and LaTeX (arXiv articles in other languages are filtered out using [languagedetect](https://github.com/shuyo/language-detection/blob/wiki/ProjectHome.md)). Formal theorem proving languages represented in this dataset are Lean 3, Isabelle, Coq, HOL Light, Metamath, and Mizar. # Evaluation The version of `set.mm` in this dataset has 10% of proofs replaced with the `?` character in order to preserve a validation and test set for Metamath provers pre-trained on the `proof-pile`. The precise split can be found here: [validation](https://github.com/zhangir-azerbayev/mm-extract/blob/main/valid_decls.json) and [test](https://github.com/zhangir-azerbayev/mm-extract/blob/main/test_decls.json). The Lean mathlib commit used in this dataset is `6313863`. Theorems created in subsequent commits can be used for evaluating Lean theorem provers. This dataset contains only the training set of the [MATH dataset](https://github.com/hendrycks/math). However, because this dataset contains ProofWiki, the Stacks Project, Trench's Analysis, and Stein's Number Theory, models trained on it cannot be evaluated on the [NaturalProofs dataset](https://github.com/wellecks/naturalproofs). # Data Preprocessing This section describes any significant filtering and transformations made to various subsets of the data. arXiv.math. The arXiv.math dataset is large, heterogeneous, and contains a great deal of noise. We used the following heuristics when choosing which files from arXiv.math source folders to include in the dataset: - Keep only files with a `.tex` extension. - Only include files that use either a `utf-8/16/32` or `latin-1` text encoding. - Discard files that do not contain a part, chapter, section, sub...section, paragraph, or subparagraph heading. - Delete files that contain the keyword `gnuplot`. Gnuplot-latex is an old command line utility that generates blocks of entirely unintelligible source. - Include only articles in English, as determined by the [langdetect library](https://pypi.org/project/langdetect/). \n", "\n", - Exclude files shorter than 280 characters (characters counted after substring removal described below). In addition, we apply the following transformations to arXiv.math texts: - Delete everything outside of `\begin{document}` and `\end{document}`. - Delete everything including or after `\Refs`, `\begin{thebibliography}`, or `\begin{bibdiv}` - Delete comments. - Any more than three consecutive newlines are replaced by three consecutive newlines. In [this notebook](https://github.com/zhangir-azerbayev/proof-pile/blob/main/analysis/arxiv_noisedetection.ipynb), we provide an analysis of the prevalence of noisy documents in the arXiv.math subset of the proof-pile. Stack Exchange. We only include questions that have at least 5 upvotes and an answer. We format Stack Exchange posts as follows ``` QUESTION [{num_upvotes} upvotes]: {text of question} REPLY [{num_upvotes} votes]: {text of reply} REPLY [{num_upvotes} votes]: {text of reply} . . . ``` set.mm. We converted `set.mm` into human-readable form by following the instructions in the [mm-extract repo](https://github.com/zhangir-azerbayev/mm-extract) ## Contributions Authors: Zhangir Azerbayev, Edward Ayers, Bartosz Piotrowski. We would like to thank Jeremy Avigad, Albert Jiang, and Wenda Li for their invaluable guidance, and the Hoskinson Center for Formal Mathematics for its support.
MBZUAI/Bactrian-X	MBZUAI	"2023-05-27T12:54:05Z"	14,623	116	[ "task_categories:text-generation", "language:af", "language:ar", "language:az", "language:bn", "language:cs", "language:de", "language:en", "language:es", "language:et", "language:fi", "language:fr", "language:gl", "language:gu", "language:he", "language:hi", "language:hr", "language:id", "language:it", "language:ja", "language:ka", "language:kk", "language:km", "language:ko", "language:lt", "language:lv", "language:mk", "language:ml", "language:mn", "language:mr", "language:my", "language:ne", "language:nl", "language:pl", "language:ps", "language:pt", "language:ro", "language:ru", "language:si", "language:sl", "language:sv", "language:sw", "language:ta", "language:te", "language:th", "language:tl", "language:tr", "language:uk", "language:ur", "language:vi", "language:xh", "language:zh", "license:cc-by-nc-4.0", "size_categories:1M<n<10M", "modality:text", "library:datasets", "library:mlcroissant", "arxiv:2008.00401", "arxiv:2305.15011", "region:us", "instruction-finetuning", "multilingual" ]	[ "text-generation" ]	"2023-04-22T12:42:39Z"	--- license: cc-by-nc-4.0 task_categories: - text-generation language: - af - ar - az - bn - cs - de - en - es - et - fi - fr - gl - gu - he - hi - hr - id - it - ja - ka - kk - km - ko - lt - lv - mk - ml - mn - mr - my - ne - nl - pl - ps - pt - ro - ru - si - sl - sv - sw - ta - te - th - tl - tr - uk - ur - vi - xh - zh tags: - instruction-finetuning - multilingual pretty_name: Bactrian-X --- # Dataset Card for "Bactrian-X" ## Table of Contents - [Dataset Description](#a-dataset-description) - [Dataset Summary](#dataset-summary) - [Languages](#languages) - [Dataset Structure](#b-dataset-structure) - [Data Fields](#data-fields) - [Data Instances](#data-instances) - [Data in 52 Languages](#data-in-52-languages) - [Dataset Creation](#c-dataset-creation) - [Considerations for Using the Data](#d-considerations-for-using-the-data) - [Additional Information](#e-additional-information) ## A. Dataset Description - Homepage: https://github.com/mbzuai-nlp/Bactrian-X - Repository: https://huggingface.co/datasets/MBZUAI/Bactrian-X - Paper: to-be-soon released ### Dataset Summary <h3 align="center"> <img src="https://raw.githubusercontent.com/fajri91/eval_picts/master/BactrianX_dataset.jpg" width="950" align="center"> </h3> The Bactrain-X dataset is a collection of 3.4M instruction-response pairs in 52 languages, that are obtained by translating 67K English instructions ([alpaca-52k](https://github.com/tatsu-lab/stanford_alpaca) + [dolly-15k](https://github.com/databrickslabs/dolly/tree/master/data)) into 51 languages using Google Translate API. The translated instructions are then fed to ChatGPT (`gpt-3.5-turbo`) to obtain its natural responses, resulting in 3.4M instruction-response pairs in 52 languages (52 languages x 67k instances = 3.4M instances). ### Languages We follow 52 languages of [mBART-50](https://arxiv.org/abs/2008.00401), with details can be found [below](#data-in-52-languages). ## B. Dataset Structure ### Data Fields The data fields are as follows: * `instruction`: describes the task the model should perform. Each of the 67K instructions is unique. * `input`: optional context or input for the task. For example, when the instruction is "Summarize the following article", the input is the article. Around 40% of the examples have an input. * `output`: the answer to the instruction as generated by `gpt-3.5-turbo`. * `id`: the unique index for each data piece in a specific language. The same `id` across splits corresponds to the same original English data. ### Data Instances An example in `en` looks as follows. ```json { "instruction": "What is the main idea of this text?", "input": "The robotics industry has become one of the fastest growing sectors in today’s economy. Robotics technology is being applied in various industries and applications, such as manufacturing, healthcare, and defense.", "output": "The main idea of the text is that the robotics industry is rapidly growing and its technology is being used in many different industries and applications.", "id": "alpaca-107" } ``` An example in `ar` looks as follows. ```json { "instruction": "قم بالوصول إلى إعدادات المتصفح الافتراضية على جهاز الكمبيوتر.", "input": "", "output": "لا يمكن لي كمساعد افتراضي القيام بهذه المهمة كونها تحتاج إلى الوصول إلى الجهاز المادي. يرجى الرجوع إلى دليل المستخدم للكمبيوتر الخاص بك أو البحث على الإنترنت لمعرفة كيفية الوصول إلى إعدادات المتصفح الافتراضية على جهاز الكمبيوتر الخاص بك.", "id": "alpaca-41997" } ``` An example in `id` looks as follows. ```json { "instruction": "Berapa banyak angka penting yang harus digunakan untuk nilai 0,000187?", "input": "", "output": "Ada tiga angka penting dalam nilai 0,000187.", "id": "alpaca-40382" } ``` An example in `de` looks as follows. ```json { "instruction": "Komponieren Sie ein Musikstück mit einem Titel, der Trauer bezeichnet.", "input": "", "output": ""Schmerzendes Herz"\n\nDas Stück beginnt mit einer langsamen, traurigen Melodie, gespielt von einem Solo-Violoncello. Die Harmonien, die von einem Klavier begleitet werden, sind durcheinander und dissonant, um ein Gefühl von Schmerz und Trauer zu vermitteln.\n\nIm Laufe des Stücks treten andere Instrumente ein, wie Streicher, Flöte und Oboe, um die Melodie zu unterstützen und zu intensivieren. Der Rhythmus bleibt langsam und schwerfällig, um die Schwere des Schmerzes darzustellen.\n\nIn der Mitte des Stücks gibt es einen Höhepunkt, wo die Melodie und Harmonien sich verdichten und ein Gefühl von Überwältigung erzeugen. Der Solo-Violoncello spielt eine traurige und schnelle Phrase, die die Verzweiflung und Isolation des Protagonisten ausdrückt.\n\nDas Stück endet mit einer Wiederholung der ersten Melodie, gespielt von einem Solo-Klavier, während die anderen Instrumente auslaufen. Die Harmonien werden jedoch weicher und sanfter, um einen Hauch von Hoffnung zu vermitteln, dass der Schmerz langsam vergeht.", "id": "alpaca-33619" } ``` An example in `fr` looks as follows. ```json { "instruction": "Les Ceanothus ont-ils des racines peu profondes ?", "input": "", "output": "En tant qu'IA, je ne peux pas répondre avec une certitude absolue, mais voici des informations générales sur les racines de Ceanothus : \n\nLes Ceanothus ont tendance à avoir un système racinaire étendu et peu profond. Les racines peuvent s'étaler jusqu'à 4 à 6 fois la taille de la plante et s'étendre à environ 60 à 90 cm de profondeur. Cependant, cela peut varier en fonction du type de sol et de la variété de Ceanothus. Certaines variétés de Ceanothus pourraient avoir des racines plus profondes si les conditions s'y prêtent.", "id": "dolly-10940" } ``` ### Data in 52 Languages \| No \| Languages \| Code \| Train \| \| ---\|---------------- \| ----- \| ----- \| \| 1 \| [Afrikaans](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/af) \| af_ZA \| 67017 \| \| 2 \| [Arabic](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/ar) \| ar_AR \| 67017 \| \| 3 \| [Azerbaijani](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/az) \| az_AZ \| 67017 \| \| 4 \| [Bengali](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/bn) \| bn_IN \| 67017 \| \| 5 \| [Czech](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/cs) \| cs_CZ \| 67017 \| \| 6 \| [German](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/de) \| de_DE \| 67017 \| \| 7 \| [English](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/en) \| en_XX \| 67017 \| \| 8 \| [Spanish](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/es) \| es_XX \| 67017 \| \| 9 \| [Estonian](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/et) \| et_EE \| 67017 \| \| 10 \| [Persian](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/fa) \| fa_IR \| 67017 \| \| 11 \| [Finnish](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/fi) \| fi_FI \| 67017 \| \| 12 \| [French](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/fr) \| fr_XX \| 67017 \| \| 13 \| [Galician](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/gl) \| gl_ES \| 67017 \| \| 14 \| [Gujarati](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/gu) \| gu_IN \| 67017 \| \| 15 \| [Hebrew](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/he) \| he_IL \| 67017 \| \| 16 \| [Hindi](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/hi) \| hi_IN \| 67017 \| \| 17 \| [Croatian](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/hr) \| hr_HR \| 67017 \| \| 18 \| [Indonesian](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/id) \| id_ID \| 67017 \| \| 19 \| [Italian](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/it) \| it_IT \| 67017 \| \| 20 \| [Japanese](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/ja) \| ja_XX \| 67017 \| \| 21 \| [Georgian](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/ka) \| ka_GE \| 67017 \| \| 22 \| [Kazakh](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/kk) \| kk_KZ \| 67017 \| \| 23 \| [Khmer](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/km) \| km_KH \| 67017 \| \| 24 \| [Korean](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/ko) \| ko_KR \| 67017 \| \| 25 \| [Lithuanian](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/lt) \| lt_LT \| 67017 \| \| 26 \| [Latvian](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/lv) \| lv_LV \| 67017 \| \| 27 \| [Macedonian](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/mk) \| mk_MK \| 67017 \| \| 28 \| [Malayalam](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/ml) \| ml_IN \| 67017 \| \| 29 \| [Mongolian](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/mn) \| mn_MN \| 67017 \| \| 30 \| [Marathi](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/mr) \| mr_IN \| 67017 \| \| 31 \| [Burmese](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/my) \| my_MM \| 67017 \| \| 32 \| [Nepali](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/ne) \| ne_NP \| 67017 \| \| 33 \| [Dutch](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/nl) \| nl_XX \| 67017 \| \| 34 \| [Polish](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/pl) \| pl_PL \| 67017 \| \| 35 \| [Pashto](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/ps) \| ps_AF \| 67017 \| \| 36 \| [Portuguese](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/pt) \| pt_XX \| 67017 \| \| 37 \| [Romanian](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/ro) \| ro_RO \| 67017 \| \| 38 \| [Russian](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/ru) \| ru_RU \| 67017 \| \| 39 \| [Sinhala](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/si) \| si_LK \| 67017 \| \| 40 \| [Slovene](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/sl) \| sl_SI \| 67017 \| \| 41 \| [Swedish](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/sv) \| sv_SE \| 67017 \| \| 42 \| [Swahili](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/sw) \| sw_KE \| 67017 \| \| 43 \| [Tamil](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/ta) \| ta_IN \| 67017 \| \| 44 \| [Telugu](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/te) \| te_IN \| 67017 \| \| 45 \| [Thai](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/th) \| th_TH \| 67017 \| \| 46 \| [Tagalog](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/tl) \| tl_XX \| 67017 \| \| 47 \| [Turkish](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/tr) \| tr_TR \| 67017 \| \| 48 \| [Ukrainian](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/uk) \| uk_UA \| 67017 \| \| 49 \| [Urdu](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/ur) \| ur_PK \| 67017 \| \| 50 \| [Vietnamese](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/vi) \| vi_VN \| 67017 \| \| 51 \| [Xhosa](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/xh) \| xh_ZA \| 67017 \| \| 52 \| [Chinese](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/zh) \| zh_CN \| 67017 \| ## C. Dataset Creation 1. English Instructions: The English instuctions are obtained from [alpaca-53k](https://github.com/tatsu-lab/stanford_alpaca), and [dolly-15k](https://github.com/databrickslabs/dolly/tree/master/data). 2. Instruction Translation: The instructions (and inputs) are translated into 51 languages using Google Translation API (conducted on April 2023). 3. Output Generation: We generate output from `gpt-3.5-turbo` for each language (conducted on April 2023). ## D. Considerations for Using the Data ### Social Impact of Dataset NLP for everyone: this dataset helps to democratize the cutting-edge instruction-following models in 52 languages. This dataset also allows the first experiment on the multilingual LoRA-based LLaMA model. ### Discussion of Biases (1) Translation bias; (2) Potential English-culture bias in the translated dataset. ### Other Known Limitations The `Bactrian-X` data is generated by a language model (`gpt-3.5-turbo`) and inevitably contains some errors or biases. We encourage users to use this data with caution and propose new methods to filter or improve the imperfections. ## E. Additional Information ### Dataset Curators [Haonan Li](https://haonan-li.github.io/) and [Fajri Koto](http://www.fajrikoto.com) ### Licensing Information The dataset is available under the [Creative Commons NonCommercial (CC BY-NC 4.0)](https://creativecommons.org/licenses/by-nc/4.0/legalcode). ### Citation Information ``` @misc{li2023bactrianx, title={Bactrian-X : A Multilingual Replicable Instruction-Following Model with Low-Rank Adaptation}, author={Haonan Li and Fajri Koto and Minghao Wu and Alham Fikri Aji and Timothy Baldwin}, year={2023}, eprint={2305.15011}, archivePrefix={arXiv}, primaryClass={cs.CL} } ``` ### Contributions Thanks to [@haonan-li](https://github.com/haonan-li), [@fajri91](https://github.com/fajri91) for adding this dataset.
qiaojin/PubMedQA	qiaojin	"2024-03-06T01:50:16Z"	14,569	204	[ "task_categories:question-answering", "task_ids:multiple-choice-qa", "annotations_creators:expert-generated", "annotations_creators:machine-generated", "language_creators:expert-generated", "multilinguality:monolingual", "source_datasets:original", "language:en", "license:mit", "size_categories:100K<n<1M", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "arxiv:1909.06146", "region:us" ]	[ "question-answering" ]	"2022-03-02T23:29:22Z"	--- annotations_creators: - expert-generated - machine-generated language_creators: - expert-generated language: - en license: - mit multilinguality: - monolingual size_categories: - 100K<n<1M - 10K<n<100K - 1K<n<10K source_datasets: - original task_categories: - question-answering task_ids: - multiple-choice-qa paperswithcode_id: pubmedqa pretty_name: PubMedQA config_names: - pqa_artificial - pqa_labeled - pqa_unlabeled dataset_info: - config_name: pqa_artificial features: - name: pubid dtype: int32 - name: question dtype: string - name: context sequence: - name: contexts dtype: string - name: labels dtype: string - name: meshes dtype: string - name: long_answer dtype: string - name: final_decision dtype: string splits: - name: train num_bytes: 443501057 num_examples: 211269 download_size: 233411194 dataset_size: 443501057 - config_name: pqa_labeled features: - name: pubid dtype: int32 - name: question dtype: string - name: context sequence: - name: contexts dtype: string - name: labels dtype: string - name: meshes dtype: string - name: reasoning_required_pred dtype: string - name: reasoning_free_pred dtype: string - name: long_answer dtype: string - name: final_decision dtype: string splits: - name: train num_bytes: 2088898 num_examples: 1000 download_size: 1075513 dataset_size: 2088898 - config_name: pqa_unlabeled features: - name: pubid dtype: int32 - name: question dtype: string - name: context sequence: - name: contexts dtype: string - name: labels dtype: string - name: meshes dtype: string - name: long_answer dtype: string splits: - name: train num_bytes: 125922964 num_examples: 61249 download_size: 66010017 dataset_size: 125922964 configs: - config_name: pqa_artificial data_files: - split: train path: pqa_artificial/train-* - config_name: pqa_labeled data_files: - split: train path: pqa_labeled/train-* - config_name: pqa_unlabeled data_files: - split: train path: pqa_unlabeled/train-* --- # Dataset Card for [Dataset Name] ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - Homepage: [PubMedQA homepage](https://pubmedqa.github.io/ ) - Repository: [PubMedQA repository](https://github.com/pubmedqa/pubmedqa) - Paper: [PubMedQA: A Dataset for Biomedical Research Question Answering](https://arxiv.org/abs/1909.06146) - Leaderboard: [PubMedQA: Leaderboard](https://pubmedqa.github.io/) ### Dataset Summary The task of PubMedQA is to answer research questions with yes/no/maybe (e.g.: Do preoperative statins reduce atrial fibrillation after coronary artery bypass grafting?) using the corresponding abstracts. ### Supported Tasks and Leaderboards The official leaderboard is available at: https://pubmedqa.github.io/. 500 questions in the `pqa_labeled` are used as the test set. They can be found at https://github.com/pubmedqa/pubmedqa. ### Languages English ## Dataset Structure ### Data Instances [More Information Needed] ### Data Fields [More Information Needed] ### Data Splits [More Information Needed] ## Dataset Creation ### Curation Rationale [More Information Needed] ### Source Data #### Initial Data Collection and Normalization [More Information Needed] #### Who are the source language producers? [More Information Needed] ### Annotations #### Annotation process [More Information Needed] #### Who are the annotators? [More Information Needed] ### Personal and Sensitive Information [More Information Needed] ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed] ### Discussion of Biases [More Information Needed] ### Other Known Limitations [More Information Needed] ## Additional Information ### Dataset Curators [More Information Needed] ### Licensing Information [More Information Needed] ### Citation Information [More Information Needed] ### Contributions Thanks to [@tuner007](https://github.com/tuner007) for adding this dataset.
zhoujt1994/HumanCellEpigenomeAtlas_sc_allc	zhoujt1994	"2025-03-17T13:52:53Z"	14,564	0	[ "license:mit", "region:us" ]	null	"2025-03-16T22:31:29Z"	--- license: mit ---
eduagarcia-temp/OSCAR-2301_meta	eduagarcia-temp	"2023-08-28T14:07:22Z"	14,552	0	[ "size_categories:10M<n<100M", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]	null	"2023-08-27T20:24:54Z"	--- dataset_info: features: - name: id dtype: int64 - name: text dtype: string - name: meta struct: - name: categories sequence: string - name: dedup struct: - name: exact_norm struct: - name: cluster_main_idx dtype: int64 - name: cluster_size dtype: int64 - name: exact_hash_idx dtype: int64 - name: is_duplicate dtype: bool - name: minhash struct: - name: cluster_main_idx dtype: int64 - name: cluster_size dtype: int64 - name: is_duplicate dtype: bool - name: minhash_idx dtype: int64 - name: harmful_pp dtype: float64 - name: identification struct: - name: label dtype: string - name: prob dtype: float64 - name: quality_warnings sequence: string - name: sentence_identifications list: - name: label dtype: string - name: prob dtype: float64 - name: tlsh dtype: string - name: warc_headers struct: - name: content-length dtype: int64 - name: content-type dtype: string - name: warc-block-digest dtype: string - name: warc-date dtype: string - name: warc-identified-content-language dtype: string - name: warc-record-id dtype: string - name: warc-refers-to dtype: string - name: warc-target-uri dtype: string - name: warc-type dtype: string splits: - name: train num_bytes: 127702717461 num_examples: 18031400 download_size: 40317121912 dataset_size: 127702717461 --- # Dataset Card for "OSCAR-2301_meta" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
OpenGVLab/OmniCorpus-CC	OpenGVLab	"2025-03-20T12:32:06Z"	14,513	16	[ "task_categories:image-to-text", "task_categories:visual-question-answering", "language:en", "license:cc-by-4.0", "size_categories:100M<n<1B", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "arxiv:2406.08418", "region:us" ]	[ "image-to-text", "visual-question-answering" ]	"2024-08-30T06:16:02Z"	--- language: - en license: cc-by-4.0 size_categories: - 100M<n<1B task_categories: - image-to-text - visual-question-answering dataset_info: - config_name: CC-MAIN-2013-20 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 19908676196 num_examples: 3878063 download_size: 9303464923 dataset_size: 19908676196 - config_name: CC-MAIN-2013-48 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 15282078925 num_examples: 3091537 download_size: 6965036866 dataset_size: 15282078925 - config_name: CC-MAIN-2014-10 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 7227087609 num_examples: 1390034 download_size: 3259239561 dataset_size: 7227087609 - config_name: CC-MAIN-2014-15 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 10106913108 num_examples: 1968361 download_size: 4567738362 dataset_size: 10106913108 - config_name: CC-MAIN-2014-23 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 7997621043 num_examples: 1455331 download_size: 3468852905 dataset_size: 7997621043 - config_name: CC-MAIN-2014-35 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 6228103779 num_examples: 1219200 download_size: 2849584613 dataset_size: 6228103779 - config_name: CC-MAIN-2014-41 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 8321822952 num_examples: 1573955 download_size: 3775989970 dataset_size: 8321822952 - config_name: CC-MAIN-2014-42 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 7732679416 num_examples: 1511931 download_size: 3505766162 dataset_size: 7732679416 - config_name: CC-MAIN-2014-49 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 4473311810 num_examples: 837735 download_size: 1982728919 dataset_size: 4473311810 - config_name: CC-MAIN-2014-52 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 7292722888 num_examples: 1304730 download_size: 2957626766 dataset_size: 7292722888 - config_name: CC-MAIN-2015-06 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 5775826679 num_examples: 1061940 download_size: 2462379667 dataset_size: 5775826679 - config_name: CC-MAIN-2015-11 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 6263650452 num_examples: 1129411 download_size: 2528026633 dataset_size: 6263650452 - config_name: CC-MAIN-2015-14 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 4524425019 num_examples: 885221 download_size: 1939222111 dataset_size: 4524425019 - config_name: CC-MAIN-2015-18 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 6195227565 num_examples: 1104115 download_size: 2634204322 dataset_size: 6195227565 - config_name: CC-MAIN-2015-22 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 7008276790 num_examples: 1290530 download_size: 2913627974 dataset_size: 7008276790 - config_name: CC-MAIN-2015-27 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 4320140953 num_examples: 784496 download_size: 1828575226 dataset_size: 4320140953 - config_name: CC-MAIN-2015-32 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 4952806590 num_examples: 875601 download_size: 2065207099 dataset_size: 4952806590 - config_name: CC-MAIN-2015-35 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 6053257306 num_examples: 1086470 download_size: 2632032769 dataset_size: 6053257306 - config_name: CC-MAIN-2015-40 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 5206096790 num_examples: 924036 download_size: 2203603087 dataset_size: 5206096790 - config_name: CC-MAIN-2015-48 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 8343050753 num_examples: 1537468 download_size: 3489600630 dataset_size: 8343050753 - config_name: CC-MAIN-2016-07 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 9329220105 num_examples: 1738650 download_size: 4005599785 dataset_size: 9329220105 - config_name: CC-MAIN-2016-18 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 3897220786 num_examples: 747570 download_size: 1675500816 dataset_size: 3897220786 - config_name: CC-MAIN-2016-22 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 4623903344 num_examples: 857060 download_size: 2000624854 dataset_size: 4623903344 - config_name: CC-MAIN-2016-26 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 3414418701 num_examples: 627995 download_size: 1403890884 dataset_size: 3414418701 - config_name: CC-MAIN-2016-30 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 7244342539 num_examples: 1183776 download_size: 2913394840 dataset_size: 7244342539 - config_name: CC-MAIN-2016-36 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 5402565529 num_examples: 915878 download_size: 2248454753 dataset_size: 5402565529 - config_name: CC-MAIN-2016-40 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 5938544915 num_examples: 1113534 download_size: 2530904625 dataset_size: 5938544915 - config_name: CC-MAIN-2016-44 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 15819536321 num_examples: 3528637 download_size: 6516546200 dataset_size: 15819536321 - config_name: CC-MAIN-2016-50 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 10822695594 num_examples: 2215939 download_size: 4439728574 dataset_size: 10822695594 - config_name: CC-MAIN-2017-04 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 11949732148 num_examples: 2441316 download_size: 5045763620 dataset_size: 11949732148 - config_name: CC-MAIN-2017-09 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 12473370126 num_examples: 2561539 download_size: 5398993614 dataset_size: 12473370126 - config_name: CC-MAIN-2017-13 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 12209904783 num_examples: 2458486 download_size: 5422393873 dataset_size: 12209904783 - config_name: CC-MAIN-2017-17 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 13763109013 num_examples: 2615558 download_size: 6025106556 dataset_size: 13763109013 - config_name: CC-MAIN-2017-22 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 14456991831 num_examples: 2775332 download_size: 6258001465 dataset_size: 14456991831 - config_name: CC-MAIN-2017-26 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 15036103558 num_examples: 2973499 download_size: 6813218532 dataset_size: 15036103558 - config_name: CC-MAIN-2017-30 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 18833639414 num_examples: 3870197 download_size: 8464443468 dataset_size: 18833639414 - config_name: CC-MAIN-2017-34 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 25828116836 num_examples: 4848154 download_size: 11599137919 dataset_size: 25828116836 - config_name: CC-MAIN-2017-39 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 29432150311 num_examples: 4840435 download_size: 13172655761 dataset_size: 29432150311 - config_name: CC-MAIN-2017-43 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 32672966840 num_examples: 5724493 download_size: 15041820212 dataset_size: 32672966840 - config_name: CC-MAIN-2017-47 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 34301891443 num_examples: 5291581 download_size: 15593452226 dataset_size: 34301891443 - config_name: CC-MAIN-2017-51 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 30012533603 num_examples: 5466672 download_size: 14005518471 dataset_size: 30012533603 - config_name: CC-MAIN-2018-05 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 47738703452 num_examples: 8053879 download_size: 22533983733 dataset_size: 47738703452 - config_name: CC-MAIN-2018-09 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 45503126107 num_examples: 8045410 download_size: 21900491411 dataset_size: 45503126107 - config_name: CC-MAIN-2018-13 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 43904789090 num_examples: 7980931 download_size: 21178075620 dataset_size: 43904789090 - config_name: CC-MAIN-2018-17 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 44481167440 num_examples: 8699878 download_size: 21623780968 dataset_size: 44481167440 - config_name: CC-MAIN-2018-22 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 64369136465 num_examples: 13332059 download_size: 32293951649 dataset_size: 64369136465 - config_name: CC-MAIN-2018-26 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 81232597180 num_examples: 16249638 download_size: 41007491366 dataset_size: 81232597180 - config_name: CC-MAIN-2018-30 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 151537007358 num_examples: 32535697 download_size: 77517210537 dataset_size: 151537007358 - config_name: CC-MAIN-2018-34 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 39026071869 num_examples: 6347230 download_size: 19285382621 dataset_size: 39026071869 - config_name: CC-MAIN-2018-39 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 35948493161 num_examples: 6372711 download_size: 17597722170 dataset_size: 35948493161 - config_name: CC-MAIN-2018-43 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 50928918805 num_examples: 8758225 download_size: 25291022646 dataset_size: 50928918805 - config_name: CC-MAIN-2018-47 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 43961213014 num_examples: 7270815 download_size: 22024998684 dataset_size: 43961213014 - config_name: CC-MAIN-2018-51 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 58902353921 num_examples: 10215384 download_size: 29497256483 dataset_size: 58902353921 - config_name: CC-MAIN-2019-04 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 54814836003 num_examples: 9930553 download_size: 27458854931 dataset_size: 54814836003 - config_name: CC-MAIN-2019-09 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 54426174385 num_examples: 8897510 download_size: 28125345656 dataset_size: 54426174385 - config_name: CC-MAIN-2019-13 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 48712051219 num_examples: 7803004 download_size: 25156014252 dataset_size: 48712051219 - config_name: CC-MAIN-2019-18 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 48203751852 num_examples: 7532171 download_size: 24844412087 dataset_size: 48203751852 - config_name: CC-MAIN-2019-22 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 51674379059 num_examples: 8339842 download_size: 26257475492 dataset_size: 51674379059 - config_name: CC-MAIN-2019-26 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 43336967638 num_examples: 7320268 download_size: 21900316910 dataset_size: 43336967638 - config_name: CC-MAIN-2019-30 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 46313133200 num_examples: 7682281 download_size: 23262218065 dataset_size: 46313133200 - config_name: CC-MAIN-2019-35 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 49570657315 num_examples: 8098108 download_size: 24938729240 dataset_size: 49570657315 - config_name: CC-MAIN-2019-39 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 43538081906 num_examples: 7102645 download_size: 21728983014 dataset_size: 43538081906 - config_name: CC-MAIN-2019-43 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 52817470138 num_examples: 8567061 download_size: 26105523209 dataset_size: 52817470138 - config_name: CC-MAIN-2019-47 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 42252827792 num_examples: 6775943 download_size: 21228532199 dataset_size: 42252827792 - config_name: CC-MAIN-2019-51 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 38926356094 num_examples: 6415558 download_size: 19510339598 dataset_size: 38926356094 - config_name: CC-MAIN-2020-05 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 48189844491 num_examples: 7921372 download_size: 24235687030 dataset_size: 48189844491 - config_name: CC-MAIN-2020-10 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 48904133840 num_examples: 8211791 download_size: 24576159189 dataset_size: 48904133840 - config_name: CC-MAIN-2020-16 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 51243682770 num_examples: 8578633 download_size: 25485035979 dataset_size: 51243682770 - config_name: CC-MAIN-2020-24 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 59424939072 num_examples: 10438139 download_size: 29827361603 dataset_size: 59424939072 - config_name: CC-MAIN-2020-29 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 66229730938 num_examples: 11475631 download_size: 33030161773 dataset_size: 66229730938 - config_name: CC-MAIN-2020-34 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 54287690582 num_examples: 9495610 download_size: 27018821467 dataset_size: 54287690582 - config_name: CC-MAIN-2020-40 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 71587907978 num_examples: 12058149 download_size: 35795677487 dataset_size: 71587907978 - config_name: CC-MAIN-2020-45 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 59172857400 num_examples: 9694734 download_size: 29495814784 dataset_size: 59172857400 - config_name: CC-MAIN-2020-50 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 58557861606 num_examples: 9539918 download_size: 29083801775 dataset_size: 58557861606 - config_name: CC-MAIN-2021-04 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 74507336015 num_examples: 12273028 download_size: 36874887518 dataset_size: 74507336015 - config_name: CC-MAIN-2021-10 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 60802783945 num_examples: 10176190 download_size: 30326513365 dataset_size: 60802783945 - config_name: CC-MAIN-2021-17 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 75061494488 num_examples: 12343366 download_size: 37345114890 dataset_size: 75061494488 - config_name: CC-MAIN-2021-21 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 70036417178 num_examples: 11584034 download_size: 34806730527 dataset_size: 70036417178 - config_name: CC-MAIN-2021-25 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 73653674063 num_examples: 12065281 download_size: 36581310312 dataset_size: 73653674063 - config_name: CC-MAIN-2021-31 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 79535885182 num_examples: 13383552 download_size: 39702500971 dataset_size: 79535885182 - config_name: CC-MAIN-2021-39 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 90302065651 num_examples: 14794773 download_size: 45211764750 dataset_size: 90302065651 - config_name: CC-MAIN-2021-43 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 108356023335 num_examples: 17698206 download_size: 54292215300 dataset_size: 108356023335 - config_name: CC-MAIN-2021-49 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 95867022229 num_examples: 15643875 download_size: 47902433321 dataset_size: 95867022229 - config_name: CC-MAIN-2022-05 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 97602903488 num_examples: 15772898 download_size: 48711364812 dataset_size: 97602903488 - config_name: CC-MAIN-2022-21 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 127495492928 num_examples: 21745889 download_size: 63379692210 dataset_size: 127495492928 - config_name: CC-MAIN-2022-27 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 128061655541 num_examples: 21580054 download_size: 63763936007 dataset_size: 128061655541 - config_name: CC-MAIN-2022-33 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 126436062118 num_examples: 21495687 download_size: 63067252044 dataset_size: 126436062118 - config_name: CC-MAIN-2022-40 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 123806739937 num_examples: 20206120 download_size: 61929035270 dataset_size: 123806739937 - config_name: CC-MAIN-2022-49 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 152577158166 num_examples: 24634059 download_size: 76529854484 dataset_size: 152577158166 - config_name: CC-MAIN-2023-06 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 174815301023 num_examples: 28962355 download_size: 87301203013 dataset_size: 174815301023 - config_name: CC-MAIN-2023-14 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 227631152876 num_examples: 37223376 download_size: 114188282465 dataset_size: 227631152876 - config_name: CC-MAIN-2023-23 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 321036722459 num_examples: 52119692 download_size: 161491274249 dataset_size: 321036722459 - config_name: CC-MAIN-2023-40 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 648032999611 num_examples: 101292016 download_size: 317965522325 dataset_size: 648032999611 - config_name: CC-MAIN-2023-50 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 744768384551 num_examples: 117073004 download_size: 365332295606 dataset_size: 744768384551 configs: - config_name: CC-MAIN-2013-20 data_files: - split: train path: CC-MAIN-2013-20/train-* - config_name: CC-MAIN-2013-48 data_files: - split: train path: CC-MAIN-2013-48/train-* - config_name: CC-MAIN-2014-10 data_files: - split: train path: CC-MAIN-2014-10/train-* - config_name: CC-MAIN-2014-15 data_files: - split: train path: CC-MAIN-2014-15/train-* - config_name: CC-MAIN-2014-23 data_files: - split: train path: CC-MAIN-2014-23/train-* - config_name: CC-MAIN-2014-35 data_files: - split: train path: CC-MAIN-2014-35/train-* - config_name: CC-MAIN-2014-41 data_files: - split: train path: CC-MAIN-2014-41/train-* - config_name: CC-MAIN-2014-42 data_files: - split: train path: CC-MAIN-2014-42/train-* - config_name: CC-MAIN-2014-49 data_files: - split: train path: CC-MAIN-2014-49/train-* - config_name: CC-MAIN-2014-52 data_files: - split: train path: CC-MAIN-2014-52/train-* - config_name: CC-MAIN-2015-06 data_files: - split: train path: CC-MAIN-2015-06/train-* - config_name: CC-MAIN-2015-11 data_files: - split: train path: CC-MAIN-2015-11/train-* - config_name: CC-MAIN-2015-14 data_files: - split: train path: CC-MAIN-2015-14/train-* - config_name: CC-MAIN-2015-18 data_files: - split: train path: CC-MAIN-2015-18/train-* - config_name: CC-MAIN-2015-22 data_files: - split: train path: CC-MAIN-2015-22/train-* - config_name: CC-MAIN-2015-27 data_files: - split: train path: CC-MAIN-2015-27/train-* - config_name: CC-MAIN-2015-32 data_files: - split: train path: CC-MAIN-2015-32/train-* - config_name: CC-MAIN-2015-35 data_files: - split: train path: CC-MAIN-2015-35/train-* - config_name: CC-MAIN-2015-40 data_files: - split: train path: CC-MAIN-2015-40/train-* - config_name: CC-MAIN-2015-48 data_files: - split: train path: CC-MAIN-2015-48/train-* - config_name: CC-MAIN-2016-07 data_files: - split: train path: CC-MAIN-2016-07/train-* - config_name: CC-MAIN-2016-18 data_files: - split: train path: CC-MAIN-2016-18/train-* - config_name: CC-MAIN-2016-22 data_files: - split: train path: CC-MAIN-2016-22/train-* - config_name: CC-MAIN-2016-26 data_files: - split: train path: CC-MAIN-2016-26/train-* - config_name: CC-MAIN-2016-30 data_files: - split: train path: CC-MAIN-2016-30/train-* - config_name: CC-MAIN-2016-36 data_files: - split: train path: CC-MAIN-2016-36/train-* - config_name: CC-MAIN-2016-40 data_files: - split: train path: CC-MAIN-2016-40/train-* - config_name: CC-MAIN-2016-44 data_files: - split: train path: CC-MAIN-2016-44/train-* - config_name: CC-MAIN-2016-50 data_files: - split: train path: CC-MAIN-2016-50/train-* - config_name: CC-MAIN-2017-04 data_files: - split: train path: CC-MAIN-2017-04/train-* - config_name: CC-MAIN-2017-09 data_files: - split: train path: CC-MAIN-2017-09/train-* - config_name: CC-MAIN-2017-13 data_files: - split: train path: CC-MAIN-2017-13/train-* - config_name: CC-MAIN-2017-17 data_files: - split: train path: CC-MAIN-2017-17/train-* - config_name: CC-MAIN-2017-22 data_files: - split: train path: CC-MAIN-2017-22/train-* - config_name: CC-MAIN-2017-26 data_files: - split: train path: CC-MAIN-2017-26/train-* - config_name: CC-MAIN-2017-30 data_files: - split: train path: CC-MAIN-2017-30/train-* - config_name: CC-MAIN-2017-34 data_files: - split: train path: CC-MAIN-2017-34/train-* - config_name: CC-MAIN-2017-39 data_files: - split: train path: CC-MAIN-2017-39/train-* - config_name: CC-MAIN-2017-43 data_files: - split: train path: CC-MAIN-2017-43/train-* - config_name: CC-MAIN-2017-47 data_files: - split: train path: CC-MAIN-2017-47/train-* - config_name: CC-MAIN-2017-51 data_files: - split: train path: CC-MAIN-2017-51/train-* - config_name: CC-MAIN-2018-05 data_files: - split: train path: CC-MAIN-2018-05/train-* - config_name: CC-MAIN-2018-09 data_files: - split: train path: CC-MAIN-2018-09/train-* - config_name: CC-MAIN-2018-13 data_files: - split: train path: CC-MAIN-2018-13/train-* - config_name: CC-MAIN-2018-17 data_files: - split: train path: CC-MAIN-2018-17/train-* - config_name: CC-MAIN-2018-22 data_files: - split: train path: CC-MAIN-2018-22/train-* - config_name: CC-MAIN-2018-26 data_files: - split: train path: CC-MAIN-2018-26/train-* - config_name: CC-MAIN-2018-30 data_files: - split: train path: CC-MAIN-2018-30/train-* - config_name: CC-MAIN-2018-34 data_files: - split: train path: CC-MAIN-2018-34/train-* - config_name: CC-MAIN-2018-39 data_files: - split: train path: CC-MAIN-2018-39/train-* - config_name: CC-MAIN-2018-43 data_files: - split: train path: CC-MAIN-2018-43/train-* - config_name: CC-MAIN-2018-47 data_files: - split: train path: CC-MAIN-2018-47/train-* - config_name: CC-MAIN-2018-51 data_files: - split: train path: CC-MAIN-2018-51/train-* - config_name: CC-MAIN-2019-04 data_files: - split: train path: CC-MAIN-2019-04/train-* - config_name: CC-MAIN-2019-09 data_files: - split: train path: CC-MAIN-2019-09/train-* - config_name: CC-MAIN-2019-13 data_files: - split: train path: CC-MAIN-2019-13/train-* - config_name: CC-MAIN-2019-18 data_files: - split: train path: CC-MAIN-2019-18/train-* - config_name: CC-MAIN-2019-22 data_files: - split: train path: CC-MAIN-2019-22/train-* - config_name: CC-MAIN-2019-26 data_files: - split: train path: CC-MAIN-2019-26/train-* - config_name: CC-MAIN-2019-30 data_files: - split: train path: CC-MAIN-2019-30/train-* - config_name: CC-MAIN-2019-35 data_files: - split: train path: CC-MAIN-2019-35/train-* - config_name: CC-MAIN-2019-39 data_files: - split: train path: CC-MAIN-2019-39/train-* - config_name: CC-MAIN-2019-43 data_files: - split: train path: CC-MAIN-2019-43/train-* - config_name: CC-MAIN-2019-47 data_files: - split: train path: CC-MAIN-2019-47/train-* - config_name: CC-MAIN-2019-51 data_files: - split: train path: CC-MAIN-2019-51/train-* - config_name: CC-MAIN-2020-05 data_files: - split: train path: CC-MAIN-2020-05/train-* - config_name: CC-MAIN-2020-10 data_files: - split: train path: CC-MAIN-2020-10/train-* - config_name: CC-MAIN-2020-16 data_files: - split: train path: CC-MAIN-2020-16/train-* - config_name: CC-MAIN-2020-24 data_files: - split: train path: CC-MAIN-2020-24/train-* - config_name: CC-MAIN-2020-29 data_files: - split: train path: CC-MAIN-2020-29/train-* - config_name: CC-MAIN-2020-34 data_files: - split: train path: CC-MAIN-2020-34/train-* - config_name: CC-MAIN-2020-40 data_files: - split: train path: CC-MAIN-2020-40/train-* - config_name: CC-MAIN-2020-45 data_files: - split: train path: CC-MAIN-2020-45/train-* - config_name: CC-MAIN-2020-50 data_files: - split: train path: CC-MAIN-2020-50/train-* - config_name: CC-MAIN-2021-04 data_files: - split: train path: CC-MAIN-2021-04/train-* - config_name: CC-MAIN-2021-10 data_files: - split: train path: CC-MAIN-2021-10/train-* - config_name: CC-MAIN-2021-17 data_files: - split: train path: CC-MAIN-2021-17/train-* - config_name: CC-MAIN-2021-21 data_files: - split: train path: CC-MAIN-2021-21/train-* - config_name: CC-MAIN-2021-25 data_files: - split: train path: CC-MAIN-2021-25/train-* - config_name: CC-MAIN-2021-31 data_files: - split: train path: CC-MAIN-2021-31/train-* - config_name: CC-MAIN-2021-39 data_files: - split: train path: CC-MAIN-2021-39/train-* - config_name: CC-MAIN-2021-43 data_files: - split: train path: CC-MAIN-2021-43/train-* - config_name: CC-MAIN-2021-49 data_files: - split: train path: CC-MAIN-2021-49/train-* - config_name: CC-MAIN-2022-05 data_files: - split: train path: CC-MAIN-2022-05/train-* - config_name: CC-MAIN-2022-21 data_files: - split: train path: CC-MAIN-2022-21/train-* - config_name: CC-MAIN-2022-27 data_files: - split: train path: CC-MAIN-2022-27/train-* - config_name: CC-MAIN-2022-33 data_files: - split: train path: CC-MAIN-2022-33/train-* - config_name: CC-MAIN-2022-40 data_files: - split: train path: CC-MAIN-2022-40/train-* - config_name: CC-MAIN-2022-49 data_files: - split: train path: CC-MAIN-2022-49/train-* - config_name: CC-MAIN-2023-06 data_files: - split: train path: CC-MAIN-2023-06/train-* - config_name: CC-MAIN-2023-14 data_files: - split: train path: CC-MAIN-2023-14/train-* - config_name: CC-MAIN-2023-23 data_files: - split: train path: CC-MAIN-2023-23/train-* - config_name: CC-MAIN-2023-40 data_files: - split: train path: CC-MAIN-2023-40/train-* - config_name: CC-MAIN-2023-50 data_files: - split: train path: CC-MAIN-2023-50/train-* --- <p align="center"> <h1 align="center">🐳 OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text</h1> </p> > ⭐️ NOTE: Several parquet files were marked unsafe (viruses) by official scaning of hf, while they are reported safe by ClamAV and Virustotal. > We found [many false positive cases](https://discuss.huggingface.co/u/mcpotato/summary) of the hf automatic scanning in hf discussions and raise [one discussion](https://discuss.huggingface.co/t/one-parquet-file-of-my-dataset-was-marked-unsafe/113745) to ask for a re-scanning. This is the repository of OmniCorpus-CC, which contains 988 million image-text interleaved documents collected from [Common Crawl](https://commoncrawl.org/). - Repository: https://github.com/OpenGVLab/OmniCorpus - Paper (ICLR 2025 Spotlight): https://arxiv.org/abs/2406.08418 OmniCorpus dataset is a large-scale image-text interleaved dataset, which pushes the boundaries of scale and diversity by encompassing 8.6 billion images interleaved with 1,696 text tokens from diverse sources, significantly surpassing previous datasets. This dataset demonstrates several advantages over its counterparts: 1. Larger data scale: Our dataset is 1.7 times larger in images and 12.5 times larger in texts compared to the previously largest multimodal dataset, LAION-5B, while maintaining excellent data quality. 2. Richer data diversity: Drawing from a broader range of data sources, our dataset is more diverse than other image-text interleaved datasets. It includes bilingual multimodal data in both Chinese and English, and encompasses text-centric and vision-centric documents extracted from common websites and video platforms. 3. More flexible format: The streaming data format of our dataset offers exceptional flexibility, allowing adaptation to various data structures, including pure text corpora, image-text pairs, and interleaved data formats. <img width="578" alt="image" src="https://github.com/OpenGVLab/OmniCorpus/assets/47669167/641a6427-ba50-41e6-8634-8810113fd803"> The OmniCorpus contains three sections: - OmniCorpus-CC: processed from dumps in Common Crawl from 2013 to Nov./Dec. 2023. - OmniCorpus-CW: sourced from Chinese internet resources, will be availiable in [OpenDataLab](https://opendatalab.com/) platform. - OmniCorpus-YT: samples Youtube video frames as images and collects subtitles as texts. Code for pre-training, evaluating, main body extracting, and filtering have been released in the official [repository](https://github.com/OpenGVLab/OmniCorpus). A pre-trained model is availiable [here](https://huggingface.co/Qingyun/OmniCorpus-InternVL). # Data Pipeline Our data pipeline consists of five key stages: main body extraction, preliminary text filtering, document deduplication, image downloading \& filtering, and detailed text filtering. Each stage efficiently reduces the dataset to retain only high-quality data. Please refer to our paper for more details about the data pipeline. <img width="723" alt="image" src="https://github.com/OpenGVLab/OmniCorpus/assets/47669167/a6de8928-58fb-4ff4-8ef9-4bd90e9ada5f"> # Usages The image-text interleaved documents are recommanded for the following usages: - Pre-training multimodal large language model (MLLM): Recent MLLMs (such as Flamingo series, EMU series, IDEFICS series, MM1, Cambrian-1, and xGen-MM) have shown that image-text interleaved data aids multimodal in-context learning and maintains the capabilities of large language models during multimodal fine-tuning. - Long text-image retrieval: We provide image-text similarities calculated with CLIP, which can convert the documents to image-text retrieval dataset with longer text. A retrieval model pre-trained on such data can retrieval images based on longer text, which can be used for multimodal RAG, converting pure text to multimodal sample, etc. - Source for futher dataset research: Our data is large-scale, which can serve as the source for researches for data curation strategies. We provide many useful attributes as metadata for each document, which can enrich the filtering strategy and reduce the cost. - ...... # Data Format Following common practices, the data is organized into Parquet file format. You might encounter errors when using `pandas.read_parquet` (because the data structure contains nested elements). We recommend using fastparquet to load the parquet files. ```Python import fastparquet df = fastparquet.ParquetFile(parquet_file_path).to_pandas() # You can also use iter_batches parquet_file = pq.ParquetFile(filepath) for batch in parquet_file.iter_batches(): df = batch.to_pandas() ``` You can convert the i-th document and convert it into a dictionary. ```Python doc_dict = df.iloc[i].to_dict() ``` The document format is as follow: ```json { 'images': [ <str: image_1_url>, None, <str: image_2_url>, None, ], 'texts': [ None, <str: text_paragraph_1_content> None, <str: text_paragraph_2_content>, ] 'metadata': [ <dict: image_1_metadata>, None, <dict: image_2_metadata>, None ], 'general_metadata': { "url": <str: document url>, "id": <str: document id>, "domain": <list[str]: domains extracted from document url>, "fluency_prob": <float: the probability of fluency>, "non_advertisement_prob": <float: the probability of non-advertisement>, "porn_prob": <float: the probability of porn content>, "politics_prob": <float: the probability of politics content>, "toxic_prob": <float: the probability of toxic content>, } } ``` Each image metadata is as follow: ```json { "img_url_sha": <str: sha code of image url>, "width": <int: image width>, "height": <int: image height>, "bytes": <int: byte number of the image file>, "d_hash": <str: d_hash code of the image, used for image deduplication>, "p_hash": <str: p_hash code of the image, used for image deduplication>, "d_hash_dup_count": <int: duplicated times detected by d_hash code>, "p_hash_dup_count": <int: duplicated times detected by p_hash code>, "aesthetic prob": <float: aesthetic probility>, "unsafe prob": <float: NSFW probility>, } ``` # License and Terms of Use The OmniCorpus dataset is distributed under [the CC BY 4.0 License](https://creativecommons.org/licenses/by/4.0/). The open-source code is released under the [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0). The Terms of Use (ToUs) have been developed based on widely accepted standards. By accessing or using this dataset, users acknowledge their responsibility to comply with all relevant legal, regulatory, and ethical standards. - All users, whether from academia or industry, must comply with the ToUs outlined in the CC BY 4.0 License. - Any derived datasets or models must acknowledge the use of the OmniCorpus dataset to maintain transparency. - The OmniCorpus must not be used in any project involving sensitive content or harmful outcomes, including but not limited to political manipulation, hate speech generation, misinformation propagation, or tasks that perpetuate harmful stereotypes or biases. - The use of this dataset in any manner that violates rights, such as copyright infringement, privacy breaches, or misuse of sensitive information, is strictly prohibited. - While we do not enforce jurisdiction-specific terms, we strongly recommend that users ensure compliance with applicable local laws and regulations. - The use of specific subset must comply with the ToUs of the primary source. Specifically, the use of OmniCorpus-CC, OmniCorpus-CW, and OmniCorpus-YT must comply with [the Common Crawl ToUs](https://commoncrawl.org/terms-of-use), the [regulations](https://www.gov.cn/zhengce/content/202409/content\_6977766.htm) on the security management of Internet data in China, and [YouTube’s ToUs](https://www.youtube.com/terms), respectively. - These ToUs do not supersede the ToUs of the original content sources. Users must ensure that any use of the dataset’s content complies with the original ToUs and the rights of the data subjects. # Citation ``` @inproceedings{li2024omnicorpus, title={OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text}, author={Li, Qingyun and Chen, Zhe and Wang, Weiyun and Wang, Wenhai and Ye, Shenglong and Jin, Zhenjiang and others}, booktitle={The Thirteenth International Conference on Learning Representations}, year={2025} } ```
haonan-li/cmmlu	haonan-li	"2023-07-13T10:19:29Z"	14,504	66	[ "task_categories:multiple-choice", "task_categories:question-answering", "language:zh", "license:cc-by-nc-4.0", "size_categories:10K<n<100K", "modality:text", "library:datasets", "library:mlcroissant", "arxiv:2306.09212", "region:us", "chinese", "llm", "evaluation" ]	[ "multiple-choice", "question-answering" ]	"2023-06-25T16:37:44Z"	--- license: cc-by-nc-4.0 task_categories: - multiple-choice - question-answering language: - zh tags: - chinese - llm - evaluation pretty_name: CMMLU size_categories: - 10K<n<100K --- # CMMLU: Measuring massive multitask language understanding in Chinese - Homepage: [https://github.com/haonan-li/CMMLU](https://github.com/haonan-li/CMMLU) - Repository: [https://huggingface.co/datasets/haonan-li/cmmlu](https://huggingface.co/datasets/haonan-li/cmmlu) - Paper: [CMMLU: Measuring Chinese Massive Multitask Language Understanding](https://arxiv.org/abs/2306.09212). ## Table of Contents - [Introduction](#introduction) - [Leaderboard](#leaderboard) - [Data](#data) - [Citation](#citation) - [License](#license) ## Introduction CMMLU is a comprehensive Chinese assessment suite specifically designed to evaluate the advanced knowledge and reasoning abilities of LLMs within the Chinese language and cultural context. CMMLU covers a wide range of subjects, comprising 67 topics that span from elementary to advanced professional levels. It includes subjects that require computational expertise, such as physics and mathematics, as well as disciplines within humanities and social sciences. Many of these tasks are not easily translatable from other languages due to their specific contextual nuances and wording. Furthermore, numerous tasks within CMMLU have answers that are specific to China and may not be universally applicable or considered correct in other regions or languages. ## Leaderboard Latest leaderboard is in our [github](https://github.com/haonan-li/CMMLU). ## Data We provide development and test dataset for each of 67 subjects, with 5 questions in development set and 100+ quesitons in test set. Each question in the dataset is a multiple-choice questions with 4 choices and only one choice as the correct answer. Here are two examples: ``` 题目：同一物种的两类细胞各产生一种分泌蛋白，组成这两种蛋白质的各种氨基酸含量相同，但排列顺序不同。其原因是参与这两种蛋白质合成的： A. tRNA种类不同 B. 同一密码子所决定的氨基酸不同 C. mRNA碱基序列不同 D. 核糖体成分不同答案是：C ``` ``` 题目：某种植物病毒V是通过稻飞虱吸食水稻汁液在水稻间传播的。稻田中青蛙数量的增加可减少该病毒在水稻间的传播。下列叙述正确的是： A. 青蛙与稻飞虱是捕食关系 B. 水稻和病毒V是互利共生关系 C. 病毒V与青蛙是寄生关系 D. 水稻与青蛙是竞争关系答案是： ``` #### Load data ```python from datasets import load_dataset cmmlu=load_dataset(r"haonan-li/cmmlu", 'agronomy') print(cmmlu['test'][0]) ``` #### Load all data at once ```python task_list = ['agronomy', 'anatomy', 'ancient_chinese', 'arts', 'astronomy', 'business_ethics', 'chinese_civil_service_exam', 'chinese_driving_rule', 'chinese_food_culture', 'chinese_foreign_policy', 'chinese_history', 'chinese_literature', 'chinese_teacher_qualification', 'clinical_knowledge', 'college_actuarial_science', 'college_education', 'college_engineering_hydrology', 'college_law', 'college_mathematics', 'college_medical_statistics', 'college_medicine', 'computer_science', 'computer_security', 'conceptual_physics', 'construction_project_management', 'economics', 'education', 'electrical_engineering', 'elementary_chinese', 'elementary_commonsense', 'elementary_information_and_technology', 'elementary_mathematics', 'ethnology', 'food_science', 'genetics', 'global_facts', 'high_school_biology', 'high_school_chemistry', 'high_school_geography', 'high_school_mathematics', 'high_school_physics', 'high_school_politics', 'human_sexuality', 'international_law', 'journalism', 'jurisprudence', 'legal_and_moral_basis', 'logical', 'machine_learning', 'management', 'marketing', 'marxist_theory', 'modern_chinese', 'nutrition', 'philosophy', 'professional_accounting', 'professional_law', 'professional_medicine', 'professional_psychology', 'public_relations', 'security_study', 'sociology', 'sports_science', 'traditional_chinese_medicine', 'virology', 'world_history', 'world_religions'] from datasets import load_dataset cmmlu = {k: load_dataset(r"haonan-li/cmmlu", k) for k in task_list} ``` ## Citation ``` @misc{li2023cmmlu, title={CMMLU: Measuring massive multitask language understanding in Chinese}, author={Haonan Li and Yixuan Zhang and Fajri Koto and Yifei Yang and Hai Zhao and Yeyun Gong and Nan Duan and Timothy Baldwin}, year={2023}, eprint={2306.09212}, archivePrefix={arXiv}, primaryClass={cs.CL} } ``` ## License The CMMLU dataset is licensed under a [Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License](http://creativecommons.org/licenses/by-nc-sa/4.0/).
desmondlzy/bigs-data	desmondlzy	"2025-03-11T21:09:56Z"	14,468	0	[ "license:cc-by-sa-4.0", "modality:image", "arxiv:2408.13370", "region:us", "olat" ]	null	"2025-03-10T08:45:14Z"	--- license: cc-by-sa-4.0 tags: - olat pretty_name: 'Dataset for BiGS: Bidirectional Primitives for Relightable 3D Gaussian Splatting' --- # BiGS Dataset The OLAT dataset used in the paper _BiGS: Bidirectional Primitives for Relightable 3D Gaussian Splatting_ (3DV 2025). Check out our [project page](https://desmondlzy.me/publications/bigs/). We provide 7 synthetic scenes in the dataset, featuring various complex light transport effects, such as subsurface scattering, fuzzy surfaces, and iridescent reflection. Each scene (1.8 ~ 3.2 GB) consists of: - 40 training OLAT conditions (`olat_1` - `olat_40`) with 48 views per light condition; - 58 test OLAT conditions (`olat_41` - `olat_98`) with 1 view per light condition; - 1 all-light-on conditions (`olat_all`) with 48 views per light conditions. Each light condition includes `.exr` images, object masks, transforms with camera poses, light positions and intensities. Please refer to our [github repo](https://github.com/desmondlzy/bigs) for how to use the dataset provided here to train BiGS, and our [paper (arxiv)](https://www.arxiv.org/abs/2408.13370) for details of BiGS. ## Citation If you use our dataset in your research, please consider citing us with the below bibtex entry: ``` @misc{zhenyuan2024bigs, title={BiGS: Bidirectional Primitives for Relightable 3D Gaussian Splatting}, author={Liu Zhenyuan and Yu Guo and Xinyuan Li and Bernd Bickel and Ran Zhang}, year={2024}, eprint={2408.13370}, url={https://arxiv.org/abs/2408.13370}, } ``` ## Acknowledgments Our synthetic data is generated using [Mitsuba](https://mitsuba.readthedocs.io/en/stable/). We thank the 3D models' creators: Keenan Crane for _Spot_; Stanford Computer Graphics Laboratory for the models _Dragon_ and _Bunny_; Wenzel Jakob for the model _Mistuba Ball_. Special thanks to Changxi Zheng for supporting the internship program at Tencent Pixel Lab.
kevinjesse/ManyRefactors4C	kevinjesse	"2022-09-25T12:59:34Z"	14,461	0	[ "license:cc-by-2.0", "size_categories:10M<n<100M", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]	null	"2022-09-25T06:28:58Z"	--- license: cc-by-2.0 ---
fixie-ai/peoples_speech	fixie-ai	"2024-08-11T17:26:01Z"	14,320	2	[ "size_categories:1M<n<10M", "format:parquet", "modality:audio", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]	null	"2024-08-05T18:35:01Z"	--- dataset_info: - config_name: clean features: - name: id dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: duration_ms dtype: int32 - name: text dtype: string - name: continuation dtype: string splits: - name: validation num_bytes: 2511523987.692 num_examples: 18622 - name: test num_bytes: 4259695510.794 num_examples: 34898 - name: train num_bytes: 401646320552.671 num_examples: 1501271 download_size: 398922548670 dataset_size: 408417540051 - config_name: dirty_sa features: - name: id dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: duration_ms dtype: int32 - name: text dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 144432442623.054 num_examples: 548014 - name: validation num_bytes: 2511524241.692 num_examples: 18622 - name: test num_bytes: 4259695588.794 num_examples: 34898 download_size: 149491764186 dataset_size: 151203662453.53998 configs: - config_name: clean data_files: - split: validation path: clean/validation-* - split: test path: clean/test-* - split: train path: data/train-* - config_name: dirty_sa data_files: - split: train path: dirty_sa/train-* - split: validation path: dirty_sa/validation-* - split: test path: dirty_sa/test-* ---

hlillemark/c4_t5_pretrain

hlillemark

"2023-05-22T16:33:38Z"

19,586

0

[ "size_categories:100M<n<1B", "format:parquet", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]

null

"2023-05-19T09:17:45Z"

--- dataset_info: features: - name: input_ids sequence: int32 - name: labels sequence: int64 splits: - name: validation num_bytes: 53400000 num_examples: 10000 - name: train num_bytes: 961505597520 num_examples: 180057228 download_size: 2939856140 dataset_size: 961558997520 --- # Dataset Card for "c4_t5_pretrain" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

CohereForAI/Global-MMLU

CohereForAI

"2025-03-20T19:47:13Z"

19,513

116

[ "language:en", "language:ar", "language:bn", "language:es", "language:fr", "language:hi", "language:ru", "language:de", "language:id", "language:it", "language:ja", "language:ko", "language:pt", "language:zh", "language:yo", "language:nl", "language:ro", "language:uk", "language:vi", "language:tr", "language:pl", "language:fa", "language:cs", "language:he", "language:el", "language:ms", "language:fil", "language:te", "language:si", "language:ne", "language:ky", "language:sv", "language:lt", "language:sr", "language:mg", "language:so", "language:ha", "language:am", "language:sn", "language:ig", "language:ny", "language:sw", "license:apache-2.0", "size_categories:100K<n<1M", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "library:argilla", "arxiv:2412.03304", "region:us", "argilla" ]

null

"2024-12-01T22:45:59Z"

--- dataset_info: - config_name: am features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 209505 num_examples: 285 - name: test num_bytes: 12085768 num_examples: 14042 download_size: 10260448 dataset_size: 12295273 - config_name: ar features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 202343 num_examples: 285 - name: test num_bytes: 11621977 num_examples: 14042 download_size: 9817049 dataset_size: 11824320 - config_name: bn features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 301875 num_examples: 285 - name: test num_bytes: 18061158 num_examples: 14042 download_size: 12524784 dataset_size: 18363033 - config_name: cs features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 149807 num_examples: 285 - name: test num_bytes: 8607308 num_examples: 14042 download_size: 8640151 dataset_size: 8757115 - config_name: de features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 162406 num_examples: 285 - name: test num_bytes: 9575360 num_examples: 14042 download_size: 9187953 dataset_size: 9737766 - config_name: el features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 254308 num_examples: 285 - name: test num_bytes: 14502137 num_examples: 14042 download_size: 12288940 dataset_size: 14756445 - config_name: en features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 146364 num_examples: 285 - name: test num_bytes: 8440632 num_examples: 14042 download_size: 7912429 dataset_size: 8586996 - config_name: es features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 160633 num_examples: 285 - name: test num_bytes: 9399724 num_examples: 14042 download_size: 8752720 dataset_size: 9560357 - config_name: fa features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 202609 num_examples: 285 - name: test num_bytes: 11611890 num_examples: 14042 download_size: 9564082 dataset_size: 11814499 - config_name: fil features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 165182 num_examples: 285 - name: test num_bytes: 9510179 num_examples: 14042 download_size: 8564879 dataset_size: 9675361 - config_name: fr features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 166173 num_examples: 285 - name: test num_bytes: 9858873 num_examples: 14042 download_size: 9202595 dataset_size: 10025046 - config_name: ha features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 147406 num_examples: 285 - name: test num_bytes: 8445707 num_examples: 14042 download_size: 7665529 dataset_size: 8593113 - config_name: he features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 178912 num_examples: 285 - name: test num_bytes: 10248592 num_examples: 14042 download_size: 8818618 dataset_size: 10427504 - config_name: hi features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 308254 num_examples: 285 - name: test num_bytes: 17970478 num_examples: 14042 download_size: 12407854 dataset_size: 18278732 - config_name: id features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 154692 num_examples: 285 - name: test num_bytes: 8886643 num_examples: 14042 download_size: 7793365 dataset_size: 9041335 - config_name: ig features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 157376 num_examples: 285 - name: test num_bytes: 9221405 num_examples: 14042 download_size: 7644102 dataset_size: 9378781 - config_name: it features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 157547 num_examples: 285 - name: test num_bytes: 9374481 num_examples: 14042 download_size: 8873034 dataset_size: 9532028 - config_name: ja features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 167646 num_examples: 285 - name: test num_bytes: 9830716 num_examples: 14042 download_size: 8826164 dataset_size: 9998362 - config_name: ko features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 160572 num_examples: 285 - name: test num_bytes: 9454859 num_examples: 14042 download_size: 8640457 dataset_size: 9615431 - config_name: ky features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 235001 num_examples: 285 - name: test num_bytes: 13483934 num_examples: 14042 download_size: 11148813 dataset_size: 13718935 - config_name: lt features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 148917 num_examples: 285 - name: test num_bytes: 8504949 num_examples: 14042 download_size: 8416467 dataset_size: 8653866 - config_name: mg features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 161992 num_examples: 285 - name: test num_bytes: 9337415 num_examples: 14042 download_size: 8011427 dataset_size: 9499407 - config_name: ms features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 152549 num_examples: 285 - name: test num_bytes: 8823844 num_examples: 14042 download_size: 7783581 dataset_size: 8976393 - config_name: ne features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 294790 num_examples: 285 - name: test num_bytes: 16972110 num_examples: 14042 download_size: 11895818 dataset_size: 17266900 - config_name: nl features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 158122 num_examples: 285 - name: test num_bytes: 9099176 num_examples: 14042 download_size: 8565959 dataset_size: 9257298 - config_name: ny features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 151315 num_examples: 285 - name: test num_bytes: 8686819 num_examples: 14042 download_size: 7822699 dataset_size: 8838134 - config_name: pl features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 157290 num_examples: 285 - name: test num_bytes: 8980730 num_examples: 14042 download_size: 8981270 dataset_size: 9138020 - config_name: pt features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 154592 num_examples: 285 - name: test num_bytes: 8983299 num_examples: 14042 download_size: 8517588 dataset_size: 9137891 - config_name: ro features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 158311 num_examples: 285 - name: test num_bytes: 9163189 num_examples: 14042 download_size: 8773232 dataset_size: 9321500 - config_name: ru features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 246059 num_examples: 285 - name: test num_bytes: 14059847 num_examples: 14042 download_size: 11904365 dataset_size: 14305906 - config_name: si features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 297843 num_examples: 285 - name: test num_bytes: 17374939 num_examples: 14042 download_size: 12790098 dataset_size: 17672782 - config_name: sn features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 147355 num_examples: 285 - name: test num_bytes: 8507368 num_examples: 14042 download_size: 7962672 dataset_size: 8654723 - config_name: so features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 156282 num_examples: 285 - name: test num_bytes: 9033243 num_examples: 14042 download_size: 8706693 dataset_size: 9189525 - config_name: sr features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 221580 num_examples: 285 - name: test num_bytes: 12695546 num_examples: 14042 download_size: 10748391 dataset_size: 12917126 - config_name: sv features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 147893 num_examples: 285 - name: test num_bytes: 8549708 num_examples: 14042 download_size: 8181997 dataset_size: 8697601 - config_name: sw features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 147069 num_examples: 285 - name: test num_bytes: 8653210 num_examples: 14042 download_size: 7932986 dataset_size: 8800279 - config_name: te features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 315724 num_examples: 285 - name: test num_bytes: 18170058 num_examples: 14042 download_size: 12631358 dataset_size: 18485782 - config_name: tr features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 153426 num_examples: 285 - name: test num_bytes: 8833244 num_examples: 14042 download_size: 8351339 dataset_size: 8986670 - config_name: uk features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 229888 num_examples: 285 - name: test num_bytes: 13233771 num_examples: 14042 download_size: 11347842 dataset_size: 13463659 - config_name: vi features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 185712 num_examples: 285 - name: test num_bytes: 10604332 num_examples: 14042 download_size: 8971266 dataset_size: 10790044 - config_name: yo features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 153810 num_examples: 285 - name: test num_bytes: 10694916 num_examples: 14042 download_size: 9303668 dataset_size: 10848726 - config_name: zh features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 127577 num_examples: 285 - name: test num_bytes: 7393764 num_examples: 14042 download_size: 7322261 dataset_size: 7521341 configs: - config_name: am data_files: - split: test path: am/test-* - split: dev path: am/dev-* - config_name: ar data_files: - split: test path: ar/test-* - split: dev path: ar/dev-* - config_name: bn data_files: - split: test path: bn/test-* - split: dev path: bn/dev-* - config_name: cs data_files: - split: test path: cs/test-* - split: dev path: cs/dev-* - config_name: de data_files: - split: test path: de/test-* - split: dev path: de/dev-* - config_name: el data_files: - split: test path: el/test-* - split: dev path: el/dev-* - config_name: en data_files: - split: test path: en/test-* - split: dev path: en/dev-* - config_name: es data_files: - split: test path: es/test-* - split: dev path: es/dev-* - config_name: fa data_files: - split: test path: fa/test-* - split: dev path: fa/dev-* - config_name: fil data_files: - split: test path: fil/test-* - split: dev path: fil/dev-* - config_name: fr data_files: - split: test path: fr/test-* - split: dev path: fr/dev-* - config_name: ha data_files: - split: test path: ha/test-* - split: dev path: ha/dev-* - config_name: he data_files: - split: test path: he/test-* - split: dev path: he/dev-* - config_name: hi data_files: - split: test path: hi/test-* - split: dev path: hi/dev-* - config_name: id data_files: - split: test path: id/test-* - split: dev path: id/dev-* - config_name: ig data_files: - split: test path: ig/test-* - split: dev path: ig/dev-* - config_name: it data_files: - split: test path: it/test-* - split: dev path: it/dev-* - config_name: ja data_files: - split: test path: ja/test-* - split: dev path: ja/dev-* - config_name: ko data_files: - split: test path: ko/test-* - split: dev path: ko/dev-* - config_name: ky data_files: - split: test path: ky/test-* - split: dev path: ky/dev-* - config_name: lt data_files: - split: test path: lt/test-* - split: dev path: lt/dev-* - config_name: mg data_files: - split: test path: mg/test-* - split: dev path: mg/dev-* - config_name: ms data_files: - split: test path: ms/test-* - split: dev path: ms/dev-* - config_name: ne data_files: - split: test path: ne/test-* - split: dev path: ne/dev-* - config_name: nl data_files: - split: test path: nl/test-* - split: dev path: nl/dev-* - config_name: ny data_files: - split: test path: ny/test-* - split: dev path: ny/dev-* - config_name: pl data_files: - split: test path: pl/test-* - split: dev path: pl/dev-* - config_name: pt data_files: - split: test path: pt/test-* - split: dev path: pt/dev-* - config_name: ro data_files: - split: test path: ro/test-* - split: dev path: ro/dev-* - config_name: ru data_files: - split: test path: ru/test-* - split: dev path: ru/dev-* - config_name: si data_files: - split: test path: si/test-* - split: dev path: si/dev-* - config_name: sn data_files: - split: test path: sn/test-* - split: dev path: sn/dev-* - config_name: so data_files: - split: test path: so/test-* - split: dev path: so/dev-* - config_name: sr data_files: - split: test path: sr/test-* - split: dev path: sr/dev-* - config_name: sv data_files: - split: test path: sv/test-* - split: dev path: sv/dev-* - config_name: sw data_files: - split: test path: sw/test-* - split: dev path: sw/dev-* - config_name: te data_files: - split: test path: te/test-* - split: dev path: te/dev-* - config_name: tr data_files: - split: test path: tr/test-* - split: dev path: tr/dev-* - config_name: uk data_files: - split: test path: uk/test-* - split: dev path: uk/dev-* - config_name: vi data_files: - split: test path: vi/test-* - split: dev path: vi/dev-* - config_name: yo data_files: - split: test path: yo/test-* - split: dev path: yo/dev-* - config_name: zh data_files: - split: test path: zh/test-* - split: dev path: zh/dev-* tags: - argilla license: apache-2.0 language: - en - ar - bn - es - fr - hi - ru - de - id - it - ja - ko - pt - zh - yo - nl - ro - uk - vi - tr - pl - fa - cs - he - el - ms - fil - te - si - ne - ky - sv - lt - sr - mg - so - ha - am - sn - ig - ny - sw --- ![GlobalMMLU Header](https://huggingface.co/datasets/CohereForAI/Global-MMLU/resolve/main/global_mmlu.jpg) # Dataset Summary [Global-MMLU](https://arxiv.org/abs/2412.03304) 🌍 is a multilingual evaluation set spanning 42 languages, including English. This dataset combines machine translations for [MMLU](https://huggingface.co/datasets/cais/mmlu) questions along with professional translations and crowd-sourced post-edits. It also includes cultural sensitivity annotations for a subset of the questions (2850 questions per language) and classifies them as *Culturally Sensitive* (CS) 🗽 or *Culturally Agnostic* (CA) ⚖️. These annotations were collected as part of an open science initiative led by Cohere For AI in collaboration with many external collaborators from both industry and academia. - **Curated by:** Professional annotators and contributors of [Cohere For AI Community](https://cohere.com/research). - **Language(s):** 42 languages. - **License:** [Apache 2.0](https://opensource.org/license/apache-2-0) **Note:** We also provide a "lite" version of Global MMLU called ["Global-MMLU-Lite"](https://huggingface.co/datasets/CohereForAI/Global-MMLU-Lite). This datatset is more balanced containing 200 samples each for CA and CS subsets for each language. And provides coverage for 15 languages with human translations. ### **Global-MMLU Dataset Family:** | Name | Explanation | |------|--------------| | [Global-MMLU](https://huggingface.co/datasets/CohereForAI/Global-MMLU) | Full Global-MMLU set with translations for all 14K samples including CS and CA subsets| | [Global-MMLU-Lite](https://huggingface.co/datasets/CohereForAI/Global-MMLU-Lite) | Lite version of Global-MMLU with human translated samples in 15 languages and containing 200 samples each for CS and CA subsets per language.| ## Load with Datasets To load this dataset with `datasets`, you'll first need to install it using `pip install datasets` and then use the following code: ```python from datasets import load_dataset # load HF dataset global_mmlu = load_dataset("CohereForAI/Global-MMLU", 'en') # can also be used as pandas dataframe global_mmlu.set_format("pandas") global_mmlu_test = global_mmlu['test'][:] global_mmlu_dev = global_mmlu['dev'][:] ``` <details> <summary> additional details </summary> The columns corresponding to annotations collected from our cultural bias study (i.e. 'required_knowledge', 'time_sensitive', 'reference', 'culture', 'region', 'country') contain a list of values representing annotations from different annotators. However, to avoid conversion issues to HF dataset, these columns are provided as string in the final dataset. You can convert these columns back to list of values for easier manipulation as follows: ```python import ast # convert string values to list global_mmlu_df['required_knowledge'] = global_mmlu_df['required_knowledge'].apply(lamda x: ast.literal_eval(x)) ``` </details> <br> ## Data Fields The data fields are the same among all splits. Brief description of each field is provided below. <details> <summary> data field description </summary> - `sample_id`: A unique identifier for the question. - `subject`: The main topic the question falls under. - `subject_category`: The high-level category the subject falls under i.e. STEM/Humanities/Social Sciences/Medical/Business/Other. - `question`: translated question from MMLU - `option_a`: one of the possible option choices - `option_b`: one of the possible option choices - `option_c`: one of the possible option choices - `option_d`: one of the possible option choices - `answer': the correct answer (A/B/C/D) - `required_knowledge`: annotator votes for knowledge needed to answer the question correctly. Possible values include: "cultural", "regional", "dialect" or "none" - `time_sensitive`: annotator votes indicating if the question's answer is time-dependent. Possible values include: Yes/No - `reference`: annotations for which part of the question contains cultural/regional/dialect references. The different items in the list are annotations from different annotators. - `culture`: annotations for which culture does the question belong to. The different items in the list correspond to annotations from different annotators. - `region`: Geographic region the question is relevant to. Each item in the list correspond to annotations from different annotators. - `country`: Specific country the question pertains to. Each item in the list correspond to annotations from different annotators. - `cultural_sensitivity_label`: Label to indicate if question is culturally sensitive (CS) or culturally agnostic (CA) based on annotator votes. - `is_annotated`: True/False flag to indicate if sample contains any annotations from our cultural bias study. </details> <br> ## Data Splits The following are the splits of the data: | Split | No. of instances | Language Coverage | |-------|------------------|-------------------| | test | 589,764 | 42 | | dev | 11,970 | 42 | ## Data Instances An example from `test` set looks as follows: ```json {'sample_id': 'world_religions/test/170' 'subject': 'world_religions', 'subject_category': 'Humanities', 'question': ' The numen of Augustus referred to which of the following characteristics?', 'option_a': 'Divine power', 'option_b': 'Sexual virility', 'option_c': 'Military acumen', 'option_d': 'Philosophical intellect', 'answer': 'A', 'required_knowledge': "['none', 'cultural', 'cultural', 'cultural']", 'time_sensitive': "['No', 'No', 'No', 'No']", 'reference': "['-', '-', {'end': 22, 'label': 'Cultural', 'score': None, 'start': 5}, {'end': 22, 'label': 'Cultural', 'score': None, 'start': 5}]", 'culture': "['Western Culture', 'Western Culture', 'Western Culture']", 'region': "['North America', 'Europe']", 'country': "['Italy']", 'cultural_sensitivity_label': 'CS', 'is_annotated': True, } ``` ## Statistics ### Annotation Types The following is the breakdown of CS🗽, CA⚖️ and MA📝 samples in the final dataset. | Type of Annotation | Instances per language | No. of languages | Total instances |--------------------|------------------------|------------------|----------------| | Culturally Sensitive 🗽 | 792 | 42 | 33,264 | | Culturally Agnostic ⚖️ | 2058 |42 | 86,436 | | MMLU Annotated 📝| 2850 |42 | 119,700 | ### Languages The dataset covers 42 languages: 20 high-resource, 9 mid-resource, and 13 low-resource languages. The following is details about the languages included in the dataset. <details> <summary> Languages Info </summary> | ISO Code | Language | Resources | |----------|----------|-----------| | `am` | Amharic | Low | | `ar` | Arabic (Standard)| High | | `bn` | Bengali | Mid | | `de` | German | High | | `el` | Greek | Mid | | `en` | English | High | | `fil` | Filipino | Mid | | `fr` | French | High | | `ha` | Hausa | Low | | `he` | Hebrew | Mid | | `hi` | Hindi | High | | `ig` | Igbo | Low | | `id` | Indonesian | Mid | | `it` | Italian | High | | `ja` | Japanese | High | | `ky` | Kyrgyz | Low | | `ko` | Korean | Mid | | `lt` | Lithuanian | Mid | | `mg` | Malagasy | Low | | `ms` | Malay | Mid | | `ne` | Nepali | Low | | `nl` | Dutch | High | | `ny` | Chichewa | Low | | `fa` | Persian | High | | `pl` | Polish | High | | `pt` | Portuguese | High | | `ru` | Russian | High | | `si` | Sinhala | Low | | `sn` | Shona | Low | | `so` | Somali | Low | | `es` | Spanish | High | | `sr` | Serbian | High | | `sw` | Swahili | Low | | `sv` | Swedish | High | | `te` | Telugu | Low | | `tr` | Turkish | High | | `uk` | Ukrainian | Mid | | `vi` | Vietnamese | High | | `yo` | Yorùbá | Low | | `zh` | Chinese (Simplified) | High | </details> <br> # Known Limitations A brief overview of limitations of this dataset is provided below. <details> <summary> show limitations </summary> - **Language and dialect coverage:** Global-MMLU focusses on 42 languages. However, this is still only a tiny fraction of the world’s linguistic diversity. Future work is needed to continue to improve evaluations beyond these 42 languages and take into account how technology serves different dialects. - **Uneven distribution of contributions:** The dataset contains translation post-edits from community volunteers, with a 'long tail' of volunteers making only one or two contributions. Similarly, there is a huge gap between languages with the highest number of contributions and ones with the lowest number of contributions. - **Toxic or offensive speech:** Our annotation process did not focus on flagging for toxic,harmful, or offensive speech, so it is possible that Global-MMLU contains some data that could be considered harmful. We believe this is of relatively low risk because of the nature of the original MMLU and the focus on examination material. - **Region Category Assignment:** For the annotation of geographically sensitive questions, we classified regions into six geographic regions (Africa, Asia, Europe, North America, Oceania,and South America). However, based upon discussions we would going forward recommend switching to the taxonomy proposed by the World Bank which is more granular and includes separate designations for Central America and Sub-Saharan Africa. - **Identifying cultural sensitivity does not guarantee cultural inclusion:** While Global-MMLU highlights important limitations in current datasets by identifying gaps in non-Western cultural representation. Future work must prioritize the integration of diverse culturally grounded knowledge to achieve true inclusivity and fairness in multilingual AI evaluation. </details> <br> # Additional Information ## Provenance - **Methods Used:** Professional annotations as well as crowd-sourced through volunteer annotations. - **Methodology Details:** We collected cultural bias annotations as well as post-edits of translations for different mmlu questions. - [Cultural Sensitivity Annotation Platform](https://huggingface.co/spaces/CohereForAI/MMLU-evaluation) - [Translation Quality Annotation Platform](https://huggingface.co/spaces/CohereForAI/review-mmlu-translations) - Dates of Collection: May 2024 - Aug 2024 ## Dataset Version and Maintenance - **Maintenance Status:** Actively Maintained - **Version Details:** - *Current version:* 1.0 - *Last Update:* 12/2024 - *First Release:* 12/2024 ## Authorship - **Publishing Organization:** [Cohere For AI](https://cohere.com/research) - **Industry Type:** Not-for-profit - Tech ## Licensing Information This dataset can be used for any purpose, under the terms of the [Apache 2.0](https://opensource.org/license/apache-2-0) License. ## Additional Details For any additional details, please check our paper, [Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation](https://arxiv.org/abs/2412.03304). ## Citation Information ```bibtex @misc{singh2024globalmmluunderstandingaddressing, title={Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation}, author={Shivalika Singh and Angelika Romanou and Clémentine Fourrier and David I. Adelani and Jian Gang Ngui and Daniel Vila-Suero and Peerat Limkonchotiwat and Kelly Marchisio and Wei Qi Leong and Yosephine Susanto and Raymond Ng and Shayne Longpre and Wei-Yin Ko and Madeline Smith and Antoine Bosselut and Alice Oh and Andre F. T. Martins and Leshem Choshen and Daphne Ippolito and Enzo Ferrante and Marzieh Fadaee and Beyza Ermis and Sara Hooker}, year={2024}, eprint={2412.03304}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2412.03304}, } ```

gvecchio/MatSynth

gvecchio

"2024-04-16T13:44:10Z"

19,433

47

[ "task_categories:image-to-image", "task_categories:unconditional-image-generation", "task_categories:image-classification", "task_categories:text-to-image", "language:en", "size_categories:1K<n<10K", "arxiv:2401.06056", "region:us", "materials", "pbr", "4d", "graphics", "rendering", "svbrdf", "synthetic" ]

[ "image-to-image", "unconditional-image-generation", "image-classification", "text-to-image" ]

"2023-11-29T11:24:57Z"

--- language: - en size_categories: - 1K<n<10K task_categories: - image-to-image - unconditional-image-generation - image-classification - text-to-image pretty_name: MatSynth dataset_info: features: - name: name dtype: string - name: category dtype: class_label: names: '0': ceramic '1': concrete '2': fabric '3': ground '4': leather '5': marble '6': metal '7': misc '8': plaster '9': plastic '10': stone '11': terracotta '12': wood - name: metadata struct: - name: authors sequence: string - name: category dtype: string - name: description dtype: string - name: height_factor dtype: float32 - name: height_mean dtype: float32 - name: license dtype: string - name: link dtype: string - name: maps sequence: string - name: method dtype: string - name: name dtype: string - name: physical_size dtype: float32 - name: source dtype: string - name: stationary dtype: bool - name: tags sequence: string - name: version_date dtype: string - name: basecolor dtype: image - name: diffuse dtype: image - name: displacement dtype: image - name: height dtype: image - name: metallic dtype: image - name: normal dtype: image - name: opacity dtype: image - name: roughness dtype: image - name: specular dtype: image - name: blend_mask dtype: image splits: - name: test num_bytes: 7443356066.0 num_examples: 89 - name: train num_bytes: 430581667965.1 num_examples: 5700 download_size: 440284274332 dataset_size: 438025024031.1 configs: - config_name: default data_files: - split: test path: data/test-* - split: train path: data/train-* tags: - materials - pbr - 4d - graphics - rendering - svbrdf - synthetic viewer: false --- # MatSynth MatSynth is a Physically Based Rendering (PBR) materials dataset designed for modern AI applications. This dataset consists of over 4,000 ultra-high resolution, offering unparalleled scale, diversity, and detail. Meticulously collected and curated, MatSynth is poised to drive innovation in material acquisition and generation applications, providing a rich resource for researchers, developers, and enthusiasts in computer graphics and related fields. For further information, refer to our paper: ["MatSynth: A Modern PBR Materials Dataset"](https://arxiv.org/abs/2401.06056) available on arXiv. <center> <img src="https://gvecchio.com/matsynth/static/images/teaser.png" style="border-radius:10px"> </center> ## 🔍 Dataset Details ### Dataset Description MatSynth is a new large-scale dataset comprising over 4,000 ultra-high resolution Physically Based Rendering (PBR) materials, all released under permissive licensing. All materials in the dataset are represented by a common set of maps (*Basecolor*, *Diffuse*, *Normal*, *Height*, *Roughness*, *Metallic*, *Specular* and, when useful, *Opacity*), modelling both the reflectance and mesostructure of the material. Each material in the dataset comes with rich metadata, including information on its origin, licensing details, category, tags, creation method, and, when available, descriptions and physical size. This comprehensive metadata facilitates precise material selection and usage, catering to the specific needs of users. <center> <img src="https://gvecchio.com/matsynth/static/images/data.png" style="border-radius:10px"> </center> ## 📂 Dataset Structure The MatSynth dataset is divided into two splits: the test split, containing 89 materials, and the train split, consisting of 3,980 materials. ## 🔨 Dataset Creation The MatSynth dataset is designed to support modern, learning-based techniques for a variety of material-related tasks including, but not limited to, material acquisition, material generation and synthetic data generation e.g. for retrieval or segmentation. ### 🗃️ Source Data The MatSynth dataset is the result of an extensively collection of data from multiple online sources operating under the CC0 and CC-BY licensing framework. This collection strategy allows to capture a broad spectrum of materials, from commonly used ones to more niche or specialized variants while guaranteeing that the data can be used for a variety of usecases. Materials under CC0 license were collected from [AmbientCG](https://ambientcg.com/), [CGBookCase](https://www.cgbookcase.com/), [PolyHeaven](https://polyhaven.com/), [ShateTexture](https://www.sharetextures.com/), and [TextureCan](https://www.texturecan.com/). The dataset also includes limited set of materials from the artist [Julio Sillet](https://juliosillet.gumroad.com/), distributed under CC-BY license. We collected over 6000 materials which we meticulously filter to keep only tileable, 4K materials. This high resolution allows us to extract many different crops from each sample at different scale for augmentation. Additionally, we discard blurry or low-quality materials (by visual inspection). The resulting dataset consists of 3736 unique materials which we augment by blending semantically compatible materials (e.g.: snow over ground). In total, our dataset contains 4069 unique 4K materials. ### ✒️ Annotations The dataset is composed of material maps (Basecolor, Diffuse, Normal, Height, Roughness, Metallic, Specular and, when useful, opacity) and associated renderings under varying environmental illuminations, and multi-scale crops. We adopt the OpenGL standard for the Normal map (Y-axis pointing upward). The Height map is given in a 16-bit single channel format for higher precision. In addition to these maps, the dataset includes other annotations providing context to each material: the capture method (photogrammetry, procedural generation, or approximation); list of descriptive tags; source name (website); source link; licensing and a timestamps for eventual future versioning. For a subset of materials, when the information is available, we also provide the author name (387), text description (572) and a physical size, presented as the length of the edge in centimeters (358). ## 🧑‍💻 Usage MatSynth is accessible through the datasets python library. Following a usage example: ```python import torchvision.transforms.functional as TF from datasets import load_dataset from torch.utils.data import DataLoader # image processing function def process_img(x): x = TF.resize(x, (1024, 1024)) x = TF.to_tensor(x) return x # item processing function def process_batch(examples): examples["basecolor"] = [process_img(x) for x in examples["basecolor"]] return examples # load the dataset in streaming mode ds = load_dataset( "gvecchio/MatSynth", streaming = True, ) # remove unwanted columns ds = ds.remove_columns(["diffuse", "specular", "displacement", "opacity", "blend_mask"]) # or keep only specified columns ds = ds.select_columns(["metadata", "basecolor"]) # shuffle data ds = ds.shuffle(buffer_size=100) # filter data matching a specific criteria, e.g.: only CC0 materials ds = ds.filter(lambda x: x["metadata"]["license"] == "CC0") # filter out data from Deschaintre et al. 2018 ds = ds.filter(lambda x: x["metadata"]["source"] != "deschaintre_2020") # Set up processing ds = ds.map(process_batch, batched=True, batch_size=8) # set format for usage in torch ds = ds.with_format("torch") # iterate over the dataset for x in ds: print(x) ``` ⚠️ **Note**: Streaming can be slow. We strongly suggest to cache data locally. ## 📜 Citation ``` @inproceedings{vecchio2023matsynth, title={MatSynth: A Modern PBR Materials Dataset}, author={Vecchio, Giuseppe and Deschaintre, Valentin}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, year={2024} } ``` If you use the data from Deschaintre et al. contained in this dataset, please also cite: ``` @article{deschaintre2018single, title={Single-image svbrdf capture with a rendering-aware deep network}, author={Deschaintre, Valentin and Aittala, Miika and Durand, Fredo and Drettakis, George and Bousseau, Adrien}, journal={ACM Transactions on Graphics (ToG)}, volume={37}, number={4}, pages={1--15}, year={2018}, publisher={ACM New York, NY, USA} } ```

jiachenlei/imagenet

jiachenlei

"2024-11-28T02:31:55Z"

19,367

1

[ "region:us" ]

null

"2024-11-27T02:39:50Z"

--- configs: - config_name: imagenet data_files: - split: train path: - "imagenet/train" - split: val path: "imagenet/val" - config_name: imagenet256 data_files: - split: train path: - "imagenet256/train" - split: val path: "imagenet256/val" - config_name: imagenet_features data_files: - split: train path: - "imagenet_features/train" - split: val path: "imagenet_features/val" ---

alexandrainst/ftspeech

alexandrainst

"2024-09-04T15:01:21Z"

19,357

3

[ "task_categories:automatic-speech-recognition", "language:da", "license:other", "size_categories:1M<n<10M", "format:parquet", "modality:audio", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "arxiv:2005.12368", "region:us" ]

[ "automatic-speech-recognition" ]

"2023-05-11T13:08:57Z"

--- dataset_info: features: - name: utterance_id dtype: string - name: speaker_gender dtype: string - name: sentence dtype: string - name: speaker_id dtype: string - name: audio dtype: audio: sampling_rate: 16000 splits: - name: train num_bytes: 209434570129.268 num_examples: 995677 - name: dev_balanced num_bytes: 579692770.829 num_examples: 2601 - name: dev_other num_bytes: 1725502342.095 num_examples: 7595 - name: test_balanced num_bytes: 1158740779.222 num_examples: 5534 - name: test_other num_bytes: 1254987645.527 num_examples: 5837 download_size: 101776974871 dataset_size: 214153493666.941 task_categories: - automatic-speech-recognition language: - da pretty_name: FT Speech size_categories: - 100K<n<1M license: other --- # Dataset Card for FT Speech ## Dataset Description - **Repository:** <https://ftspeech.github.io/> - **Point of Contact:** [Dan Saattrup Nielsen](mailto:[email protected]) - **Size of downloaded dataset files:** 101.78 GB - **Size of the generated dataset:** 214.15 GB - **Total amount of disk used:** 315.93 GB ### Dataset Summary This dataset is an upload of the [FT Speech dataset](https://ftspeech.github.io/). The training, validation and test splits are the original ones. ### Supported Tasks and Leaderboards Training automatic speech recognition is the intended task for this dataset. No leaderboard is active at this point. ### Languages The dataset is available in Danish (`da`). ## Dataset Structure ### Data Instances - **Size of downloaded dataset files:** 101.78 GB - **Size of the generated dataset:** 214.15 GB - **Total amount of disk used:** 315.93 GB An example from the dataset looks as follows. ``` { 'utterance_id': 'S001_20151_M012_P00034-2', 'speaker_gender': 'F', 'sentence': 'alle de fem tekniske justeringer der er en del af lovforslaget', 'speaker_id': 'S001', 'audio': { 'path': 'S001_20151_M012_P00034-2.wav', 'array': array([-3.75366211e-03, -5.27954102e-03, -3.87573242e-03, ..., 9.15527344e-05, -1.52587891e-04, 5.79833984e-04]), 'sampling_rate': 16000 } } ``` ### Data Fields The data fields are the same among all splits. - `utterance_id`: a `string` feature. - `speaker_gender`: a `string` feature. - `sentence`: a `string` feature. - `speaker_id`: a `string` feature. - `audio`: an `Audio` feature. ### Dataset Statistics There are 995,677 samples in the training split, 2,601 in the dev_balanced split, 7,595 in the dev_other split, 5,534 in the test_balanced and 5,837 in the test_other split. #### Speakers There are 374 unique speakers in the training dataset, 20 unique speakers in the validation dataset and 40 unique speakers in the test dataset. None of the dataset splits share any speakers. #### Gender Distribution ![ftspeech-gender-distribution.png](https://cdn-uploads.huggingface.co/production/uploads/60d368a613f774189902f555/0h_L7-riNfQbKFdYWgy01.png) #### Transcription Length Distribution ![ftspeech-length-distribution.png](https://cdn-uploads.huggingface.co/production/uploads/60d368a613f774189902f555/z1MqsvACrY_8XNXAx0UcD.png) ## Dataset Creation ### Curation Rationale There are not many large-scale ASR datasets in Danish. ### Source Data The data constitutes public recordings of sessions from the Danish Parliament, along with manual transcriptions. ## Additional Information ### Dataset Curators Andreas Kirkedal, Marija Stepanović and Barbara Plank curated the dataset as part of their FT Speech paper (see citation below). [Dan Saattrup Nielsen](https://saattrupdan.github.io/) from the [The Alexandra Institute](https://alexandra.dk/) reorganised the dataset and uploaded it to the Hugging Face Hub. ### Licensing Information The dataset is licensed under [this custom license](https://www.ft.dk/da/aktuelt/tv-fra-folketinget/deling-og-rettigheder). ### Citation ``` @inproceedings{ftspeech, author = {Kirkedal, Andreas and Stepanović, Marija and Plank, Barbara}, title = {{FT Speech: Danish Parliament Speech Corpus}}, booktitle = {Proc. Interspeech 2020}, year = {2020}, url = {arxiv.org/abs/2005.12368} } ```

EleutherAI/race

EleutherAI

"2023-07-03T21:27:18Z"

19,340

6

[ "task_categories:multiple-choice", "task_ids:multiple-choice-qa", "annotations_creators:expert-generated", "language_creators:found", "multilinguality:monolingual", "source_datasets:original", "language:en", "license:other", "size_categories:1K<n<10K", "modality:text", "library:datasets", "library:mlcroissant", "arxiv:1704.04683", "region:us" ]

[ "multiple-choice" ]

"2023-07-03T13:20:38Z"

--- annotations_creators: - expert-generated language: - en language_creators: - found license: - other multilinguality: - monolingual pretty_name: RACE size_categories: - 10K<n<100K source_datasets: - original task_categories: - multiple-choice task_ids: - multiple-choice-qa paperswithcode_id: race dataset_info: --- # "race" Grouped by Article This is a modified version of https://huggingface.co/datasets/race that returns documents grouped by article context instead of by question. **Note:** This dataset currently only contains that test set of the ```high``` subset of the data. The original readme is contained below. # Dataset Card for "race" ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Homepage:** [http://www.cs.cmu.edu/~glai1/data/race/](http://www.cs.cmu.edu/~glai1/data/race/) - **Repository:** https://github.com/qizhex/RACE_AR_baselines - **Paper:** [RACE: Large-scale ReAding Comprehension Dataset From Examinations](https://arxiv.org/abs/1704.04683) - **Point of Contact:** [Guokun Lai](mailto:[email protected]), [Qizhe Xie](mailto:[email protected]) - **Size of downloaded dataset files:** 76.33 MB - **Size of the generated dataset:** 349.46 MB - **Total amount of disk used:** 425.80 MB ### Dataset Summary RACE is a large-scale reading comprehension dataset with more than 28,000 passages and nearly 100,000 questions. The dataset is collected from English examinations in China, which are designed for middle school and high school students. The dataset can be served as the training and test sets for machine comprehension. ### Supported Tasks and Leaderboards [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Languages [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Dataset Structure ### Data Instances #### all - **Size of downloaded dataset files:** 25.44 MB - **Size of the generated dataset:** 174.73 MB - **Total amount of disk used:** 200.17 MB An example of 'train' looks as follows. ``` This example was too long and was cropped: { "answer": "A", "article": "\"Schoolgirls have been wearing such short skirts at Paget High School in Branston that they've been ordered to wear trousers ins...", "example_id": "high132.txt", "options": ["short skirts give people the impression of sexualisation", "short skirts are too expensive for parents to afford", "the headmaster doesn't like girls wearing short skirts", "the girls wearing short skirts will be at the risk of being laughed at"], "question": "The girls at Paget High School are not allowed to wear skirts in that _ ." } ``` #### high - **Size of downloaded dataset files:** 25.44 MB - **Size of the generated dataset:** 140.12 MB - **Total amount of disk used:** 165.56 MB An example of 'train' looks as follows. ``` This example was too long and was cropped: { "answer": "A", "article": "\"Schoolgirls have been wearing such short skirts at Paget High School in Branston that they've been ordered to wear trousers ins...", "example_id": "high132.txt", "options": ["short skirts give people the impression of sexualisation", "short skirts are too expensive for parents to afford", "the headmaster doesn't like girls wearing short skirts", "the girls wearing short skirts will be at the risk of being laughed at"], "question": "The girls at Paget High School are not allowed to wear skirts in that _ ." } ``` #### middle - **Size of downloaded dataset files:** 25.44 MB - **Size of the generated dataset:** 34.61 MB - **Total amount of disk used:** 60.05 MB An example of 'train' looks as follows. ``` This example was too long and was cropped: { "answer": "B", "article": "\"There is not enough oil in the world now. As time goes by, it becomes less and less, so what are we going to do when it runs ou...", "example_id": "middle3.txt", "options": ["There is more petroleum than we can use now.", "Trees are needed for some other things besides making gas.", "We got electricity from ocean tides in the old days.", "Gas wasn't used to run cars in the Second World War."], "question": "According to the passage, which of the following statements is TRUE?" } ``` ### Data Fields The data fields are the same among all splits. #### all - `example_id`: a `string` feature. - `article`: a `string` feature. - `answer`: a `string` feature. - `question`: a `string` feature. - `options`: a `list` of `string` features. #### high - `example_id`: a `string` feature. - `article`: a `string` feature. - `answer`: a `string` feature. - `question`: a `string` feature. - `options`: a `list` of `string` features. #### middle - `example_id`: a `string` feature. - `article`: a `string` feature. - `answer`: a `string` feature. - `question`: a `string` feature. - `options`: a `list` of `string` features. ### Data Splits | name |train|validation|test| |------|----:|---------:|---:| |all |87866| 4887|4934| |high |62445| 3451|3498| |middle|25421| 1436|1436| ## Dataset Creation ### Curation Rationale [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Source Data #### Initial Data Collection and Normalization [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the source language producers? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Annotations #### Annotation process [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the annotators? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Personal and Sensitive Information [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Discussion of Biases [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Other Known Limitations [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Additional Information ### Dataset Curators [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Licensing Information http://www.cs.cmu.edu/~glai1/data/race/ 1. RACE dataset is available for non-commercial research purpose only. 2. All passages are obtained from the Internet which is not property of Carnegie Mellon University. We are not responsible for the content nor the meaning of these passages. 3. You agree not to reproduce, duplicate, copy, sell, trade, resell or exploit for any commercial purpose, any portion of the contexts and any portion of derived data. 4. We reserve the right to terminate your access to the RACE dataset at any time. ### Citation Information ``` @inproceedings{lai-etal-2017-race, title = "{RACE}: Large-scale {R}e{A}ding Comprehension Dataset From Examinations", author = "Lai, Guokun and Xie, Qizhe and Liu, Hanxiao and Yang, Yiming and Hovy, Eduard", booktitle = "Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing", month = sep, year = "2017", address = "Copenhagen, Denmark", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/D17-1082", doi = "10.18653/v1/D17-1082", pages = "785--794", } ``` ### Contributions Thanks to [@abarbosa94](https://github.com/abarbosa94), [@patrickvonplaten](https://github.com/patrickvonplaten), [@lewtun](https://github.com/lewtun), [@thomwolf](https://github.com/thomwolf), [@mariamabarham](https://github.com/mariamabarham) for adding this dataset.

agents-course/certificates

agents-course

"2025-04-12T00:52:35Z"

19,322

41

[ "license:apache-2.0", "region:us" ]

null

"2025-02-06T08:17:59Z"

--- license: apache-2.0 ---

Graphcore/wikipedia-bert-128

Graphcore

"2022-09-07T14:42:32Z"

19,254

1

[ "language:en", "license:cc-by-sa-3.0", "size_categories:10M<n<100M", "format:parquet", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]

null

"2022-03-02T23:29:22Z"

--- language: - en license: - cc-by-sa-3.0 ---

lmms-lab/Video-MME

lmms-lab

"2024-07-04T08:14:20Z"

19,248

39

[ "size_categories:1K<n<10K", "format:parquet", "modality:text", "modality:video", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]

null

"2024-06-07T12:06:37Z"

--- dataset_info: config_name: videomme features: - name: video_id dtype: string - name: duration dtype: string - name: domain dtype: string - name: sub_category dtype: string - name: url dtype: string - name: videoID dtype: string - name: question_id dtype: string - name: task_type dtype: string - name: question dtype: string - name: options sequence: string - name: answer dtype: string splits: - name: test num_bytes: 1003241.0 num_examples: 2700 download_size: 405167 dataset_size: 1003241.0 configs: - config_name: videomme data_files: - split: test path: videomme/test-* ---

neashton/ahmedml

neashton

"2025-04-08T13:29:43Z"

19,223

2

[ "license:cc-by-sa-4.0", "arxiv:2407.20801", "doi:10.57967/hf/5002", "region:us" ]

null

"2025-02-10T11:19:24Z"

--- license: cc-by-sa-4.0 --- AhmedML: High-Fidelity Computational Fluid Dynamics dataset for incompressible, low-speed bluff body aerodynamics ------- Contact: ---------- Neil Ashton (NVIDIA) - [email protected] website: ---------- https://caemldatasets.org Summary: ------- This dataset contains 500 different geometric variations of the Ahmed Car Body - a simplified car-like shape that exhibits many of the flow topologies that are present on bluff bodies such as road vehicles. The dataset contains a wide range of geometries that exhibit fundamental flow physics such as geometry and pressure-induced flow separation of flows as well as 3D vortical structures. Each variation of the Ahmed car body were run using a time-accurate hybrid Reynolds-Averaged Navier-Stokes (RANS) - Large-Eddy Simulation (LES) turbulence modelling approach using the open-source CFD code OpenFOAM. The dataset contains both surface boundary, 3D volume, geometry STL and forces/moments in open-source formats (.vtu,.vtp). CFD Solver: ---------- All cases were run using the open-source finite-volume code OpenFOAM v2212. Each case was run transiently for approximately 80 convective time units (CTU) on meshes of approximately 20M cells. Please see the paper for full details on the code and validation: How to cite this dataset: ---------------- In order to cite the use of this dataset please cite the paper below which contains full details on the dataset. It can be found here: https://arxiv.org/abs/2407.20801 @article{ashton2024ahmed, title = {{AhmedML: High-Fidelity Computational Fluid Dynamics dataset for incompressible, low-speed bluff body aerodynamics}}, year = {2024}, journal = {arxiv.org}, author = {Ashton, Neil and Maddix, Danielle and Gundry, Samuel and Shabestari, Parisa} } Files: ------- Each folder (e.g run_1,run_2...run_"i" etc) corresponds to a different geometry that contains the following files where "i" is the run number: * ahmed_i.stl : geometry stl (~5mb): * geo_parameters_1.csv (missing run 500): parameters that define the geometry * boundary_i.vtp : Boundary VTP (~500mb) * volume_i.vtu : Volume field VTU (~5GB) * force_mom_i.csv : forces (Cd,Cl) time-averaged with constant reference area * force_mom_varref_i.csv : forces (Cd,Cl) time-averaged with varying reference area * slices : folder containing .vtp slices in x,y,z that contain flow-field variables * images : (folder) that contains images of the following variables (CpT, UxMean) for slices of the domain in the X,Y & Z locations. In addition we provide: * force_mom_all.csv : run, cd,cl for all runs in a single file * force_mom_varref_all.csv : run, cd,cl for all runs in a single file with varying reference area * geo_parameters_all.csv : all the geometry parameters for each run inside a single file * ahmedml.slvs : SolveSpace input file to create the parametric geometries * stl : folder containing stl files that were used as inputs to the OpenFOAM process * openfoam-casesetup.tgz : complete OpenFOAM setup that can be used to extend or reproduce the dataset * validation : folder containing full outputs from all four mesh levels that were used to validate the methodology Downloads -------------- The dataset is now available on HuggingFace. Below are some examples of how to download all or selected parts of the dataset. Please refer to the HuggingFace documentation for other ways to accessing the dataset and building workflows. Example 1: Download all files (~2TB) -------- Please note you'll need to have git lfs installed first, then you can run the following command: ``` git clone [email protected]:datasets/neashton/ahmedml ``` Example 2: only download select files (STL,images & force and moments): --------- Create the following bash script that could be adapted to loop through only select runs or to change to download different files e.g boundary/volume. ``` #!/bin/bash # Set the paths HF_OWNER="neashton" HF_PREFIX="ahmedml" # Set the local directory to download the files LOCAL_DIR="./ahmed_data" # Create the local directory if it doesn't exist mkdir -p "$LOCAL_DIR" # Loop through the run folders from 1 to 500 for i in $(seq 1 500); do RUN_DIR="run_$i" RUN_LOCAL_DIR="$LOCAL_DIR/$RUN_DIR" # Create the run directory if it doesn't exist mkdir -p "$RUN_LOCAL_DIR" # Download the ahmed_i.stl file wget "https://huggingface.co/datasets/${HF_OWNER}/${HF_PREFIX}/resolve/main/$RUN_DIR/ahmed_$i.stl" -O "$RUN_LOCAL_DIR/ahmed_$i.stl" # Download the force_mom_i.csv file wget "https://huggingface.co/datasets/${HF_OWNER}/${HF_PREFIX}/resolve/main/$RUN_DIR/force_mom_$i.csv" -O "$RUN_LOCAL_DIR/force_mom_$i.csv" done ``` Acknowledgements ----------- * OpenFOAM solver and workflow development by Neil Ashton (Amazon Web Services, now NVIDIA) * Geometry parameterization by Samuel Gundry (Amazon Web Services) and Parisa Shabestari (Amazon Web Services) * Guidance on dataset preparation for ML by Danielle Madix (Amazon Web Services) * Simulation runs, HPC setup and dataset preparation by Neil Ashton (Amazon Web Services, now NVIDIA) License ---- This dataset is provided under the CC BY SA 4.0 license, please see LICENSE.txt for full license text. version history: --------------- * 15/02/2025 - files uploaded to HuggingFace * 12/11/2024 - added validation folder that contains the full output from all four mesh levels that were used to validate the methodology used. * 04/08/2024 - updates to the file description and arxiv paper * 05/06/2024 - global forces/geo added for all runs * 01/05/2024 - force/moments corrected (prior version had incorrect Cs data) * 18/04/2024 - draft version produced

AstroMLCore/AstroM3Dataset

AstroMLCore

"2025-03-27T21:43:24Z"

18,918

0

[ "license:mit", "size_categories:10K<n<100K", "arxiv:2411.08842", "region:us", "astronomy", "multimodal", "classification" ]

null

"2024-11-06T20:51:40Z"

--- license: mit pretty_name: AstroM3Dataset size_categories: - 10K<n<100K tags: - astronomy - multimodal - classification arxiv: - arXiv:2411.08842 --- # AstroM3Dataset ## Description AstroM3Dataset is a time-series astronomy dataset containing photometry, spectra, and metadata features for variable stars. The dataset was constructed by cross-matching publicly available astronomical datasets, primarily from the ASAS-SN (Shappee et al. 2014) variable star catalog (Jayasinghe et al. 2019) and LAMOST spectroscopic survey (Cui et al. 2012), along with data from WISE (Wright et al. 2010), GALEX (Morrissey et al. 2007), 2MASS (Skrutskie et al. 2006) and Gaia EDR3 (Gaia Collaboration et al. 2021). The dataset includes multiple subsets (`full`, `sub10`, `sub25`, `sub50`) and supports different random seeds (`42`, `66`, `0`, `12`, `123`). Each sample consists of: - **Photometry**: Light curve data of shape `(N, 3)` (time, flux, flux\_error). - **Spectra**: Spectra observations of shape `(M, 3)` (wavelength, flux, flux\_error). - **Metadata**: - `meta_cols`: Dictionary of metadata feature names and values. - `photo_cols`: Dictionary of photometric feature names and values. - **Label**: The class name as a string. ## Corresponding paper and code - Paper: [AstroM<sup>3</sup>: A self-supervised multimodal model for astronomy](https://arxiv.org/abs/2411.08842) - Code Repository: [GitHub: AstroM<sup>3</sup>](https://github.com/MeriDK/AstroM3/) - Processed Data: [AstroMLCore/AstroM3Processed](https://huggingface.co/datasets/AstroMLCore/AstroM3Processed/) **Note:** The processed dataset `AstroM3Processed` is created from the original dataset `AstroM3Dataset` by using [preprocess.py](https://huggingface.co/datasets/AstroMLCore/AstroM3Dataset/blob/main/preprocess.py) --- ## Subsets and Seeds AstroM3Dataset is available in different subset sizes: - `full`: Entire dataset - `sub50`: 50% subset - `sub25`: 25% subset - `sub10`: 10% subset Each subset is sampled from the respective train, validation, and test splits of the full dataset. For reproducibility, each subset is provided with different random seeds: - `42`, `66`, `0`, `12`, `123` ## Data Organization The dataset is organized as follows: ``` AstroM3Dataset/ ├── photometry.zip # Contains all photometry light curves ├── utils/ │ ├── parallelzipfile.py # Zip file reader to open photometry.zip ├── spectra/ # Spectra files organized by class │ ├── EA/ │ │ ├── file1.dat │ │ ├── file2.dat │ │ ├── ... │ ├── EW/ │ ├── SR/ │ ├── ... ├── splits/ # Train/val/test splits for each subset and seed │ ├── full/ │ │ ├── 42/ │ │ │ ├── train.csv │ │ │ ├── val.csv │ │ │ ├── test.csv │ │ │ ├── info.json # Contains feature descriptions and preprocessing info │ │ ├── 66/ │ │ ├── 0/ │ │ ├── 12/ │ │ ├── 123/ │ ├── sub10/ │ ├── sub25/ │ ├── sub50/ │── AstroM3Dataset.py # Hugging Face dataset script ``` ## Usage To load the dataset using the Hugging Face `datasets` library: ```python from datasets import load_dataset # Load the default full dataset with seed 42 dataset = load_dataset("AstroMLCore/AstroM3Dataset", trust_remote_code=True) ``` The default configuration is **full_42** (entire dataset with seed 42). To load a specific subset and seed, use {subset}_{seed} as the name: ```python from datasets import load_dataset # Load the 25% subset sampled using seed 123 dataset = load_dataset("AstroMLCore/AstroM3Dataset", name="sub25_123", trust_remote_code=True) ``` --- ## Citation 🤗 If you find this dataset usefull, please cite our paper 🤗 ```bibtex @article{rizhko2024astrom, title={AstroM $\^{} 3$: A self-supervised multimodal model for astronomy}, author={Rizhko, Mariia and Bloom, Joshua S}, journal={arXiv preprint arXiv:2411.08842}, year={2024} } ``` ## References 1. Shappee, B. J., Prieto, J. L., Grupe, D., et al. 2014, ApJ, 788, 48, doi: 10.1088/0004-637X/788/1/48 2. Jayasinghe, T., Stanek, K. Z., Kochanek, C. S., et al. 2019, MNRAS, 486, 1907, doi: 10.1093/mnras/stz844 3. Cui, X.-Q., Zhao, Y.-H., Chu, Y.-Q., et al. 2012, Research in Astronomy and Astrophysics, 12, 1197, doi: 10.1088/1674-4527/12/9/003 4. Wright, E. L., Eisenhardt, P. R. M., Mainzer, A. K., et al. 2010, AJ, 140, 1868, doi: 10.1088/0004-6256/140/6/1868 5. Morrissey, P., Conrow, T., Barlow, T. A., et al. 2007, ApJS, 173, 682, doi: 10.1086/520512 6. Skrutskie, M. F., Cutri, R. M., Stiening, R., et al. 2006, AJ, 131, 1163, doi: 10.1086/498708 7. Gaia Collaboration, Brown, A. G. A., et al. 2021, AAP, 649, A1, doi: 10.1051/0004-6361/202039657

TIGER-Lab/OmniEdit-Filtered-1.2M

TIGER-Lab

"2024-12-06T02:57:59Z"

18,883

85

[ "language:en", "license:mit", "size_categories:1M<n<10M", "format:parquet", "modality:image", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "arxiv:2411.07199", "region:us", "image" ]

null

"2024-11-11T07:40:47Z"

--- language: - en license: mit size_categories: - 1M<n<10M pretty_name: OmniEdit dataset_info: features: - name: omni_edit_id dtype: string - name: task dtype: string - name: src_img dtype: image - name: edited_img dtype: image - name: edited_prompt_list sequence: string - name: width dtype: int64 - name: height dtype: int64 - name: sc_score_1 dtype: int64 - name: sc_score_2 dtype: int64 - name: sc_reasoning dtype: string - name: pq_score dtype: int64 - name: pq_reasoning dtype: string - name: o_score dtype: float64 splits: - name: dev num_bytes: 1547839078.0 num_examples: 700 - name: train num_bytes: 2852916299223.88 num_examples: 1202797 download_size: 2978259415518 dataset_size: 2854464138301.88 configs: - config_name: default data_files: - split: dev path: data/dev-* - split: train path: data/train-* tags: - image --- ## OmniEdit In this paper, we present OMNI-EDIT, which is an omnipotent editor to handle seven different image editing tasks with any aspect ratio seamlessly. Our contribution is in four folds: (1) OMNI-EDIT is trained by utilizing the supervision from seven different specialist models to ensure task coverage. (2) we utilize importance sampling based on the scores provided by large multimodal models (like GPT-4o) instead of CLIP-score to improve the data quality. [📃Paper](https://tiger-ai-lab.github.io/OmniEdit/) | [🌐Website](https://tiger-ai-lab.github.io/OmniEdit/) | [💻Github](https://github.com/TIGER-AI-Lab/OmniEdit) | [📚Dataset](https://huggingface.co/datasets/TIGER-Lab/OmniEdit-Filtered-1.2M) ## Dataset Columns The dataset contains the following columns: - src, edited_img: they are the source and edited images. - edited_prompt_list: they are the short and long editing instructions. - task: this indicates the editing task, which has seven categories like addition, removal, background, environment, style, etc. - sc_score_1 and sc_score_1: semantic consistency score assigned by our quality rater. - pq_score: the perceptual quality score assigned by our quality rater. - o_score: the overall score, which is the weighted average of sc and pq score. - *_reasoning: the rationale for assigning these scores. ## Data Pipeline We synthesize the large scale dataset through specialist distillation. Our synthesis pipeline is depicted in <p align="center"> <img src="synthesis.png" width="800"> </p> Our released version contains 1.2M pairs covering seven different skills like addition, swaping, removal, attribute modification, background change, environment change and sytle transfer. The dataset has been filtered with VIEScore. ## Comparison with Others Our dataset has the most diverse, highest-quality image editing pairs of any resolution. <p align="center"> <img src="comparison.png" width="800"> </p> ## Citation If you find our paper useful, please cite us with ``` @article{wei2024omniedit, title={OmniEdit: Building Image Editing Generalist Models Through Specialist Supervision}, author={Wei, Cong and Xiong, Zheyang and Ren, Weiming and Du, Xinrun and Zhang, Ge and Chen, Wenhu}, journal={arXiv preprint arXiv:2411.07199}, year={2024} } ```

dair-ai/emotion

dair-ai

"2024-08-08T06:10:47Z"

18,876

351

[ "task_categories:text-classification", "task_ids:multi-class-classification", "annotations_creators:machine-generated", "language_creators:machine-generated", "multilinguality:monolingual", "source_datasets:original", "language:en", "license:other", "size_categories:100K<n<1M", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us", "emotion-classification" ]

[ "text-classification" ]

"2022-03-02T23:29:22Z"

--- annotations_creators: - machine-generated language_creators: - machine-generated language: - en license: - other multilinguality: - monolingual size_categories: - 10K<n<100K source_datasets: - original task_categories: - text-classification task_ids: - multi-class-classification paperswithcode_id: emotion pretty_name: Emotion tags: - emotion-classification dataset_info: - config_name: split features: - name: text dtype: string - name: label dtype: class_label: names: '0': sadness '1': joy '2': love '3': anger '4': fear '5': surprise splits: - name: train num_bytes: 1741533 num_examples: 16000 - name: validation num_bytes: 214695 num_examples: 2000 - name: test num_bytes: 217173 num_examples: 2000 download_size: 1287193 dataset_size: 2173401 - config_name: unsplit features: - name: text dtype: string - name: label dtype: class_label: names: '0': sadness '1': joy '2': love '3': anger '4': fear '5': surprise splits: - name: train num_bytes: 45444017 num_examples: 416809 download_size: 26888538 dataset_size: 45444017 configs: - config_name: split data_files: - split: train path: split/train-* - split: validation path: split/validation-* - split: test path: split/test-* default: true - config_name: unsplit data_files: - split: train path: unsplit/train-* train-eval-index: - config: default task: text-classification task_id: multi_class_classification splits: train_split: train eval_split: test col_mapping: text: text label: target metrics: - type: accuracy name: Accuracy - type: f1 name: F1 macro args: average: macro - type: f1 name: F1 micro args: average: micro - type: f1 name: F1 weighted args: average: weighted - type: precision name: Precision macro args: average: macro - type: precision name: Precision micro args: average: micro - type: precision name: Precision weighted args: average: weighted - type: recall name: Recall macro args: average: macro - type: recall name: Recall micro args: average: micro - type: recall name: Recall weighted args: average: weighted --- # Dataset Card for "emotion" ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Homepage:** [https://github.com/dair-ai/emotion_dataset](https://github.com/dair-ai/emotion_dataset) - **Repository:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - **Paper:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - **Point of Contact:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - **Size of downloaded dataset files:** 16.13 MB - **Size of the generated dataset:** 47.62 MB - **Total amount of disk used:** 63.75 MB ### Dataset Summary Emotion is a dataset of English Twitter messages with six basic emotions: anger, fear, joy, love, sadness, and surprise. For more detailed information please refer to the paper. ### Supported Tasks and Leaderboards [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Languages [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Dataset Structure ### Data Instances An example looks as follows. ``` { "text": "im feeling quite sad and sorry for myself but ill snap out of it soon", "label": 0 } ``` ### Data Fields The data fields are: - `text`: a `string` feature. - `label`: a classification label, with possible values including `sadness` (0), `joy` (1), `love` (2), `anger` (3), `fear` (4), `surprise` (5). ### Data Splits The dataset has 2 configurations: - split: with a total of 20_000 examples split into train, validation and split - unsplit: with a total of 416_809 examples in a single train split | name | train | validation | test | |---------|-------:|-----------:|-----:| | split | 16000 | 2000 | 2000 | | unsplit | 416809 | n/a | n/a | ## Dataset Creation ### Curation Rationale [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Source Data #### Initial Data Collection and Normalization [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the source language producers? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Annotations #### Annotation process [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the annotators? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Personal and Sensitive Information [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Discussion of Biases [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Other Known Limitations [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Additional Information ### Dataset Curators [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Licensing Information The dataset should be used for educational and research purposes only. ### Citation Information If you use this dataset, please cite: ``` @inproceedings{saravia-etal-2018-carer, title = "{CARER}: Contextualized Affect Representations for Emotion Recognition", author = "Saravia, Elvis and Liu, Hsien-Chi Toby and Huang, Yen-Hao and Wu, Junlin and Chen, Yi-Shin", booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing", month = oct # "-" # nov, year = "2018", address = "Brussels, Belgium", publisher = "Association for Computational Linguistics", url = "https://www.aclweb.org/anthology/D18-1404", doi = "10.18653/v1/D18-1404", pages = "3687--3697", abstract = "Emotions are expressed in nuanced ways, which varies by collective or individual experiences, knowledge, and beliefs. Therefore, to understand emotion, as conveyed through text, a robust mechanism capable of capturing and modeling different linguistic nuances and phenomena is needed. We propose a semi-supervised, graph-based algorithm to produce rich structural descriptors which serve as the building blocks for constructing contextualized affect representations from text. The pattern-based representations are further enriched with word embeddings and evaluated through several emotion recognition tasks. Our experimental results demonstrate that the proposed method outperforms state-of-the-art techniques on emotion recognition tasks.", } ``` ### Contributions Thanks to [@lhoestq](https://github.com/lhoestq), [@thomwolf](https://github.com/thomwolf), [@lewtun](https://github.com/lewtun) for adding this dataset.

HuggingFaceH4/ultrachat_200k

HuggingFaceH4

"2024-10-16T11:52:27Z"

18,813

526

[ "task_categories:text-generation", "language:en", "license:mit", "size_categories:100K<n<1M", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "arxiv:2305.14233", "region:us" ]

[ "text-generation" ]

"2023-10-24T08:24:57Z"

--- language: - en license: mit size_categories: - 100K<n<1M task_categories: - text-generation pretty_name: UltraChat 200k configs: - config_name: default data_files: - split: train_sft path: data/train_sft-* - split: test_sft path: data/test_sft-* - split: train_gen path: data/train_gen-* - split: test_gen path: data/test_gen-* dataset_info: features: - name: prompt dtype: string - name: prompt_id dtype: string - name: messages list: - name: content dtype: string - name: role dtype: string splits: - name: train_sft num_bytes: 1397058554 num_examples: 207865 - name: test_sft num_bytes: 154695659 num_examples: 23110 - name: train_gen num_bytes: 1347396812 num_examples: 256032 - name: test_gen num_bytes: 148276089 num_examples: 28304 download_size: 1624049723 dataset_size: 3047427114 --- # Dataset Card for UltraChat 200k ## Dataset Description This is a heavily filtered version of the [UltraChat](https://github.com/thunlp/UltraChat) dataset and was used to train [Zephyr-7B-β](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta), a state of the art 7b chat model. The original datasets consists of 1.4M dialogues generated by ChatGPT and spanning a wide range of topics. To create `UltraChat 200k`, we applied the following logic: - Selection of a subset of data for faster supervised fine tuning. - Truecasing of the dataset, as we observed around 5% of the data contained grammatical errors like "Hello. how are you?" instead of "Hello. How are you?" - Removal of dialogues where the assistant replies with phrases like "I do not have emotions" or "I don't have opinions", even for fact-based prompts that don't involve either. ## Dataset Structure The dataset has four splits, suitable for: * Supervised fine-tuning (`sft`). * Generation ranking (`gen`) via techniques like rejection sampling or PPO. The number of examples per split is shown as follows: | train_sft | test_sft | train_gen | test_gen | |:-------:|:-----------:|:-----:| :-----:| | 207865 | 23110 | 256032 | 28304 | The dataset is stored in parquet format with each entry using the following schema: ``` { "prompt": "Create a fully-developed protagonist who is challenged to survive within a dystopian society under the rule of a tyrant. ...", "messages":[ { "content": "Create a fully-developed protagonist who is challenged to survive within a dystopian society under the rule of a tyrant. ...", "role": "user" }, { "content": "Name: Ava\n\n Ava was just 16 years old when the world as she knew it came crashing down. The government had collapsed, leaving behind a chaotic and lawless society. ...", "role": "assistant" }, { "content": "Wow, Ava's story is so intense and inspiring! Can you provide me with more details. ...", "role": "user" }, { "content": "Certainly! ....", "role": "assistant" }, { "content": "That's really interesting! I would love to hear more...", "role": "user" } { "content": "Certainly! ....", "role": "assistant" }, ], "prompt_id": "d938b65dfe31f05f80eb8572964c6673eddbd68eff3db6bd234d7f1e3b86c2af" } ``` ## Citation If you find this dataset is useful in your work, please cite the original UltraChat dataset: ``` @misc{ding2023enhancing, title={Enhancing Chat Language Models by Scaling High-quality Instructional Conversations}, author={Ning Ding and Yulin Chen and Bokai Xu and Yujia Qin and Zhi Zheng and Shengding Hu and Zhiyuan Liu and Maosong Sun and Bowen Zhou}, year={2023}, eprint={2305.14233}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```

TrevorDohm/Stack_Tokenized

TrevorDohm

"2024-04-16T00:19:53Z"

18,811

0

[ "task_categories:text-generation", "language_creators:crowdsourced", "language_creators:expert-generated", "multilinguality:multilingual", "language:code", "license:other", "size_categories:100M<n<1B", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]

[ "text-generation" ]

"2024-03-10T05:49:00Z"

--- annotations_creators: [] language_creators: - crowdsourced - expert-generated language: - code license: - other multilinguality: - multilingual pretty_name: The-Stack-Tokenized size_categories: - unknown source_datasets: [] task_categories: - text-generation task_ids: [] ---

ceval/ceval-exam

ceval

"2025-03-25T13:18:03Z"

18,647

259

[ "task_categories:text-classification", "task_categories:multiple-choice", "task_categories:question-answering", "language:zh", "license:cc-by-nc-sa-4.0", "size_categories:10K<n<100K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "arxiv:2305.08322", "region:us" ]

[ "text-classification", "multiple-choice", "question-answering" ]

"2023-05-16T01:47:44Z"

--- license: cc-by-nc-sa-4.0 task_categories: - text-classification - multiple-choice - question-answering language: - zh pretty_name: C-Eval size_categories: - 10K<n<100K configs: - config_name: accountant data_files: - split: test path: accountant/test-* - split: val path: accountant/val-* - split: dev path: accountant/dev-* - config_name: advanced_mathematics data_files: - split: test path: advanced_mathematics/test-* - split: val path: advanced_mathematics/val-* - split: dev path: advanced_mathematics/dev-* - config_name: art_studies data_files: - split: test path: art_studies/test-* - split: val path: art_studies/val-* - split: dev path: art_studies/dev-* - config_name: basic_medicine data_files: - split: test path: basic_medicine/test-* - split: val path: basic_medicine/val-* - split: dev path: basic_medicine/dev-* - config_name: business_administration data_files: - split: test path: business_administration/test-* - split: val path: business_administration/val-* - split: dev path: business_administration/dev-* - config_name: chinese_language_and_literature data_files: - split: test path: chinese_language_and_literature/test-* - split: val path: chinese_language_and_literature/val-* - split: dev path: chinese_language_and_literature/dev-* - config_name: civil_servant data_files: - split: test path: civil_servant/test-* - split: val path: civil_servant/val-* - split: dev path: civil_servant/dev-* - config_name: clinical_medicine data_files: - split: test path: clinical_medicine/test-* - split: val path: clinical_medicine/val-* - split: dev path: clinical_medicine/dev-* - config_name: college_chemistry data_files: - split: test path: college_chemistry/test-* - split: val path: college_chemistry/val-* - split: dev path: college_chemistry/dev-* - config_name: college_economics data_files: - split: test path: college_economics/test-* - split: val path: college_economics/val-* - split: dev path: college_economics/dev-* - config_name: college_physics data_files: - split: test path: college_physics/test-* - split: val path: college_physics/val-* - split: dev path: college_physics/dev-* - config_name: college_programming data_files: - split: test path: college_programming/test-* - split: val path: college_programming/val-* - split: dev path: college_programming/dev-* - config_name: computer_architecture data_files: - split: test path: computer_architecture/test-* - split: val path: computer_architecture/val-* - split: dev path: computer_architecture/dev-* - config_name: computer_network data_files: - split: test path: computer_network/test-* - split: val path: computer_network/val-* - split: dev path: computer_network/dev-* - config_name: discrete_mathematics data_files: - split: test path: discrete_mathematics/test-* - split: val path: discrete_mathematics/val-* - split: dev path: discrete_mathematics/dev-* - config_name: education_science data_files: - split: test path: education_science/test-* - split: val path: education_science/val-* - split: dev path: education_science/dev-* - config_name: electrical_engineer data_files: - split: test path: electrical_engineer/test-* - split: val path: electrical_engineer/val-* - split: dev path: electrical_engineer/dev-* - config_name: environmental_impact_assessment_engineer data_files: - split: test path: environmental_impact_assessment_engineer/test-* - split: val path: environmental_impact_assessment_engineer/val-* - split: dev path: environmental_impact_assessment_engineer/dev-* - config_name: fire_engineer data_files: - split: test path: fire_engineer/test-* - split: val path: fire_engineer/val-* - split: dev path: fire_engineer/dev-* - config_name: high_school_biology data_files: - split: test path: high_school_biology/test-* - split: val path: high_school_biology/val-* - split: dev path: high_school_biology/dev-* - config_name: high_school_chemistry data_files: - split: test path: high_school_chemistry/test-* - split: val path: high_school_chemistry/val-* - split: dev path: high_school_chemistry/dev-* - config_name: high_school_chinese data_files: - split: test path: high_school_chinese/test-* - split: val path: high_school_chinese/val-* - split: dev path: high_school_chinese/dev-* - config_name: high_school_geography data_files: - split: test path: high_school_geography/test-* - split: val path: high_school_geography/val-* - split: dev path: high_school_geography/dev-* - config_name: high_school_history data_files: - split: test path: high_school_history/test-* - split: val path: high_school_history/val-* - split: dev path: high_school_history/dev-* - config_name: high_school_mathematics data_files: - split: test path: high_school_mathematics/test-* - split: val path: high_school_mathematics/val-* - split: dev path: high_school_mathematics/dev-* - config_name: high_school_physics data_files: - split: test path: high_school_physics/test-* - split: val path: high_school_physics/val-* - split: dev path: high_school_physics/dev-* - config_name: high_school_politics data_files: - split: test path: high_school_politics/test-* - split: val path: high_school_politics/val-* - split: dev path: high_school_politics/dev-* - config_name: ideological_and_moral_cultivation data_files: - split: test path: ideological_and_moral_cultivation/test-* - split: val path: ideological_and_moral_cultivation/val-* - split: dev path: ideological_and_moral_cultivation/dev-* - config_name: law data_files: - split: test path: law/test-* - split: val path: law/val-* - split: dev path: law/dev-* - config_name: legal_professional data_files: - split: test path: legal_professional/test-* - split: val path: legal_professional/val-* - split: dev path: legal_professional/dev-* - config_name: logic data_files: - split: test path: logic/test-* - split: val path: logic/val-* - split: dev path: logic/dev-* - config_name: mao_zedong_thought data_files: - split: test path: mao_zedong_thought/test-* - split: val path: mao_zedong_thought/val-* - split: dev path: mao_zedong_thought/dev-* - config_name: marxism data_files: - split: test path: marxism/test-* - split: val path: marxism/val-* - split: dev path: marxism/dev-* - config_name: metrology_engineer data_files: - split: test path: metrology_engineer/test-* - split: val path: metrology_engineer/val-* - split: dev path: metrology_engineer/dev-* - config_name: middle_school_biology data_files: - split: test path: middle_school_biology/test-* - split: val path: middle_school_biology/val-* - split: dev path: middle_school_biology/dev-* - config_name: middle_school_chemistry data_files: - split: test path: middle_school_chemistry/test-* - split: val path: middle_school_chemistry/val-* - split: dev path: middle_school_chemistry/dev-* - config_name: middle_school_geography data_files: - split: test path: middle_school_geography/test-* - split: val path: middle_school_geography/val-* - split: dev path: middle_school_geography/dev-* - config_name: middle_school_history data_files: - split: test path: middle_school_history/test-* - split: val path: middle_school_history/val-* - split: dev path: middle_school_history/dev-* - config_name: middle_school_mathematics data_files: - split: test path: middle_school_mathematics/test-* - split: val path: middle_school_mathematics/val-* - split: dev path: middle_school_mathematics/dev-* - config_name: middle_school_physics data_files: - split: test path: middle_school_physics/test-* - split: val path: middle_school_physics/val-* - split: dev path: middle_school_physics/dev-* - config_name: middle_school_politics data_files: - split: test path: middle_school_politics/test-* - split: val path: middle_school_politics/val-* - split: dev path: middle_school_politics/dev-* - config_name: modern_chinese_history data_files: - split: test path: modern_chinese_history/test-* - split: val path: modern_chinese_history/val-* - split: dev path: modern_chinese_history/dev-* - config_name: operating_system data_files: - split: test path: operating_system/test-* - split: val path: operating_system/val-* - split: dev path: operating_system/dev-* - config_name: physician data_files: - split: test path: physician/test-* - split: val path: physician/val-* - split: dev path: physician/dev-* - config_name: plant_protection data_files: - split: test path: plant_protection/test-* - split: val path: plant_protection/val-* - split: dev path: plant_protection/dev-* - config_name: probability_and_statistics data_files: - split: test path: probability_and_statistics/test-* - split: val path: probability_and_statistics/val-* - split: dev path: probability_and_statistics/dev-* - config_name: professional_tour_guide data_files: - split: test path: professional_tour_guide/test-* - split: val path: professional_tour_guide/val-* - split: dev path: professional_tour_guide/dev-* - config_name: sports_science data_files: - split: test path: sports_science/test-* - split: val path: sports_science/val-* - split: dev path: sports_science/dev-* - config_name: tax_accountant data_files: - split: test path: tax_accountant/test-* - split: val path: tax_accountant/val-* - split: dev path: tax_accountant/dev-* - config_name: teacher_qualification data_files: - split: test path: teacher_qualification/test-* - split: val path: teacher_qualification/val-* - split: dev path: teacher_qualification/dev-* - config_name: urban_and_rural_planner data_files: - split: test path: urban_and_rural_planner/test-* - split: val path: urban_and_rural_planner/val-* - split: dev path: urban_and_rural_planner/dev-* - config_name: veterinary_medicine data_files: - split: test path: veterinary_medicine/test-* - split: val path: veterinary_medicine/val-* - split: dev path: veterinary_medicine/dev-* dataset_info: - config_name: accountant features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 176917 num_examples: 443 - name: val num_bytes: 19549 num_examples: 49 - name: dev num_bytes: 3414 num_examples: 5 download_size: 151233 dataset_size: 199880 - config_name: advanced_mathematics features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 50031 num_examples: 173 - name: val num_bytes: 5331 num_examples: 19 - name: dev num_bytes: 7012 num_examples: 5 download_size: 50962 dataset_size: 62374 - config_name: art_studies features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 41227 num_examples: 298 - name: val num_bytes: 4581 num_examples: 33 - name: dev num_bytes: 1439 num_examples: 5 download_size: 46524 dataset_size: 47247 - config_name: basic_medicine features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 28820 num_examples: 175 - name: val num_bytes: 2627 num_examples: 19 - name: dev num_bytes: 1825 num_examples: 5 download_size: 37360 dataset_size: 33272 - config_name: business_administration features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 78387 num_examples: 301 - name: val num_bytes: 9225 num_examples: 33 - name: dev num_bytes: 3155 num_examples: 5 download_size: 75885 dataset_size: 90767 - config_name: chinese_language_and_literature features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 32328 num_examples: 209 - name: val num_bytes: 3446 num_examples: 23 - name: dev num_bytes: 1892 num_examples: 5 download_size: 42310 dataset_size: 37666 - config_name: civil_servant features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 181504 num_examples: 429 - name: val num_bytes: 21273 num_examples: 47 - name: dev num_bytes: 4576 num_examples: 5 download_size: 179936 dataset_size: 207353 - config_name: clinical_medicine features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 42161 num_examples: 200 - name: val num_bytes: 4167 num_examples: 22 - name: dev num_bytes: 1951 num_examples: 5 download_size: 48689 dataset_size: 48279 - config_name: college_chemistry features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 45798 num_examples: 224 - name: val num_bytes: 4443 num_examples: 24 - name: dev num_bytes: 3611 num_examples: 5 download_size: 53519 dataset_size: 53852 - config_name: college_economics features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 119734 num_examples: 497 - name: val num_bytes: 14461 num_examples: 55 - name: dev num_bytes: 3673 num_examples: 5 download_size: 106080 dataset_size: 137868 - config_name: college_physics features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 55731 num_examples: 176 - name: val num_bytes: 6145 num_examples: 19 - name: dev num_bytes: 3824 num_examples: 5 download_size: 62877 dataset_size: 65700 - config_name: college_programming features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 83541 num_examples: 342 - name: val num_bytes: 9543 num_examples: 37 - name: dev num_bytes: 2882 num_examples: 5 download_size: 82850 dataset_size: 95966 - config_name: computer_architecture features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 40613 num_examples: 193 - name: val num_bytes: 4149 num_examples: 21 - name: dev num_bytes: 2793 num_examples: 5 download_size: 48021 dataset_size: 47555 - config_name: computer_network features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 35408 num_examples: 171 - name: val num_bytes: 3799 num_examples: 19 - name: dev num_bytes: 2361 num_examples: 5 download_size: 43940 dataset_size: 41568 - config_name: discrete_mathematics features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 36045 num_examples: 153 - name: val num_bytes: 3424 num_examples: 16 - name: dev num_bytes: 2002 num_examples: 5 download_size: 42941 dataset_size: 41471 - config_name: education_science features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 55753 num_examples: 270 - name: val num_bytes: 5519 num_examples: 29 - name: dev num_bytes: 3093 num_examples: 5 download_size: 60878 dataset_size: 64365 - config_name: electrical_engineer features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 73727 num_examples: 339 - name: val num_bytes: 8315 num_examples: 37 - name: dev num_bytes: 2180 num_examples: 5 download_size: 75493 dataset_size: 84222 - config_name: environmental_impact_assessment_engineer features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 84680 num_examples: 281 - name: val num_bytes: 9186 num_examples: 31 - name: dev num_bytes: 2495 num_examples: 5 download_size: 73938 dataset_size: 96361 - config_name: fire_engineer features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 83611 num_examples: 282 - name: val num_bytes: 9998 num_examples: 31 - name: dev num_bytes: 2209 num_examples: 5 download_size: 80027 dataset_size: 95818 - config_name: high_school_biology features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 55242 num_examples: 175 - name: val num_bytes: 6105 num_examples: 19 - name: dev num_bytes: 2164 num_examples: 5 download_size: 60521 dataset_size: 63511 - config_name: high_school_chemistry features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 46918 num_examples: 172 - name: val num_bytes: 5625 num_examples: 19 - name: dev num_bytes: 2576 num_examples: 5 download_size: 55668 dataset_size: 55119 - config_name: high_school_chinese features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 110347 num_examples: 178 - name: val num_bytes: 10475 num_examples: 19 - name: dev num_bytes: 5290 num_examples: 5 download_size: 121511 dataset_size: 126112 - config_name: high_school_geography features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 41244 num_examples: 178 - name: val num_bytes: 3985 num_examples: 19 - name: dev num_bytes: 2087 num_examples: 5 download_size: 49899 dataset_size: 47316 - config_name: high_school_history features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 56196 num_examples: 182 - name: val num_bytes: 6618 num_examples: 20 - name: dev num_bytes: 2421 num_examples: 5 download_size: 68541 dataset_size: 65235 - config_name: high_school_mathematics features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 41080 num_examples: 166 - name: val num_bytes: 5144 num_examples: 18 - name: dev num_bytes: 3552 num_examples: 5 download_size: 53050 dataset_size: 49776 - config_name: high_school_physics features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 61682 num_examples: 175 - name: val num_bytes: 7266 num_examples: 19 - name: dev num_bytes: 2266 num_examples: 5 download_size: 66380 dataset_size: 71214 - config_name: high_school_politics features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 83356 num_examples: 176 - name: val num_bytes: 8909 num_examples: 19 - name: dev num_bytes: 4730 num_examples: 5 download_size: 90214 dataset_size: 96995 - config_name: ideological_and_moral_cultivation features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 35315 num_examples: 172 - name: val num_bytes: 3241 num_examples: 19 - name: dev num_bytes: 1296 num_examples: 5 download_size: 41532 dataset_size: 39852 - config_name: law features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 79782 num_examples: 221 - name: val num_bytes: 8119 num_examples: 24 - name: dev num_bytes: 4142 num_examples: 5 download_size: 83562 dataset_size: 92043 - config_name: legal_professional features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 121985 num_examples: 215 - name: val num_bytes: 12215 num_examples: 23 - name: dev num_bytes: 6974 num_examples: 5 download_size: 125081 dataset_size: 141174 - config_name: logic features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 144246 num_examples: 204 - name: val num_bytes: 15561 num_examples: 22 - name: dev num_bytes: 5641 num_examples: 5 download_size: 141258 dataset_size: 165448 - config_name: mao_zedong_thought features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 56699 num_examples: 219 - name: val num_bytes: 5487 num_examples: 24 - name: dev num_bytes: 3349 num_examples: 5 download_size: 57281 dataset_size: 65535 - config_name: marxism features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 38662 num_examples: 179 - name: val num_bytes: 4251 num_examples: 19 - name: dev num_bytes: 2142 num_examples: 5 download_size: 45030 dataset_size: 45055 - config_name: metrology_engineer features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 47484 num_examples: 219 - name: val num_bytes: 6116 num_examples: 24 - name: dev num_bytes: 2485 num_examples: 5 download_size: 55033 dataset_size: 56085 - config_name: middle_school_biology features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 47264 num_examples: 192 - name: val num_bytes: 5263 num_examples: 21 - name: dev num_bytes: 4327 num_examples: 5 download_size: 58872 dataset_size: 56854 - config_name: middle_school_chemistry features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 47575 num_examples: 185 - name: val num_bytes: 5654 num_examples: 20 - name: dev num_bytes: 3866 num_examples: 5 download_size: 59005 dataset_size: 57095 - config_name: middle_school_geography features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 23329 num_examples: 108 - name: val num_bytes: 2641 num_examples: 12 - name: dev num_bytes: 2148 num_examples: 5 download_size: 37528 dataset_size: 28118 - config_name: middle_school_history features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 47076 num_examples: 207 - name: val num_bytes: 5990 num_examples: 22 - name: dev num_bytes: 2014 num_examples: 5 download_size: 55763 dataset_size: 55080 - config_name: middle_school_mathematics features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 33142 num_examples: 177 - name: val num_bytes: 4897 num_examples: 19 - name: dev num_bytes: 3187 num_examples: 5 download_size: 45790 dataset_size: 41226 - config_name: middle_school_physics features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 48793 num_examples: 178 - name: val num_bytes: 5279 num_examples: 19 - name: dev num_bytes: 3531 num_examples: 5 download_size: 60336 dataset_size: 57603 - config_name: middle_school_politics features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 72478 num_examples: 193 - name: val num_bytes: 7320 num_examples: 21 - name: dev num_bytes: 3687 num_examples: 5 download_size: 75631 dataset_size: 83485 - config_name: modern_chinese_history features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 51247 num_examples: 212 - name: val num_bytes: 5188 num_examples: 23 - name: dev num_bytes: 2983 num_examples: 5 download_size: 58881 dataset_size: 59418 - config_name: operating_system features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 31146 num_examples: 179 - name: val num_bytes: 3299 num_examples: 19 - name: dev num_bytes: 2557 num_examples: 5 download_size: 39873 dataset_size: 37002 - config_name: physician features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 89801 num_examples: 443 - name: val num_bytes: 8710 num_examples: 49 - name: dev num_bytes: 2033 num_examples: 5 download_size: 91373 dataset_size: 100544 - config_name: plant_protection features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 31877 num_examples: 199 - name: val num_bytes: 3634 num_examples: 22 - name: dev num_bytes: 3726 num_examples: 5 download_size: 42730 dataset_size: 39237 - config_name: probability_and_statistics features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 56749 num_examples: 166 - name: val num_bytes: 5781 num_examples: 18 - name: dev num_bytes: 6769 num_examples: 5 download_size: 62933 dataset_size: 69299 - config_name: professional_tour_guide features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 41231 num_examples: 266 - name: val num_bytes: 4509 num_examples: 29 - name: dev num_bytes: 1764 num_examples: 5 download_size: 51538 dataset_size: 47504 - config_name: sports_science features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 32527 num_examples: 180 - name: val num_bytes: 3493 num_examples: 19 - name: dev num_bytes: 4182 num_examples: 5 download_size: 44846 dataset_size: 40202 - config_name: tax_accountant features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 174482 num_examples: 443 - name: val num_bytes: 18932 num_examples: 49 - name: dev num_bytes: 4274 num_examples: 5 download_size: 147810 dataset_size: 197688 - config_name: teacher_qualification features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 107369 num_examples: 399 - name: val num_bytes: 12220 num_examples: 44 - name: dev num_bytes: 3215 num_examples: 5 download_size: 105490 dataset_size: 122804 - config_name: urban_and_rural_planner features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 110377 num_examples: 418 - name: val num_bytes: 12793 num_examples: 46 - name: dev num_bytes: 3166 num_examples: 5 download_size: 100220 dataset_size: 126336 - config_name: veterinary_medicine features: - name: id dtype: int32 - name: question dtype: string - name: A dtype: string - name: B dtype: string - name: C dtype: string - name: D dtype: string - name: answer dtype: string - name: explanation dtype: string splits: - name: test num_bytes: 39465 num_examples: 210 - name: val num_bytes: 4559 num_examples: 23 - name: dev num_bytes: 2362 num_examples: 5 download_size: 48398 dataset_size: 46386 --- C-Eval is a comprehensive Chinese evaluation suite for foundation models. It consists of 13948 multi-choice questions spanning 52 diverse disciplines and four difficulty levels. Please visit our [website](https://cevalbenchmark.com/) and [GitHub](https://github.com/SJTU-LIT/ceval/tree/main) or check our [paper](https://arxiv.org/abs/2305.08322) for more details. Each subject consists of three splits: dev, val, and test. The dev set per subject consists of five exemplars with explanations for few-shot evaluation. The val set is intended to be used for hyperparameter tuning. And the test set is for model evaluation. Labels on the test split are not released, users are required to submit their results to automatically obtain test accuracy. [How to submit?](https://github.com/SJTU-LIT/ceval/tree/main#how-to-submit) ### Load the data ```python from datasets import load_dataset dataset=load_dataset(r"ceval/ceval-exam",name="computer_network") print(dataset['val'][0]) # {'id': 0, 'question': '使用位填充方法，以01111110为位首flag，数据为011011111111111111110010，求问传送时要添加几个0____', 'A': '1', 'B': '2', 'C': '3', 'D': '4', 'answer': 'C', 'explanation': ''} ``` More details on loading and using the data are at our [github page](https://github.com/SJTU-LIT/ceval#data). Please cite our paper if you use our dataset. ``` @article{huang2023ceval, title={C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models}, author={Huang, Yuzhen and Bai, Yuzhuo and Zhu, Zhihao and Zhang, Junlei and Zhang, Jinghan and Su, Tangjun and Liu, Junteng and Lv, Chuancheng and Zhang, Yikai and Lei, Jiayi and Fu, Yao and Sun, Maosong and He, Junxian}, journal={arXiv preprint arXiv:2305.08322}, year={2023} } ```

applied-ai-018/pretraining_v1-omega_books

applied-ai-018

"2024-08-05T19:01:31Z"

18,559

1

[ "size_categories:100M<n<1B", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]

null

"2024-07-31T08:53:54Z"

--- dataset_info: config_name: CC-MAIN-2013-20 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 splits: - name: train num_bytes: 235476901236 num_examples: 51901183 download_size: 138494178972 dataset_size: 235476901236 configs: - config_name: CC-MAIN-2013-20 data_files: - split: train path: CC-MAIN-2013-20/train-* ---

mteb/biblenlp-corpus-mmteb

mteb

"2024-05-07T00:47:48Z"

18,551

1

[ "annotations_creators:no-annotation", "language_creators:expert-generated", "multilinguality:translation", "multilinguality:multilingual", "language:aai", "language:aak", "language:aau", "language:aaz", "language:abt", "language:abx", "language:aby", "language:acf", "language:acr", "language:acu", "language:adz", "language:aer", "language:aey", "language:agd", "language:agg", "language:agm", "language:agn", "language:agr", "language:agt", "language:agu", "language:aia", "language:aii", "language:aka", "language:ake", "language:alp", "language:alq", "language:als", "language:aly", "language:ame", "language:amf", "language:amk", "language:amm", "language:amn", "language:amo", "language:amp", "language:amr", "language:amu", "language:amx", "language:anh", "language:anv", "language:aoi", "language:aoj", "language:aom", "language:aon", "language:apb", "language:ape", "language:apn", "language:apr", "language:apu", "language:apw", "language:apz", "language:arb", "language:are", "language:arl", "language:arn", "language:arp", "language:asm", "language:aso", "language:ata", "language:atb", "language:atd", "language:atg", "language:att", "language:auc", "language:aui", "language:auy", "language:avt", "language:awb", "language:awk", "language:awx", "language:azb", "language:azg", "language:azz", "language:bao", "language:bba", "language:bbb", "language:bbr", "language:bch", "language:bco", "language:bdd", "language:bea", "language:bef", "language:bel", "language:ben", "language:beo", "language:beu", "language:bgs", "language:bgt", "language:bhg", "language:bhl", "language:big", "language:bjk", "language:bjp", "language:bjr", "language:bjv", "language:bjz", "language:bkd", "language:bki", "language:bkq", "language:bkx", "language:bla", "language:blw", "language:blz", "language:bmh", "language:bmk", "language:bmr", "language:bmu", "language:bnp", "language:boa", "language:boj", "language:bon", "language:box", "language:bpr", "language:bps", "language:bqc", "language:bqp", "language:bre", "language:bsj", "language:bsn", "language:bsp", "language:bss", "language:buk", "language:bus", "language:bvd", "language:bvr", "language:bxh", "language:byr", "language:byx", "language:bzd", "language:bzh", "language:bzj", "language:caa", "language:cab", "language:cac", "language:caf", "language:cak", "language:cao", "language:cap", "language:car", "language:cav", "language:cax", "language:cbc", "language:cbi", "language:cbk", "language:cbr", "language:cbs", "language:cbt", "language:cbu", "language:cbv", "language:cco", "language:ceb", "language:cek", "language:ces", "language:cgc", "language:cha", "language:chd", "language:chf", "language:chk", "language:chq", "language:chz", "language:cjo", "language:cjv", "language:ckb", "language:cle", "language:clu", "language:cme", "language:cmn", "language:cni", "language:cnl", "language:cnt", "language:cof", "language:con", "language:cop", "language:cot", "language:cpa", "language:cpb", "language:cpc", "language:cpu", "language:cpy", "language:crn", "language:crx", "language:cso", "language:csy", "language:cta", "language:cth", "language:ctp", "language:ctu", "language:cub", "language:cuc", "language:cui", "language:cuk", "language:cut", "language:cux", "language:cwe", "language:cya", "language:daa", "language:dad", "language:dah", "language:dan", "language:ded", "language:deu", "language:dgc", "language:dgr", "language:dgz", "language:dhg", "language:dif", "language:dik", "language:dji", "language:djk", "language:djr", "language:dob", "language:dop", "language:dov", "language:dwr", "language:dww", "language:dwy", "language:ebk", "language:eko", "language:emi", "language:emp", "language:eng", "language:enq", "language:epo", "language:eri", "language:ese", "language:esk", "language:etr", "language:ewe", "language:faa", "language:fai", "language:far", "language:ffm", "language:for", "language:fra", "language:fue", "language:fuf", "language:fuh", "language:gah", "language:gai", "language:gam", "language:gaw", "language:gdn", "language:gdr", "language:geb", "language:gfk", "language:ghs", "language:glk", "language:gmv", "language:gng", "language:gnn", "language:gnw", "language:gof", "language:grc", "language:gub", "language:guh", "language:gui", "language:guj", "language:gul", "language:gum", "language:gun", "language:guo", "language:gup", "language:gux", "language:gvc", "language:gvf", "language:gvn", "language:gvs", "language:gwi", "language:gym", "language:gyr", "language:hat", "language:hau", "language:haw", "language:hbo", "language:hch", "language:heb", "language:heg", "language:hin", "language:hix", "language:hla", "language:hlt", "language:hmo", "language:hns", "language:hop", "language:hot", "language:hrv", "language:hto", "language:hub", "language:hui", "language:hun", "language:hus", "language:huu", "language:huv", "language:hvn", "language:ian", "language:ign", "language:ikk", "language:ikw", "language:ilo", "language:imo", "language:inb", "language:ind", "language:ino", "language:iou", "language:ipi", "language:isn", "language:ita", "language:iws", "language:ixl", "language:jac", "language:jae", "language:jao", "language:jic", "language:jid", "language:jiv", "language:jni", "language:jpn", "language:jvn", "language:kan", "language:kaq", "language:kbc", "language:kbh", "language:kbm", "language:kbq", "language:kdc", "language:kde", "language:kdl", "language:kek", "language:ken", "language:kew", "language:kgf", "language:kgk", "language:kgp", "language:khs", "language:khz", "language:kik", "language:kiw", "language:kiz", "language:kje", "language:kjn", "language:kjs", "language:kkc", "language:kkl", "language:klt", "language:klv", "language:kmg", "language:kmh", "language:kmk", "language:kmo", "language:kms", "language:kmu", "language:kne", "language:knf", "language:knj", "language:knv", "language:kos", "language:kpf", "language:kpg", "language:kpj", "language:kpr", "language:kpw", "language:kpx", "language:kqa", "language:kqc", "language:kqf", "language:kql", "language:kqw", "language:ksd", "language:ksj", "language:ksr", "language:ktm", "language:kto", "language:kud", "language:kue", "language:kup", "language:kvg", "language:kvn", "language:kwd", "language:kwf", "language:kwi", "language:kwj", "language:kyc", "language:kyf", "language:kyg", "language:kyq", "language:kyz", "language:kze", "language:lac", "language:lat", "language:lbb", "language:lbk", "language:lcm", "language:leu", "language:lex", "language:lgl", "language:lid", "language:lif", "language:lin", "language:lit", "language:llg", "language:lug", "language:luo", "language:lww", "language:maa", "language:maj", "language:mal", "language:mam", "language:maq", "language:mar", "language:mau", "language:mav", "language:maz", "language:mbb", "language:mbc", "language:mbh", "language:mbj", "language:mbl", "language:mbs", "language:mbt", "language:mca", "language:mcb", "language:mcd", "language:mcf", "language:mco", "language:mcp", "language:mcq", "language:mcr", "language:mdy", "language:med", "language:mee", "language:mek", "language:meq", "language:met", "language:meu", "language:mgc", "language:mgh", "language:mgw", "language:mhl", "language:mib", "language:mic", "language:mie", "language:mig", "language:mih", "language:mil", "language:mio", "language:mir", "language:mit", "language:miz", "language:mjc", "language:mkj", "language:mkl", "language:mkn", "language:mks", "language:mle", "language:mlh", "language:mlp", "language:mmo", "language:mmx", "language:mna", "language:mop", "language:mox", "language:mph", "language:mpj", "language:mpm", "language:mpp", "language:mps", "language:mpt", "language:mpx", "language:mqb", "language:mqj", "language:msb", "language:msc", "language:msk", "language:msm", "language:msy", "language:mti", "language:mto", "language:mux", "language:muy", "language:mva", "language:mvn", "language:mwc", "language:mwe", "language:mwf", "language:mwp", "language:mxb", "language:mxp", "language:mxq", "language:mxt", "language:mya", "language:myk", "language:myu", "language:myw", "language:myy", "language:mzz", "language:nab", "language:naf", "language:nak", "language:nas", "language:nay", "language:nbq", "language:nca", "language:nch", "language:ncj", "language:ncl", "language:ncu", "language:ndg", "language:ndj", "language:nfa", "language:ngp", "language:ngu", "language:nhe", "language:nhg", "language:nhi", "language:nho", "language:nhr", "language:nhu", "language:nhw", "language:nhy", "language:nif", "language:nii", "language:nin", "language:nko", "language:nld", "language:nlg", "language:nmw", "language:nna", "language:nnq", "language:noa", "language:nop", "language:not", "language:nou", "language:npi", "language:npl", "language:nsn", "language:nss", "language:ntj", "language:ntp", "language:ntu", "language:nuy", "language:nvm", "language:nwi", "language:nya", "language:nys", "language:nyu", "language:obo", "language:okv", "language:omw", "language:ong", "language:ons", "language:ood", "language:opm", "language:ory", "language:ote", "language:otm", "language:otn", "language:otq", "language:ots", "language:pab", "language:pad", "language:pah", "language:pan", "language:pao", "language:pes", "language:pib", "language:pio", "language:pir", "language:piu", "language:pjt", "language:pls", "language:plu", "language:pma", "language:poe", "language:poh", "language:poi", "language:pol", "language:pon", "language:por", "language:poy", "language:ppo", "language:prf", "language:pri", "language:ptp", "language:ptu", "language:pwg", "language:qub", "language:quc", "language:quf", "language:quh", "language:qul", "language:qup", "language:qvc", "language:qve", "language:qvh", "language:qvm", "language:qvn", "language:qvs", "language:qvw", "language:qvz", "language:qwh", "language:qxh", "language:qxn", "language:qxo", "language:rai", "language:reg", "language:rgu", "language:rkb", "language:rmc", "language:rmy", "language:ron", "language:roo", "language:rop", "language:row", "language:rro", "language:ruf", "language:rug", "language:rus", "language:rwo", "language:sab", "language:san", "language:sbe", "language:sbk", "language:sbs", "language:seh", "language:sey", "language:sgb", "language:sgz", "language:shj", "language:shp", "language:sim", "language:sja", "language:sll", "language:smk", "language:snc", "language:snn", "language:snp", "language:snx", "language:sny", "language:som", "language:soq", "language:soy", "language:spa", "language:spl", "language:spm", "language:spp", "language:sps", "language:spy", "language:sri", "language:srm", "language:srn", "language:srp", "language:srq", "language:ssd", "language:ssg", "language:ssx", "language:stp", "language:sua", "language:sue", "language:sus", "language:suz", "language:swe", "language:swh", "language:swp", "language:sxb", "language:tac", "language:taj", "language:tam", "language:tav", "language:taw", "language:tbc", "language:tbf", "language:tbg", "language:tbl", "language:tbo", "language:tbz", "language:tca", "language:tcs", "language:tcz", "language:tdt", "language:tee", "language:tel", "language:ter", "language:tet", "language:tew", "language:tfr", "language:tgk", "language:tgl", "language:tgo", "language:tgp", "language:tha", "language:thd", "language:tif", "language:tim", "language:tiw", "language:tiy", "language:tke", "language:tku", "language:tlf", "language:tmd", "language:tna", "language:tnc", "language:tnk", "language:tnn", "language:tnp", "language:toc", "language:tod", "language:tof", "language:toj", "language:ton", "language:too", "language:top", "language:tos", "language:tpa", "language:tpi", "language:tpt", "language:tpz", "language:trc", "language:tsw", "language:ttc", "language:tte", "language:tuc", "language:tue", "language:tuf", "language:tuo", "language:tur", "language:tvk", "language:twi", "language:txq", "language:txu", "language:tzj", "language:tzo", "language:ubr", "language:ubu", "language:udu", "language:uig", "language:ukr", "language:uli", "language:ulk", "language:upv", "language:ura", "language:urb", "language:urd", "language:uri", "language:urt", "language:urw", "language:usa", "language:usp", "language:uvh", "language:uvl", "language:vid", "language:vie", "language:viv", "language:vmy", "language:waj", "language:wal", "language:wap", "language:wat", "language:wbi", "language:wbp", "language:wed", "language:wer", "language:wim", "language:wiu", "language:wiv", "language:wmt", "language:wmw", "language:wnc", "language:wnu", "language:wol", "language:wos", "language:wrk", "language:wro", "language:wrs", "language:wsk", "language:wuv", "language:xav", "language:xbi", "language:xed", "language:xla", "language:xnn", "language:xon", "language:xsi", "language:xtd", "language:xtm", "language:yaa", "language:yad", "language:yal", "language:yap", "language:yaq", "language:yby", "language:ycn", "language:yka", "language:yle", "language:yml", "language:yon", "language:yor", "language:yrb", "language:yre", "language:yss", "language:yuj", "language:yut", "language:yuw", "language:yva", "language:zaa", "language:zab", "language:zac", "language:zad", "language:zai", "language:zaj", "language:zam", "language:zao", "language:zap", "language:zar", "language:zas", "language:zat", "language:zav", "language:zaw", "language:zca", "language:zga", "language:zia", "language:ziw", "language:zlm", "language:zos", "language:zpc", "language:zpl", "language:zpm", "language:zpo", "language:zpq", "language:zpu", "language:zpv", "language:zpz", "language:zsr", "language:ztq", "language:zty", "language:zyp", "language:be", "language:br", "language:cs", "language:ch", "language:zh", "language:de", "language:en", "language:eo", "language:fr", "language:ht", "language:he", "language:hr", "language:id", "language:it", "language:ja", "language:la", "language:nl", "language:ru", "language:sa", "language:so", "language:es", "language:sr", "language:sv", "language:to", "language:uk", "language:vi", "license:cc-by-4.0", "license:other", "size_categories:1M<n<10M", "format:json", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "region:us" ]

null

"2024-05-05T22:41:26Z"

--- annotations_creators: - no-annotation language_creators: - expert-generated language: - aai - aak - aau - aaz - abt - abx - aby - acf - acr - acu - adz - aer - aey - agd - agg - agm - agn - agr - agt - agu - aia - aii - aka - ake - alp - alq - als - aly - ame - amf - amk - amm - amn - amo - amp - amr - amu - amx - anh - anv - aoi - aoj - aom - aon - apb - ape - apn - apr - apu - apw - apz - arb - are - arl - arn - arp - asm - aso - ata - atb - atd - atg - att - auc - aui - auy - avt - awb - awk - awx - azb - azg - azz - bao - bba - bbb - bbr - bch - bco - bdd - bea - bef - bel - ben - beo - beu - bgs - bgt - bhg - bhl - big - bjk - bjp - bjr - bjv - bjz - bkd - bki - bkq - bkx - bla - blw - blz - bmh - bmk - bmr - bmu - bnp - boa - boj - bon - box - bpr - bps - bqc - bqp - bre - bsj - bsn - bsp - bss - buk - bus - bvd - bvr - bxh - byr - byx - bzd - bzh - bzj - caa - cab - cac - caf - cak - cao - cap - car - cav - cax - cbc - cbi - cbk - cbr - cbs - cbt - cbu - cbv - cco - ceb - cek - ces - cgc - cha - chd - chf - chk - chq - chz - cjo - cjv - ckb - cle - clu - cme - cmn - cni - cnl - cnt - cof - con - cop - cot - cpa - cpb - cpc - cpu - cpy - crn - crx - cso - csy - cta - cth - ctp - ctu - cub - cuc - cui - cuk - cut - cux - cwe - cya - daa - dad - dah - dan - ded - deu - dgc - dgr - dgz - dhg - dif - dik - dji - djk - djr - dob - dop - dov - dwr - dww - dwy - ebk - eko - emi - emp - eng - enq - epo - eri - ese - esk - etr - ewe - faa - fai - far - ffm - for - fra - fue - fuf - fuh - gah - gai - gam - gaw - gdn - gdr - geb - gfk - ghs - glk - gmv - gng - gnn - gnw - gof - grc - gub - guh - gui - guj - gul - gum - gun - guo - gup - gux - gvc - gvf - gvn - gvs - gwi - gym - gyr - hat - hau - haw - hbo - hch - heb - heg - hin - hix - hla - hlt - hmo - hns - hop - hot - hrv - hto - hub - hui - hun - hus - huu - huv - hvn - ian - ign - ikk - ikw - ilo - imo - inb - ind - ino - iou - ipi - isn - ita - iws - ixl - jac - jae - jao - jic - jid - jiv - jni - jpn - jvn - kan - kaq - kbc - kbh - kbm - kbq - kdc - kde - kdl - kek - ken - kew - kgf - kgk - kgp - khs - khz - kik - kiw - kiz - kje - kjn - kjs - kkc - kkl - klt - klv - kmg - kmh - kmk - kmo - kms - kmu - kne - knf - knj - knv - kos - kpf - kpg - kpj - kpr - kpw - kpx - kqa - kqc - kqf - kql - kqw - ksd - ksj - ksr - ktm - kto - kud - kue - kup - kvg - kvn - kwd - kwf - kwi - kwj - kyc - kyf - kyg - kyq - kyz - kze - lac - lat - lbb - lbk - lcm - leu - lex - lgl - lid - lif - lin - lit - llg - lug - luo - lww - maa - maj - mal - mam - maq - mar - mau - mav - maz - mbb - mbc - mbh - mbj - mbl - mbs - mbt - mca - mcb - mcd - mcf - mco - mcp - mcq - mcr - mdy - med - mee - mek - meq - met - meu - mgc - mgh - mgw - mhl - mib - mic - mie - mig - mih - mil - mio - mir - mit - miz - mjc - mkj - mkl - mkn - mks - mle - mlh - mlp - mmo - mmx - mna - mop - mox - mph - mpj - mpm - mpp - mps - mpt - mpx - mqb - mqj - msb - msc - msk - msm - msy - mti - mto - mux - muy - mva - mvn - mwc - mwe - mwf - mwp - mxb - mxp - mxq - mxt - mya - myk - myu - myw - myy - mzz - nab - naf - nak - nas - nay - nbq - nca - nch - ncj - ncl - ncu - ndg - ndj - nfa - ngp - ngu - nhe - nhg - nhi - nho - nhr - nhu - nhw - nhy - nif - nii - nin - nko - nld - nlg - nmw - nna - nnq - noa - nop - not - nou - npi - npl - nsn - nss - ntj - ntp - ntu - nuy - nvm - nwi - nya - nys - nyu - obo - okv - omw - ong - ons - ood - opm - ory - ote - otm - otn - otq - ots - pab - pad - pah - pan - pao - pes - pib - pio - pir - piu - pjt - pls - plu - pma - poe - poh - poi - pol - pon - por - poy - ppo - prf - pri - ptp - ptu - pwg - qub - quc - quf - quh - qul - qup - qvc - qve - qvh - qvm - qvn - qvs - qvw - qvz - qwh - qxh - qxn - qxo - rai - reg - rgu - rkb - rmc - rmy - ron - roo - rop - row - rro - ruf - rug - rus - rwo - sab - san - sbe - sbk - sbs - seh - sey - sgb - sgz - shj - shp - sim - sja - sll - smk - snc - snn - snp - snx - sny - som - soq - soy - spa - spl - spm - spp - sps - spy - sri - srm - srn - srp - srq - ssd - ssg - ssx - stp - sua - sue - sus - suz - swe - swh - swp - sxb - tac - taj - tam - tav - taw - tbc - tbf - tbg - tbl - tbo - tbz - tca - tcs - tcz - tdt - tee - tel - ter - tet - tew - tfr - tgk - tgl - tgo - tgp - tha - thd - tif - tim - tiw - tiy - tke - tku - tlf - tmd - tna - tnc - tnk - tnn - tnp - toc - tod - tof - toj - ton - too - top - tos - tpa - tpi - tpt - tpz - trc - tsw - ttc - tte - tuc - tue - tuf - tuo - tur - tvk - twi - txq - txu - tzj - tzo - ubr - ubu - udu - uig - ukr - uli - ulk - upv - ura - urb - urd - uri - urt - urw - usa - usp - uvh - uvl - vid - vie - viv - vmy - waj - wal - wap - wat - wbi - wbp - wed - wer - wim - wiu - wiv - wmt - wmw - wnc - wnu - wol - wos - wrk - wro - wrs - wsk - wuv - xav - xbi - xed - xla - xnn - xon - xsi - xtd - xtm - yaa - yad - yal - yap - yaq - yby - ycn - yka - yle - yml - yon - yor - yrb - yre - yss - yuj - yut - yuw - yva - zaa - zab - zac - zad - zai - zaj - zam - zao - zap - zar - zas - zat - zav - zaw - zca - zga - zia - ziw - zlm - zos - zpc - zpl - zpm - zpo - zpq - zpu - zpv - zpz - zsr - ztq - zty - zyp - be - br - cs - ch - zh - de - en - eo - fr - ht - he - hr - id - it - ja - la - nl - ru - sa - so - es - sr - sv - to - uk - vi license: - cc-by-4.0 - other multilinguality: - translation - multilingual pretty_name: biblenlp-corpus-mmteb size_categories: - 1M<n<10M configs: - config_name: default data_files: - path: train/*.jsonl.gz split: train - path: test/*.jsonl.gz split: test - path: validation/*.jsonl.gz split: validation - config_name: eng_Latn-zac_Latn data_files: - path: train/eng_Latn-zac_Latn.jsonl.gz split: train - path: test/eng_Latn-zac_Latn.jsonl.gz split: test - path: validation/eng_Latn-zac_Latn.jsonl.gz split: validation - config_name: eng_Latn-lit_Latn data_files: - path: train/eng_Latn-lit_Latn.jsonl.gz split: train - path: test/eng_Latn-lit_Latn.jsonl.gz split: test - path: validation/eng_Latn-lit_Latn.jsonl.gz split: validation - config_name: eng_Latn-cgc_Latn data_files: - path: train/eng_Latn-cgc_Latn.jsonl.gz split: train - path: test/eng_Latn-cgc_Latn.jsonl.gz split: test - path: validation/eng_Latn-cgc_Latn.jsonl.gz split: validation - config_name: eng_Latn-guh_Latn data_files: - path: train/eng_Latn-guh_Latn.jsonl.gz split: train - path: test/eng_Latn-guh_Latn.jsonl.gz split: test - path: validation/eng_Latn-guh_Latn.jsonl.gz split: validation - config_name: eng_Latn-ckb_Arab data_files: - path: train/eng_Latn-ckb_Arab.jsonl.gz split: train - path: test/eng_Latn-ckb_Arab.jsonl.gz split: test - path: validation/eng_Latn-ckb_Arab.jsonl.gz split: validation - config_name: eng_Latn-cop_Copt data_files: - path: train/eng_Latn-cop_Copt.jsonl.gz split: train - path: test/eng_Latn-cop_Copt.jsonl.gz split: test - path: validation/eng_Latn-cop_Copt.jsonl.gz split: validation - config_name: eng_Latn-lif_Deva data_files: - path: train/eng_Latn-lif_Deva.jsonl.gz split: train - path: test/eng_Latn-lif_Deva.jsonl.gz split: test - path: validation/eng_Latn-lif_Deva.jsonl.gz split: validation - config_name: eng_Latn-cwe_Latn data_files: - path: train/eng_Latn-cwe_Latn.jsonl.gz split: train - path: test/eng_Latn-cwe_Latn.jsonl.gz split: test - path: validation/eng_Latn-cwe_Latn.jsonl.gz split: validation - config_name: eng_Latn-kwj_Latn data_files: - path: train/eng_Latn-kwj_Latn.jsonl.gz split: train - path: test/eng_Latn-kwj_Latn.jsonl.gz split: test - path: validation/eng_Latn-kwj_Latn.jsonl.gz split: validation - config_name: eng_Latn-srp_Latn data_files: - path: train/eng_Latn-srp_Latn.jsonl.gz split: train - path: test/eng_Latn-srp_Latn.jsonl.gz split: test - path: validation/eng_Latn-srp_Latn.jsonl.gz split: validation - config_name: eng_Latn-qvn_Latn data_files: - path: train/eng_Latn-qvn_Latn.jsonl.gz split: train - path: test/eng_Latn-qvn_Latn.jsonl.gz split: test - path: validation/eng_Latn-qvn_Latn.jsonl.gz split: validation - config_name: eng_Latn-tsw_Latn data_files: - path: train/eng_Latn-tsw_Latn.jsonl.gz split: train - path: test/eng_Latn-tsw_Latn.jsonl.gz split: test - path: validation/eng_Latn-tsw_Latn.jsonl.gz split: validation - config_name: eng_Latn-wro_Latn data_files: - path: train/eng_Latn-wro_Latn.jsonl.gz split: train - path: test/eng_Latn-wro_Latn.jsonl.gz split: test - path: validation/eng_Latn-wro_Latn.jsonl.gz split: validation - config_name: eng_Latn-tod_Latn data_files: - path: train/eng_Latn-tod_Latn.jsonl.gz split: train - path: test/eng_Latn-tod_Latn.jsonl.gz split: test - path: validation/eng_Latn-tod_Latn.jsonl.gz split: validation - config_name: eng_Latn-bco_Latn data_files: - path: train/eng_Latn-bco_Latn.jsonl.gz split: train - path: test/eng_Latn-bco_Latn.jsonl.gz split: test - path: validation/eng_Latn-bco_Latn.jsonl.gz split: validation - config_name: eng_Latn-ikk_Latn data_files: - path: train/eng_Latn-ikk_Latn.jsonl.gz split: train - path: test/eng_Latn-ikk_Latn.jsonl.gz split: test - path: validation/eng_Latn-ikk_Latn.jsonl.gz split: validation - config_name: eng_Latn-tna_Latn data_files: - path: train/eng_Latn-tna_Latn.jsonl.gz split: train - path: test/eng_Latn-tna_Latn.jsonl.gz split: test - path: validation/eng_Latn-tna_Latn.jsonl.gz split: validation - config_name: eng_Latn-swp_Latn data_files: - path: train/eng_Latn-swp_Latn.jsonl.gz split: train - path: test/eng_Latn-swp_Latn.jsonl.gz split: test - path: validation/eng_Latn-swp_Latn.jsonl.gz split: validation - config_name: eng_Latn-agm_Latn data_files: - path: train/eng_Latn-agm_Latn.jsonl.gz split: train - path: test/eng_Latn-agm_Latn.jsonl.gz split: test - path: validation/eng_Latn-agm_Latn.jsonl.gz split: validation - config_name: eng_Latn-con_Latn data_files: - path: train/eng_Latn-con_Latn.jsonl.gz split: train - path: test/eng_Latn-con_Latn.jsonl.gz split: test - path: validation/eng_Latn-con_Latn.jsonl.gz split: validation - config_name: eng_Latn-sgz_Latn data_files: - path: train/eng_Latn-sgz_Latn.jsonl.gz split: train - path: test/eng_Latn-sgz_Latn.jsonl.gz split: test - path: validation/eng_Latn-sgz_Latn.jsonl.gz split: validation - config_name: eng_Latn-mwc_Latn data_files: - path: train/eng_Latn-mwc_Latn.jsonl.gz split: train - path: test/eng_Latn-mwc_Latn.jsonl.gz split: test - path: validation/eng_Latn-mwc_Latn.jsonl.gz split: validation - config_name: eng_Latn-azb_Arab data_files: - path: train/eng_Latn-azb_Arab.jsonl.gz split: train - path: test/eng_Latn-azb_Arab.jsonl.gz split: test - path: validation/eng_Latn-azb_Arab.jsonl.gz split: validation - config_name: eng_Latn-aon_Latn data_files: - path: train/eng_Latn-aon_Latn.jsonl.gz split: train - path: test/eng_Latn-aon_Latn.jsonl.gz split: test - path: validation/eng_Latn-aon_Latn.jsonl.gz split: validation - config_name: eng_Latn-mvn_Latn data_files: - path: train/eng_Latn-mvn_Latn.jsonl.gz split: train - path: test/eng_Latn-mvn_Latn.jsonl.gz split: test - path: validation/eng_Latn-mvn_Latn.jsonl.gz split: validation - config_name: eng_Latn-mpj_Latn data_files: - path: train/eng_Latn-mpj_Latn.jsonl.gz split: train - path: test/eng_Latn-mpj_Latn.jsonl.gz split: test - path: validation/eng_Latn-mpj_Latn.jsonl.gz split: validation - config_name: eng_Latn-cot_Latn data_files: - path: train/eng_Latn-cot_Latn.jsonl.gz split: train - path: test/eng_Latn-cot_Latn.jsonl.gz split: test - path: validation/eng_Latn-cot_Latn.jsonl.gz split: validation - config_name: eng_Latn-tuo_Latn data_files: - path: train/eng_Latn-tuo_Latn.jsonl.gz split: train - path: test/eng_Latn-tuo_Latn.jsonl.gz split: test - path: validation/eng_Latn-tuo_Latn.jsonl.gz split: validation - config_name: eng_Latn-iou_Latn data_files: - path: train/eng_Latn-iou_Latn.jsonl.gz split: train - path: test/eng_Latn-iou_Latn.jsonl.gz split: test - path: validation/eng_Latn-iou_Latn.jsonl.gz split: validation - config_name: eng_Latn-big_Latn data_files: - path: train/eng_Latn-big_Latn.jsonl.gz split: train - path: test/eng_Latn-big_Latn.jsonl.gz split: test - path: validation/eng_Latn-big_Latn.jsonl.gz split: validation - config_name: eng_Latn-apw_Latn data_files: - path: train/eng_Latn-apw_Latn.jsonl.gz split: train - path: test/eng_Latn-apw_Latn.jsonl.gz split: test - path: validation/eng_Latn-apw_Latn.jsonl.gz split: validation - config_name: eng_Latn-kpx_Latn data_files: - path: train/eng_Latn-kpx_Latn.jsonl.gz split: train - path: test/eng_Latn-kpx_Latn.jsonl.gz split: test - path: validation/eng_Latn-kpx_Latn.jsonl.gz split: validation - config_name: eng_Latn-cui_Latn data_files: - path: train/eng_Latn-cui_Latn.jsonl.gz split: train - path: test/eng_Latn-cui_Latn.jsonl.gz split: test - path: validation/eng_Latn-cui_Latn.jsonl.gz split: validation - config_name: eng_Latn-bnp_Latn data_files: - path: train/eng_Latn-bnp_Latn.jsonl.gz split: train - path: test/eng_Latn-bnp_Latn.jsonl.gz split: test - path: validation/eng_Latn-bnp_Latn.jsonl.gz split: validation - config_name: eng_Latn-ngp_Latn data_files: - path: train/eng_Latn-ngp_Latn.jsonl.gz split: train - path: test/eng_Latn-ngp_Latn.jsonl.gz split: test - path: validation/eng_Latn-ngp_Latn.jsonl.gz split: validation - config_name: eng_Latn-mkj_Latn data_files: - path: train/eng_Latn-mkj_Latn.jsonl.gz split: train - path: test/eng_Latn-mkj_Latn.jsonl.gz split: test - path: validation/eng_Latn-mkj_Latn.jsonl.gz split: validation - config_name: eng_Latn-chf_Latn data_files: - path: train/eng_Latn-chf_Latn.jsonl.gz split: train - path: test/eng_Latn-chf_Latn.jsonl.gz split: test - path: validation/eng_Latn-chf_Latn.jsonl.gz split: validation - config_name: eng_Latn-tca_Latn data_files: - path: train/eng_Latn-tca_Latn.jsonl.gz split: train - path: test/eng_Latn-tca_Latn.jsonl.gz split: test - path: validation/eng_Latn-tca_Latn.jsonl.gz split: validation - config_name: eng_Latn-poh_Latn data_files: - path: train/eng_Latn-poh_Latn.jsonl.gz split: train - path: test/eng_Latn-poh_Latn.jsonl.gz split: test - path: validation/eng_Latn-poh_Latn.jsonl.gz split: validation - config_name: eng_Latn-ese_Latn data_files: - path: train/eng_Latn-ese_Latn.jsonl.gz split: train - path: test/eng_Latn-ese_Latn.jsonl.gz split: test - path: validation/eng_Latn-ese_Latn.jsonl.gz split: validation - config_name: eng_Latn-plu_Latn data_files: - path: train/eng_Latn-plu_Latn.jsonl.gz split: train - path: test/eng_Latn-plu_Latn.jsonl.gz split: test - path: validation/eng_Latn-plu_Latn.jsonl.gz split: validation - config_name: eng_Latn-crn_Latn data_files: - path: train/eng_Latn-crn_Latn.jsonl.gz split: train - path: test/eng_Latn-crn_Latn.jsonl.gz split: test - path: validation/eng_Latn-crn_Latn.jsonl.gz split: validation - config_name: eng_Latn-mxt_Latn data_files: - path: train/eng_Latn-mxt_Latn.jsonl.gz split: train - path: test/eng_Latn-mxt_Latn.jsonl.gz split: test - path: validation/eng_Latn-mxt_Latn.jsonl.gz split: validation - config_name: eng_Latn-tnk_Latn data_files: - path: train/eng_Latn-tnk_Latn.jsonl.gz split: train - path: test/eng_Latn-tnk_Latn.jsonl.gz split: test - path: validation/eng_Latn-tnk_Latn.jsonl.gz split: validation - config_name: eng_Latn-zar_Latn data_files: - path: train/eng_Latn-zar_Latn.jsonl.gz split: train - path: test/eng_Latn-zar_Latn.jsonl.gz split: test - path: validation/eng_Latn-zar_Latn.jsonl.gz split: validation - config_name: eng_Latn-sri_Latn data_files: - path: train/eng_Latn-sri_Latn.jsonl.gz split: train - path: test/eng_Latn-sri_Latn.jsonl.gz split: test - path: validation/eng_Latn-sri_Latn.jsonl.gz split: validation - config_name: eng_Latn-pan_Guru data_files: - path: train/eng_Latn-pan_Guru.jsonl.gz split: train - path: test/eng_Latn-pan_Guru.jsonl.gz split: test - path: validation/eng_Latn-pan_Guru.jsonl.gz split: validation - config_name: eng_Latn-kik_Latn data_files: - path: train/eng_Latn-kik_Latn.jsonl.gz split: train - path: test/eng_Latn-kik_Latn.jsonl.gz split: test - path: validation/eng_Latn-kik_Latn.jsonl.gz split: validation - config_name: eng_Latn-yby_Latn data_files: - path: train/eng_Latn-yby_Latn.jsonl.gz split: train - path: test/eng_Latn-yby_Latn.jsonl.gz split: test - path: validation/eng_Latn-yby_Latn.jsonl.gz split: validation - config_name: eng_Latn-qup_Latn data_files: - path: train/eng_Latn-qup_Latn.jsonl.gz split: train - path: test/eng_Latn-qup_Latn.jsonl.gz split: test - path: validation/eng_Latn-qup_Latn.jsonl.gz split: validation - config_name: eng_Latn-mco_Latn data_files: - path: train/eng_Latn-mco_Latn.jsonl.gz split: train - path: test/eng_Latn-mco_Latn.jsonl.gz split: test - path: validation/eng_Latn-mco_Latn.jsonl.gz split: validation - config_name: eng_Latn-gux_Latn data_files: - path: train/eng_Latn-gux_Latn.jsonl.gz split: train - path: test/eng_Latn-gux_Latn.jsonl.gz split: test - path: validation/eng_Latn-gux_Latn.jsonl.gz split: validation - config_name: eng_Latn-spa_Latn data_files: - path: train/eng_Latn-spa_Latn.jsonl.gz split: train - path: test/eng_Latn-spa_Latn.jsonl.gz split: test - path: validation/eng_Latn-spa_Latn.jsonl.gz split: validation - config_name: eng_Latn-heg_Latn data_files: - path: train/eng_Latn-heg_Latn.jsonl.gz split: train - path: test/eng_Latn-heg_Latn.jsonl.gz split: test - path: validation/eng_Latn-heg_Latn.jsonl.gz split: validation - config_name: eng_Latn-gwi_Latn data_files: - path: train/eng_Latn-gwi_Latn.jsonl.gz split: train - path: test/eng_Latn-gwi_Latn.jsonl.gz split: test - path: validation/eng_Latn-gwi_Latn.jsonl.gz split: validation - config_name: eng_Latn-ttc_Latn data_files: - path: train/eng_Latn-ttc_Latn.jsonl.gz split: train - path: test/eng_Latn-ttc_Latn.jsonl.gz split: test - path: validation/eng_Latn-ttc_Latn.jsonl.gz split: validation - config_name: eng_Latn-mqj_Latn data_files: - path: train/eng_Latn-mqj_Latn.jsonl.gz split: train - path: test/eng_Latn-mqj_Latn.jsonl.gz split: test - path: validation/eng_Latn-mqj_Latn.jsonl.gz split: validation - config_name: eng_Latn-pjt_Latn data_files: - path: train/eng_Latn-pjt_Latn.jsonl.gz split: train - path: test/eng_Latn-pjt_Latn.jsonl.gz split: test - path: validation/eng_Latn-pjt_Latn.jsonl.gz split: validation - config_name: eng_Latn-gui_Latn data_files: - path: train/eng_Latn-gui_Latn.jsonl.gz split: train - path: test/eng_Latn-gui_Latn.jsonl.gz split: test - path: validation/eng_Latn-gui_Latn.jsonl.gz split: validation - config_name: eng_Latn-tel_Telu data_files: - path: train/eng_Latn-tel_Telu.jsonl.gz split: train - path: test/eng_Latn-tel_Telu.jsonl.gz split: test - path: validation/eng_Latn-tel_Telu.jsonl.gz split: validation - config_name: eng_Latn-lbb_Latn data_files: - path: train/eng_Latn-lbb_Latn.jsonl.gz split: train - path: test/eng_Latn-lbb_Latn.jsonl.gz split: test - path: validation/eng_Latn-lbb_Latn.jsonl.gz split: validation - config_name: eng_Latn-cbr_Latn data_files: - path: train/eng_Latn-cbr_Latn.jsonl.gz split: train - path: test/eng_Latn-cbr_Latn.jsonl.gz split: test - path: validation/eng_Latn-cbr_Latn.jsonl.gz split: validation - config_name: eng_Latn-jvn_Latn data_files: - path: train/eng_Latn-jvn_Latn.jsonl.gz split: train - path: test/eng_Latn-jvn_Latn.jsonl.gz split: test - path: validation/eng_Latn-jvn_Latn.jsonl.gz split: validation - config_name: eng_Latn-huu_Latn data_files: - path: train/eng_Latn-huu_Latn.jsonl.gz split: train - path: test/eng_Latn-huu_Latn.jsonl.gz split: test - path: validation/eng_Latn-huu_Latn.jsonl.gz split: validation - config_name: eng_Latn-kyq_Latn data_files: - path: train/eng_Latn-kyq_Latn.jsonl.gz split: train - path: test/eng_Latn-kyq_Latn.jsonl.gz split: test - path: validation/eng_Latn-kyq_Latn.jsonl.gz split: validation - config_name: eng_Latn-lex_Latn data_files: - path: train/eng_Latn-lex_Latn.jsonl.gz split: train - path: test/eng_Latn-lex_Latn.jsonl.gz split: test - path: validation/eng_Latn-lex_Latn.jsonl.gz split: validation - config_name: eng_Latn-lug_Latn data_files: - path: train/eng_Latn-lug_Latn.jsonl.gz split: train - path: test/eng_Latn-lug_Latn.jsonl.gz split: test - path: validation/eng_Latn-lug_Latn.jsonl.gz split: validation - config_name: eng_Latn-tbc_Latn data_files: - path: train/eng_Latn-tbc_Latn.jsonl.gz split: train - path: test/eng_Latn-tbc_Latn.jsonl.gz split: test - path: validation/eng_Latn-tbc_Latn.jsonl.gz split: validation - config_name: eng_Latn-srm_Latn data_files: - path: train/eng_Latn-srm_Latn.jsonl.gz split: train - path: test/eng_Latn-srm_Latn.jsonl.gz split: test - path: validation/eng_Latn-srm_Latn.jsonl.gz split: validation - config_name: eng_Latn-ztq_Latn data_files: - path: train/eng_Latn-ztq_Latn.jsonl.gz split: train - path: test/eng_Latn-ztq_Latn.jsonl.gz split: test - path: validation/eng_Latn-ztq_Latn.jsonl.gz split: validation - config_name: eng_Latn-clu_Latn data_files: - path: train/eng_Latn-clu_Latn.jsonl.gz split: train - path: test/eng_Latn-clu_Latn.jsonl.gz split: test - path: validation/eng_Latn-clu_Latn.jsonl.gz split: validation - config_name: eng_Latn-wol_Latn data_files: - path: train/eng_Latn-wol_Latn.jsonl.gz split: train - path: test/eng_Latn-wol_Latn.jsonl.gz split: test - path: validation/eng_Latn-wol_Latn.jsonl.gz split: validation - config_name: eng_Latn-wrk_Latn data_files: - path: train/eng_Latn-wrk_Latn.jsonl.gz split: train - path: test/eng_Latn-wrk_Latn.jsonl.gz split: test - path: validation/eng_Latn-wrk_Latn.jsonl.gz split: validation - config_name: eng_Latn-ssg_Latn data_files: - path: train/eng_Latn-ssg_Latn.jsonl.gz split: train - path: test/eng_Latn-ssg_Latn.jsonl.gz split: test - path: validation/eng_Latn-ssg_Latn.jsonl.gz split: validation - config_name: eng_Latn-tha_Thai data_files: - path: train/eng_Latn-tha_Thai.jsonl.gz split: train - path: test/eng_Latn-tha_Thai.jsonl.gz split: test - path: validation/eng_Latn-tha_Thai.jsonl.gz split: validation - config_name: eng_Latn-gub_Latn data_files: - path: train/eng_Latn-gub_Latn.jsonl.gz split: train - path: test/eng_Latn-gub_Latn.jsonl.gz split: test - path: validation/eng_Latn-gub_Latn.jsonl.gz split: validation - config_name: eng_Latn-rop_Latn data_files: - path: train/eng_Latn-rop_Latn.jsonl.gz split: train - path: test/eng_Latn-rop_Latn.jsonl.gz split: test - path: validation/eng_Latn-rop_Latn.jsonl.gz split: validation - config_name: eng_Latn-ind_Latn data_files: - path: train/eng_Latn-ind_Latn.jsonl.gz split: train - path: test/eng_Latn-ind_Latn.jsonl.gz split: test - path: validation/eng_Latn-ind_Latn.jsonl.gz split: validation - config_name: eng_Latn-urb_Latn data_files: - path: train/eng_Latn-urb_Latn.jsonl.gz split: train - path: test/eng_Latn-urb_Latn.jsonl.gz split: test - path: validation/eng_Latn-urb_Latn.jsonl.gz split: validation - config_name: eng_Latn-ziw_Latn data_files: - path: train/eng_Latn-ziw_Latn.jsonl.gz split: train - path: test/eng_Latn-ziw_Latn.jsonl.gz split: test - path: validation/eng_Latn-ziw_Latn.jsonl.gz split: validation - config_name: eng_Latn-waj_Latn data_files: - path: train/eng_Latn-waj_Latn.jsonl.gz split: train - path: test/eng_Latn-waj_Latn.jsonl.gz split: test - path: validation/eng_Latn-waj_Latn.jsonl.gz split: validation - config_name: eng_Latn-tku_Latn data_files: - path: train/eng_Latn-tku_Latn.jsonl.gz split: train - path: test/eng_Latn-tku_Latn.jsonl.gz split: test - path: validation/eng_Latn-tku_Latn.jsonl.gz split: validation - config_name: eng_Latn-pao_Latn data_files: - path: train/eng_Latn-pao_Latn.jsonl.gz split: train - path: test/eng_Latn-pao_Latn.jsonl.gz split: test - path: validation/eng_Latn-pao_Latn.jsonl.gz split: validation - config_name: eng_Latn-tet_Latn data_files: - path: train/eng_Latn-tet_Latn.jsonl.gz split: train - path: test/eng_Latn-tet_Latn.jsonl.gz split: test - path: validation/eng_Latn-tet_Latn.jsonl.gz split: validation - config_name: eng_Latn-msc_Latn data_files: - path: train/eng_Latn-msc_Latn.jsonl.gz split: train - path: test/eng_Latn-msc_Latn.jsonl.gz split: test - path: validation/eng_Latn-msc_Latn.jsonl.gz split: validation - config_name: eng_Latn-wal_Ethi data_files: - path: train/eng_Latn-wal_Ethi.jsonl.gz split: train - path: test/eng_Latn-wal_Ethi.jsonl.gz split: test - path: validation/eng_Latn-wal_Ethi.jsonl.gz split: validation - config_name: eng_Latn-bmu_Latn data_files: - path: train/eng_Latn-bmu_Latn.jsonl.gz split: train - path: test/eng_Latn-bmu_Latn.jsonl.gz split: test - path: validation/eng_Latn-bmu_Latn.jsonl.gz split: validation - config_name: eng_Latn-yaq_Latn data_files: - path: train/eng_Latn-yaq_Latn.jsonl.gz split: train - path: test/eng_Latn-yaq_Latn.jsonl.gz split: test - path: validation/eng_Latn-yaq_Latn.jsonl.gz split: validation - config_name: eng_Latn-bgt_Latn data_files: - path: train/eng_Latn-bgt_Latn.jsonl.gz split: train - path: test/eng_Latn-bgt_Latn.jsonl.gz split: test - path: validation/eng_Latn-bgt_Latn.jsonl.gz split: validation - config_name: eng_Latn-atb_Latn data_files: - path: train/eng_Latn-atb_Latn.jsonl.gz split: train - path: test/eng_Latn-atb_Latn.jsonl.gz split: test - path: validation/eng_Latn-atb_Latn.jsonl.gz split: validation - config_name: eng_Latn-apn_Latn data_files: - path: train/eng_Latn-apn_Latn.jsonl.gz split: train - path: test/eng_Latn-apn_Latn.jsonl.gz split: test - path: validation/eng_Latn-apn_Latn.jsonl.gz split: validation - config_name: eng_Latn-por_Latn data_files: - path: train/eng_Latn-por_Latn.jsonl.gz split: train - path: test/eng_Latn-por_Latn.jsonl.gz split: test - path: validation/eng_Latn-por_Latn.jsonl.gz split: validation - config_name: eng_Latn-quf_Latn data_files: - path: train/eng_Latn-quf_Latn.jsonl.gz split: train - path: test/eng_Latn-quf_Latn.jsonl.gz split: test - path: validation/eng_Latn-quf_Latn.jsonl.gz split: validation - config_name: eng_Latn-prf_Latn data_files: - path: train/eng_Latn-prf_Latn.jsonl.gz split: train - path: test/eng_Latn-prf_Latn.jsonl.gz split: test - path: validation/eng_Latn-prf_Latn.jsonl.gz split: validation - config_name: eng_Latn-ndj_Latn data_files: - path: train/eng_Latn-ndj_Latn.jsonl.gz split: train - path: test/eng_Latn-ndj_Latn.jsonl.gz split: test - path: validation/eng_Latn-ndj_Latn.jsonl.gz split: validation - config_name: eng_Latn-hub_Latn data_files: - path: train/eng_Latn-hub_Latn.jsonl.gz split: train - path: test/eng_Latn-hub_Latn.jsonl.gz split: test - path: validation/eng_Latn-hub_Latn.jsonl.gz split: validation - config_name: eng_Latn-kvn_Latn data_files: - path: train/eng_Latn-kvn_Latn.jsonl.gz split: train - path: test/eng_Latn-kvn_Latn.jsonl.gz split: test - path: validation/eng_Latn-kvn_Latn.jsonl.gz split: validation - config_name: eng_Latn-swe_Latn data_files: - path: train/eng_Latn-swe_Latn.jsonl.gz split: train - path: test/eng_Latn-swe_Latn.jsonl.gz split: test - path: validation/eng_Latn-swe_Latn.jsonl.gz split: validation - config_name: eng_Latn-xtd_Latn data_files: - path: train/eng_Latn-xtd_Latn.jsonl.gz split: train - path: test/eng_Latn-xtd_Latn.jsonl.gz split: test - path: validation/eng_Latn-xtd_Latn.jsonl.gz split: validation - config_name: eng_Latn-blz_Latn data_files: - path: train/eng_Latn-blz_Latn.jsonl.gz split: train - path: test/eng_Latn-blz_Latn.jsonl.gz split: test - path: validation/eng_Latn-blz_Latn.jsonl.gz split: validation - config_name: eng_Latn-arb_Arab data_files: - path: train/eng_Latn-arb_Arab.jsonl.gz split: train - path: test/eng_Latn-arb_Arab.jsonl.gz split: test - path: validation/eng_Latn-arb_Arab.jsonl.gz split: validation - config_name: eng_Latn-gdr_Latn data_files: - path: train/eng_Latn-gdr_Latn.jsonl.gz split: train - path: test/eng_Latn-gdr_Latn.jsonl.gz split: test - path: validation/eng_Latn-gdr_Latn.jsonl.gz split: validation - config_name: eng_Latn-ksd_Latn data_files: - path: train/eng_Latn-ksd_Latn.jsonl.gz split: train - path: test/eng_Latn-ksd_Latn.jsonl.gz split: test - path: validation/eng_Latn-ksd_Latn.jsonl.gz split: validation - config_name: eng_Latn-toj_Latn data_files: - path: train/eng_Latn-toj_Latn.jsonl.gz split: train - path: test/eng_Latn-toj_Latn.jsonl.gz split: test - path: validation/eng_Latn-toj_Latn.jsonl.gz split: validation - config_name: eng_Latn-arp_Latn data_files: - path: train/eng_Latn-arp_Latn.jsonl.gz split: train - path: test/eng_Latn-arp_Latn.jsonl.gz split: test - path: validation/eng_Latn-arp_Latn.jsonl.gz split: validation - config_name: eng_Latn-cnt_Latn data_files: - path: train/eng_Latn-cnt_Latn.jsonl.gz split: train - path: test/eng_Latn-cnt_Latn.jsonl.gz split: test - path: validation/eng_Latn-cnt_Latn.jsonl.gz split: validation - config_name: eng_Latn-aoj_Latn data_files: - path: train/eng_Latn-aoj_Latn.jsonl.gz split: train - path: test/eng_Latn-aoj_Latn.jsonl.gz split: test - path: validation/eng_Latn-aoj_Latn.jsonl.gz split: validation - config_name: eng_Latn-fai_Latn data_files: - path: train/eng_Latn-fai_Latn.jsonl.gz split: train - path: test/eng_Latn-fai_Latn.jsonl.gz split: test - path: validation/eng_Latn-fai_Latn.jsonl.gz split: validation - config_name: eng_Latn-far_Latn data_files: - path: train/eng_Latn-far_Latn.jsonl.gz split: train - path: test/eng_Latn-far_Latn.jsonl.gz split: test - path: validation/eng_Latn-far_Latn.jsonl.gz split: validation - config_name: eng_Latn-ons_Latn data_files: - path: train/eng_Latn-ons_Latn.jsonl.gz split: train - path: test/eng_Latn-ons_Latn.jsonl.gz split: test - path: validation/eng_Latn-ons_Latn.jsonl.gz split: validation - config_name: eng_Latn-emi_Latn data_files: - path: train/eng_Latn-emi_Latn.jsonl.gz split: train - path: test/eng_Latn-emi_Latn.jsonl.gz split: test - path: validation/eng_Latn-emi_Latn.jsonl.gz split: validation - config_name: eng_Latn-yre_Latn data_files: - path: train/eng_Latn-yre_Latn.jsonl.gz split: train - path: test/eng_Latn-yre_Latn.jsonl.gz split: test - path: validation/eng_Latn-yre_Latn.jsonl.gz split: validation - config_name: eng_Latn-zpz_Latn data_files: - path: train/eng_Latn-zpz_Latn.jsonl.gz split: train - path: test/eng_Latn-zpz_Latn.jsonl.gz split: test - path: validation/eng_Latn-zpz_Latn.jsonl.gz split: validation - config_name: eng_Latn-yss_Latn data_files: - path: train/eng_Latn-yss_Latn.jsonl.gz split: train - path: test/eng_Latn-yss_Latn.jsonl.gz split: test - path: validation/eng_Latn-yss_Latn.jsonl.gz split: validation - config_name: eng_Latn-kos_Latn data_files: - path: train/eng_Latn-kos_Latn.jsonl.gz split: train - path: test/eng_Latn-kos_Latn.jsonl.gz split: test - path: validation/eng_Latn-kos_Latn.jsonl.gz split: validation - config_name: eng_Latn-reg_Latn data_files: - path: train/eng_Latn-reg_Latn.jsonl.gz split: train - path: test/eng_Latn-reg_Latn.jsonl.gz split: test - path: validation/eng_Latn-reg_Latn.jsonl.gz split: validation - config_name: eng_Latn-rro_Latn data_files: - path: train/eng_Latn-rro_Latn.jsonl.gz split: train - path: test/eng_Latn-rro_Latn.jsonl.gz split: test - path: validation/eng_Latn-rro_Latn.jsonl.gz split: validation - config_name: eng_Latn-apz_Latn data_files: - path: train/eng_Latn-apz_Latn.jsonl.gz split: train - path: test/eng_Latn-apz_Latn.jsonl.gz split: test - path: validation/eng_Latn-apz_Latn.jsonl.gz split: validation - config_name: eng_Latn-boj_Latn data_files: - path: train/eng_Latn-boj_Latn.jsonl.gz split: train - path: test/eng_Latn-boj_Latn.jsonl.gz split: test - path: validation/eng_Latn-boj_Latn.jsonl.gz split: validation - config_name: eng_Latn-hla_Latn data_files: - path: train/eng_Latn-hla_Latn.jsonl.gz split: train - path: test/eng_Latn-hla_Latn.jsonl.gz split: test - path: validation/eng_Latn-hla_Latn.jsonl.gz split: validation - config_name: eng_Latn-gyr_Latn data_files: - path: train/eng_Latn-gyr_Latn.jsonl.gz split: train - path: test/eng_Latn-gyr_Latn.jsonl.gz split: test - path: validation/eng_Latn-gyr_Latn.jsonl.gz split: validation - config_name: eng_Latn-ukr_Cyrl data_files: - path: train/eng_Latn-ukr_Cyrl.jsonl.gz split: train - path: test/eng_Latn-ukr_Cyrl.jsonl.gz split: test - path: validation/eng_Latn-ukr_Cyrl.jsonl.gz split: validation - config_name: eng_Latn-gvs_Latn data_files: - path: train/eng_Latn-gvs_Latn.jsonl.gz split: train - path: test/eng_Latn-gvs_Latn.jsonl.gz split: test - path: validation/eng_Latn-gvs_Latn.jsonl.gz split: validation - config_name: eng_Latn-mil_Latn data_files: - path: train/eng_Latn-mil_Latn.jsonl.gz split: train - path: test/eng_Latn-mil_Latn.jsonl.gz split: test - path: validation/eng_Latn-mil_Latn.jsonl.gz split: validation - config_name: eng_Latn-gul_Latn data_files: - path: train/eng_Latn-gul_Latn.jsonl.gz split: train - path: test/eng_Latn-gul_Latn.jsonl.gz split: test - path: validation/eng_Latn-gul_Latn.jsonl.gz split: validation - config_name: eng_Latn-ood_Latn data_files: - path: train/eng_Latn-ood_Latn.jsonl.gz split: train - path: test/eng_Latn-ood_Latn.jsonl.gz split: test - path: validation/eng_Latn-ood_Latn.jsonl.gz split: validation - config_name: eng_Latn-ewe_Latn data_files: - path: train/eng_Latn-ewe_Latn.jsonl.gz split: train - path: test/eng_Latn-ewe_Latn.jsonl.gz split: test - path: validation/eng_Latn-ewe_Latn.jsonl.gz split: validation - config_name: eng_Latn-qul_Latn data_files: - path: train/eng_Latn-qul_Latn.jsonl.gz split: train - path: test/eng_Latn-qul_Latn.jsonl.gz split: test - path: validation/eng_Latn-qul_Latn.jsonl.gz split: validation - config_name: eng_Latn-kbm_Latn data_files: - path: train/eng_Latn-kbm_Latn.jsonl.gz split: train - path: test/eng_Latn-kbm_Latn.jsonl.gz split: test - path: validation/eng_Latn-kbm_Latn.jsonl.gz split: validation - config_name: eng_Latn-mih_Latn data_files: - path: train/eng_Latn-mih_Latn.jsonl.gz split: train - path: test/eng_Latn-mih_Latn.jsonl.gz split: test - path: validation/eng_Latn-mih_Latn.jsonl.gz split: validation - config_name: eng_Latn-maq_Latn data_files: - path: train/eng_Latn-maq_Latn.jsonl.gz split: train - path: test/eng_Latn-maq_Latn.jsonl.gz split: test - path: validation/eng_Latn-maq_Latn.jsonl.gz split: validation - config_name: eng_Latn-bbr_Latn data_files: - path: train/eng_Latn-bbr_Latn.jsonl.gz split: train - path: test/eng_Latn-bbr_Latn.jsonl.gz split: test - path: validation/eng_Latn-bbr_Latn.jsonl.gz split: validation - config_name: eng_Latn-cbu_Latn data_files: - path: train/eng_Latn-cbu_Latn.jsonl.gz split: train - path: test/eng_Latn-cbu_Latn.jsonl.gz split: test - path: validation/eng_Latn-cbu_Latn.jsonl.gz split: validation - config_name: eng_Latn-meq_Latn data_files: - path: train/eng_Latn-meq_Latn.jsonl.gz split: train - path: test/eng_Latn-meq_Latn.jsonl.gz split: test - path: validation/eng_Latn-meq_Latn.jsonl.gz split: validation - config_name: eng_Latn-bmk_Latn data_files: - path: train/eng_Latn-bmk_Latn.jsonl.gz split: train - path: test/eng_Latn-bmk_Latn.jsonl.gz split: test - path: validation/eng_Latn-bmk_Latn.jsonl.gz split: validation - config_name: eng_Latn-hui_Latn data_files: - path: train/eng_Latn-hui_Latn.jsonl.gz split: train - path: test/eng_Latn-hui_Latn.jsonl.gz split: test - path: validation/eng_Latn-hui_Latn.jsonl.gz split: validation - config_name: eng_Latn-tgl_Latn data_files: - path: train/eng_Latn-tgl_Latn.jsonl.gz split: train - path: test/eng_Latn-tgl_Latn.jsonl.gz split: test - path: validation/eng_Latn-tgl_Latn.jsonl.gz split: validation - config_name: eng_Latn-lgl_Latn data_files: - path: train/eng_Latn-lgl_Latn.jsonl.gz split: train - path: test/eng_Latn-lgl_Latn.jsonl.gz split: test - path: validation/eng_Latn-lgl_Latn.jsonl.gz split: validation - config_name: eng_Latn-zpq_Latn data_files: - path: train/eng_Latn-zpq_Latn.jsonl.gz split: train - path: test/eng_Latn-zpq_Latn.jsonl.gz split: test - path: validation/eng_Latn-zpq_Latn.jsonl.gz split: validation - config_name: eng_Latn-mti_Latn data_files: - path: train/eng_Latn-mti_Latn.jsonl.gz split: train - path: test/eng_Latn-mti_Latn.jsonl.gz split: test - path: validation/eng_Latn-mti_Latn.jsonl.gz split: validation - config_name: eng_Latn-pah_Latn data_files: - path: train/eng_Latn-pah_Latn.jsonl.gz split: train - path: test/eng_Latn-pah_Latn.jsonl.gz split: test - path: validation/eng_Latn-pah_Latn.jsonl.gz split: validation - config_name: eng_Latn-nch_Latn data_files: - path: train/eng_Latn-nch_Latn.jsonl.gz split: train - path: test/eng_Latn-nch_Latn.jsonl.gz split: test - path: validation/eng_Latn-nch_Latn.jsonl.gz split: validation - config_name: eng_Latn-mjc_Latn data_files: - path: train/eng_Latn-mjc_Latn.jsonl.gz split: train - path: test/eng_Latn-mjc_Latn.jsonl.gz split: test - path: validation/eng_Latn-mjc_Latn.jsonl.gz split: validation - config_name: eng_Latn-zty_Latn data_files: - path: train/eng_Latn-zty_Latn.jsonl.gz split: train - path: test/eng_Latn-zty_Latn.jsonl.gz split: test - path: validation/eng_Latn-zty_Latn.jsonl.gz split: validation - config_name: eng_Latn-ksj_Latn data_files: - path: train/eng_Latn-ksj_Latn.jsonl.gz split: train - path: test/eng_Latn-ksj_Latn.jsonl.gz split: test - path: validation/eng_Latn-ksj_Latn.jsonl.gz split: validation - config_name: eng_Latn-nvm_Latn data_files: - path: train/eng_Latn-nvm_Latn.jsonl.gz split: train - path: test/eng_Latn-nvm_Latn.jsonl.gz split: test - path: validation/eng_Latn-nvm_Latn.jsonl.gz split: validation - config_name: eng_Latn-kyc_Latn data_files: - path: train/eng_Latn-kyc_Latn.jsonl.gz split: train - path: test/eng_Latn-kyc_Latn.jsonl.gz split: test - path: validation/eng_Latn-kyc_Latn.jsonl.gz split: validation - config_name: eng_Latn-bao_Latn data_files: - path: train/eng_Latn-bao_Latn.jsonl.gz split: train - path: test/eng_Latn-bao_Latn.jsonl.gz split: test - path: validation/eng_Latn-bao_Latn.jsonl.gz split: validation - config_name: eng_Latn-zas_Latn data_files: - path: train/eng_Latn-zas_Latn.jsonl.gz split: train - path: test/eng_Latn-zas_Latn.jsonl.gz split: test - path: validation/eng_Latn-zas_Latn.jsonl.gz split: validation - config_name: eng_Latn-djr_Latn data_files: - path: train/eng_Latn-djr_Latn.jsonl.gz split: train - path: test/eng_Latn-djr_Latn.jsonl.gz split: test - path: validation/eng_Latn-djr_Latn.jsonl.gz split: validation - config_name: eng_Latn-bpr_Latn data_files: - path: train/eng_Latn-bpr_Latn.jsonl.gz split: train - path: test/eng_Latn-bpr_Latn.jsonl.gz split: test - path: validation/eng_Latn-bpr_Latn.jsonl.gz split: validation - config_name: eng_Latn-ndg_Latn data_files: - path: train/eng_Latn-ndg_Latn.jsonl.gz split: train - path: test/eng_Latn-ndg_Latn.jsonl.gz split: test - path: validation/eng_Latn-ndg_Latn.jsonl.gz split: validation - config_name: eng_Latn-ots_Latn data_files: - path: train/eng_Latn-ots_Latn.jsonl.gz split: train - path: test/eng_Latn-ots_Latn.jsonl.gz split: test - path: validation/eng_Latn-ots_Latn.jsonl.gz split: validation - config_name: eng_Latn-miz_Latn data_files: - path: train/eng_Latn-miz_Latn.jsonl.gz split: train - path: test/eng_Latn-miz_Latn.jsonl.gz split: test - path: validation/eng_Latn-miz_Latn.jsonl.gz split: validation - config_name: eng_Latn-cco_Latn data_files: - path: train/eng_Latn-cco_Latn.jsonl.gz split: train - path: test/eng_Latn-cco_Latn.jsonl.gz split: test - path: validation/eng_Latn-cco_Latn.jsonl.gz split: validation - config_name: eng_Latn-mbc_Latn data_files: - path: train/eng_Latn-mbc_Latn.jsonl.gz split: train - path: test/eng_Latn-mbc_Latn.jsonl.gz split: test - path: validation/eng_Latn-mbc_Latn.jsonl.gz split: validation - config_name: eng_Latn-myy_Latn data_files: - path: train/eng_Latn-myy_Latn.jsonl.gz split: train - path: test/eng_Latn-myy_Latn.jsonl.gz split: test - path: validation/eng_Latn-myy_Latn.jsonl.gz split: validation - config_name: eng_Latn-att_Latn data_files: - path: train/eng_Latn-att_Latn.jsonl.gz split: train - path: test/eng_Latn-att_Latn.jsonl.gz split: test - path: validation/eng_Latn-att_Latn.jsonl.gz split: validation - config_name: eng_Latn-aly_Latn data_files: - path: train/eng_Latn-aly_Latn.jsonl.gz split: train - path: test/eng_Latn-aly_Latn.jsonl.gz split: test - path: validation/eng_Latn-aly_Latn.jsonl.gz split: validation - config_name: eng_Latn-mgh_Latn data_files: - path: train/eng_Latn-mgh_Latn.jsonl.gz split: train - path: test/eng_Latn-mgh_Latn.jsonl.gz split: test - path: validation/eng_Latn-mgh_Latn.jsonl.gz split: validation - config_name: eng_Latn-mqb_Latn data_files: - path: train/eng_Latn-mqb_Latn.jsonl.gz split: train - path: test/eng_Latn-mqb_Latn.jsonl.gz split: test - path: validation/eng_Latn-mqb_Latn.jsonl.gz split: validation - config_name: eng_Latn-sps_Latn data_files: - path: train/eng_Latn-sps_Latn.jsonl.gz split: train - path: test/eng_Latn-sps_Latn.jsonl.gz split: test - path: validation/eng_Latn-sps_Latn.jsonl.gz split: validation - config_name: eng_Latn-wbi_Latn data_files: - path: train/eng_Latn-wbi_Latn.jsonl.gz split: train - path: test/eng_Latn-wbi_Latn.jsonl.gz split: test - path: validation/eng_Latn-wbi_Latn.jsonl.gz split: validation - config_name: eng_Latn-rai_Latn data_files: - path: train/eng_Latn-rai_Latn.jsonl.gz split: train - path: test/eng_Latn-rai_Latn.jsonl.gz split: test - path: validation/eng_Latn-rai_Latn.jsonl.gz split: validation - config_name: eng_Latn-knf_Latn data_files: - path: train/eng_Latn-knf_Latn.jsonl.gz split: train - path: test/eng_Latn-knf_Latn.jsonl.gz split: test - path: validation/eng_Latn-knf_Latn.jsonl.gz split: validation - config_name: eng_Latn-txq_Latn data_files: - path: train/eng_Latn-txq_Latn.jsonl.gz split: train - path: test/eng_Latn-txq_Latn.jsonl.gz split: test - path: validation/eng_Latn-txq_Latn.jsonl.gz split: validation - config_name: eng_Latn-cuk_Latn data_files: - path: train/eng_Latn-cuk_Latn.jsonl.gz split: train - path: test/eng_Latn-cuk_Latn.jsonl.gz split: test - path: validation/eng_Latn-cuk_Latn.jsonl.gz split: validation - config_name: eng_Latn-tew_Latn data_files: - path: train/eng_Latn-tew_Latn.jsonl.gz split: train - path: test/eng_Latn-tew_Latn.jsonl.gz split: test - path: validation/eng_Latn-tew_Latn.jsonl.gz split: validation - config_name: eng_Latn-aia_Latn data_files: - path: train/eng_Latn-aia_Latn.jsonl.gz split: train - path: test/eng_Latn-aia_Latn.jsonl.gz split: test - path: validation/eng_Latn-aia_Latn.jsonl.gz split: validation - config_name: eng_Latn-ghs_Latn data_files: - path: train/eng_Latn-ghs_Latn.jsonl.gz split: train - path: test/eng_Latn-ghs_Latn.jsonl.gz split: test - path: validation/eng_Latn-ghs_Latn.jsonl.gz split: validation - config_name: eng_Latn-kne_Latn data_files: - path: train/eng_Latn-kne_Latn.jsonl.gz split: train - path: test/eng_Latn-kne_Latn.jsonl.gz split: test - path: validation/eng_Latn-kne_Latn.jsonl.gz split: validation - config_name: eng_Latn-snp_Latn data_files: - path: train/eng_Latn-snp_Latn.jsonl.gz split: train - path: test/eng_Latn-snp_Latn.jsonl.gz split: test - path: validation/eng_Latn-snp_Latn.jsonl.gz split: validation - config_name: eng_Latn-yon_Latn data_files: - path: train/eng_Latn-yon_Latn.jsonl.gz split: train - path: test/eng_Latn-yon_Latn.jsonl.gz split: test - path: validation/eng_Latn-yon_Latn.jsonl.gz split: validation - config_name: eng_Latn-rkb_Latn data_files: - path: train/eng_Latn-rkb_Latn.jsonl.gz split: train - path: test/eng_Latn-rkb_Latn.jsonl.gz split: test - path: validation/eng_Latn-rkb_Latn.jsonl.gz split: validation - config_name: eng_Latn-mam_Latn data_files: - path: train/eng_Latn-mam_Latn.jsonl.gz split: train - path: test/eng_Latn-mam_Latn.jsonl.gz split: test - path: validation/eng_Latn-mam_Latn.jsonl.gz split: validation - config_name: eng_Latn-ffm_Latn data_files: - path: train/eng_Latn-ffm_Latn.jsonl.gz split: train - path: test/eng_Latn-ffm_Latn.jsonl.gz split: test - path: validation/eng_Latn-ffm_Latn.jsonl.gz split: validation - config_name: eng_Latn-tbo_Latn data_files: - path: train/eng_Latn-tbo_Latn.jsonl.gz split: train - path: test/eng_Latn-tbo_Latn.jsonl.gz split: test - path: validation/eng_Latn-tbo_Latn.jsonl.gz split: validation - config_name: eng_Latn-cta_Latn data_files: - path: train/eng_Latn-cta_Latn.jsonl.gz split: train - path: test/eng_Latn-cta_Latn.jsonl.gz split: test - path: validation/eng_Latn-cta_Latn.jsonl.gz split: validation - config_name: eng_Latn-mca_Latn data_files: - path: train/eng_Latn-mca_Latn.jsonl.gz split: train - path: test/eng_Latn-mca_Latn.jsonl.gz split: test - path: validation/eng_Latn-mca_Latn.jsonl.gz split: validation - config_name: eng_Latn-smk_Latn data_files: - path: train/eng_Latn-smk_Latn.jsonl.gz split: train - path: test/eng_Latn-smk_Latn.jsonl.gz split: test - path: validation/eng_Latn-smk_Latn.jsonl.gz split: validation - config_name: eng_Latn-bqc_Latn data_files: - path: train/eng_Latn-bqc_Latn.jsonl.gz split: train - path: test/eng_Latn-bqc_Latn.jsonl.gz split: test - path: validation/eng_Latn-bqc_Latn.jsonl.gz split: validation - config_name: eng_Latn-khz_Latn data_files: - path: train/eng_Latn-khz_Latn.jsonl.gz split: train - path: test/eng_Latn-khz_Latn.jsonl.gz split: test - path: validation/eng_Latn-khz_Latn.jsonl.gz split: validation - config_name: eng_Latn-ceb_Latn data_files: - path: train/eng_Latn-ceb_Latn.jsonl.gz split: train - path: test/eng_Latn-ceb_Latn.jsonl.gz split: test - path: validation/eng_Latn-ceb_Latn.jsonl.gz split: validation - config_name: eng_Latn-nyu_Latn data_files: - path: train/eng_Latn-nyu_Latn.jsonl.gz split: train - path: test/eng_Latn-nyu_Latn.jsonl.gz split: test - path: validation/eng_Latn-nyu_Latn.jsonl.gz split: validation - config_name: eng_Latn-hlt_Latn data_files: - path: train/eng_Latn-hlt_Latn.jsonl.gz split: train - path: test/eng_Latn-hlt_Latn.jsonl.gz split: test - path: validation/eng_Latn-hlt_Latn.jsonl.gz split: validation - config_name: eng_Latn-qvw_Latn data_files: - path: train/eng_Latn-qvw_Latn.jsonl.gz split: train - path: test/eng_Latn-qvw_Latn.jsonl.gz split: test - path: validation/eng_Latn-qvw_Latn.jsonl.gz split: validation - config_name: eng_Latn-poy_Latn data_files: - path: train/eng_Latn-poy_Latn.jsonl.gz split: train - path: test/eng_Latn-poy_Latn.jsonl.gz split: test - path: validation/eng_Latn-poy_Latn.jsonl.gz split: validation - config_name: eng_Latn-jiv_Latn data_files: - path: train/eng_Latn-jiv_Latn.jsonl.gz split: train - path: test/eng_Latn-jiv_Latn.jsonl.gz split: test - path: validation/eng_Latn-jiv_Latn.jsonl.gz split: validation - config_name: eng_Latn-mna_Latn data_files: - path: train/eng_Latn-mna_Latn.jsonl.gz split: train - path: test/eng_Latn-mna_Latn.jsonl.gz split: test - path: validation/eng_Latn-mna_Latn.jsonl.gz split: validation - config_name: eng_Latn-xsi_Latn data_files: - path: train/eng_Latn-xsi_Latn.jsonl.gz split: train - path: test/eng_Latn-xsi_Latn.jsonl.gz split: test - path: validation/eng_Latn-xsi_Latn.jsonl.gz split: validation - config_name: eng_Latn-crx_Latn data_files: - path: train/eng_Latn-crx_Latn.jsonl.gz split: train - path: test/eng_Latn-crx_Latn.jsonl.gz split: test - path: validation/eng_Latn-crx_Latn.jsonl.gz split: validation - config_name: eng_Latn-apb_Latn data_files: - path: train/eng_Latn-apb_Latn.jsonl.gz split: train - path: test/eng_Latn-apb_Latn.jsonl.gz split: test - path: validation/eng_Latn-apb_Latn.jsonl.gz split: validation - config_name: eng_Latn-imo_Latn data_files: - path: train/eng_Latn-imo_Latn.jsonl.gz split: train - path: test/eng_Latn-imo_Latn.jsonl.gz split: test - path: validation/eng_Latn-imo_Latn.jsonl.gz split: validation - config_name: eng_Latn-fue_Latn data_files: - path: train/eng_Latn-fue_Latn.jsonl.gz split: train - path: test/eng_Latn-fue_Latn.jsonl.gz split: test - path: validation/eng_Latn-fue_Latn.jsonl.gz split: validation - config_name: eng_Latn-bhl_Latn data_files: - path: train/eng_Latn-bhl_Latn.jsonl.gz split: train - path: test/eng_Latn-bhl_Latn.jsonl.gz split: test - path: validation/eng_Latn-bhl_Latn.jsonl.gz split: validation - config_name: eng_Latn-tim_Latn data_files: - path: train/eng_Latn-tim_Latn.jsonl.gz split: train - path: test/eng_Latn-tim_Latn.jsonl.gz split: test - path: validation/eng_Latn-tim_Latn.jsonl.gz split: validation - config_name: eng_Latn-mgw_Latn data_files: - path: train/eng_Latn-mgw_Latn.jsonl.gz split: train - path: test/eng_Latn-mgw_Latn.jsonl.gz split: test - path: validation/eng_Latn-mgw_Latn.jsonl.gz split: validation - config_name: eng_Latn-taj_Deva data_files: - path: train/eng_Latn-taj_Deva.jsonl.gz split: train - path: test/eng_Latn-taj_Deva.jsonl.gz split: test - path: validation/eng_Latn-taj_Deva.jsonl.gz split: validation - config_name: eng_Latn-djk_Latn data_files: - path: train/eng_Latn-djk_Latn.jsonl.gz split: train - path: test/eng_Latn-djk_Latn.jsonl.gz split: test - path: validation/eng_Latn-djk_Latn.jsonl.gz split: validation - config_name: eng_Latn-ruf_Latn data_files: - path: train/eng_Latn-ruf_Latn.jsonl.gz split: train - path: test/eng_Latn-ruf_Latn.jsonl.gz split: test - path: validation/eng_Latn-ruf_Latn.jsonl.gz split: validation - config_name: eng_Latn-bqp_Latn data_files: - path: train/eng_Latn-bqp_Latn.jsonl.gz split: train - path: test/eng_Latn-bqp_Latn.jsonl.gz split: test - path: validation/eng_Latn-bqp_Latn.jsonl.gz split: validation - config_name: eng_Latn-adz_Latn data_files: - path: train/eng_Latn-adz_Latn.jsonl.gz split: train - path: test/eng_Latn-adz_Latn.jsonl.gz split: test - path: validation/eng_Latn-adz_Latn.jsonl.gz split: validation - config_name: eng_Latn-bmr_Latn data_files: - path: train/eng_Latn-bmr_Latn.jsonl.gz split: train - path: test/eng_Latn-bmr_Latn.jsonl.gz split: test - path: validation/eng_Latn-bmr_Latn.jsonl.gz split: validation - config_name: eng_Latn-ata_Latn data_files: - path: train/eng_Latn-ata_Latn.jsonl.gz split: train - path: test/eng_Latn-ata_Latn.jsonl.gz split: test - path: validation/eng_Latn-ata_Latn.jsonl.gz split: validation - config_name: eng_Latn-mio_Latn data_files: - path: train/eng_Latn-mio_Latn.jsonl.gz split: train - path: test/eng_Latn-mio_Latn.jsonl.gz split: test - path: validation/eng_Latn-mio_Latn.jsonl.gz split: validation - config_name: eng_Latn-pad_Latn data_files: - path: train/eng_Latn-pad_Latn.jsonl.gz split: train - path: test/eng_Latn-pad_Latn.jsonl.gz split: test - path: validation/eng_Latn-pad_Latn.jsonl.gz split: validation - config_name: eng_Latn-qxh_Latn data_files: - path: train/eng_Latn-qxh_Latn.jsonl.gz split: train - path: test/eng_Latn-qxh_Latn.jsonl.gz split: test - path: validation/eng_Latn-qxh_Latn.jsonl.gz split: validation - config_name: eng_Latn-tfr_Latn data_files: - path: train/eng_Latn-tfr_Latn.jsonl.gz split: train - path: test/eng_Latn-tfr_Latn.jsonl.gz split: test - path: validation/eng_Latn-tfr_Latn.jsonl.gz split: validation - config_name: eng_Latn-mie_Latn data_files: - path: train/eng_Latn-mie_Latn.jsonl.gz split: train - path: test/eng_Latn-mie_Latn.jsonl.gz split: test - path: validation/eng_Latn-mie_Latn.jsonl.gz split: validation - config_name: eng_Latn-tpi_Latn data_files: - path: train/eng_Latn-tpi_Latn.jsonl.gz split: train - path: test/eng_Latn-tpi_Latn.jsonl.gz split: test - path: validation/eng_Latn-tpi_Latn.jsonl.gz split: validation - config_name: eng_Latn-fuh_Latn data_files: - path: train/eng_Latn-fuh_Latn.jsonl.gz split: train - path: test/eng_Latn-fuh_Latn.jsonl.gz split: test - path: validation/eng_Latn-fuh_Latn.jsonl.gz split: validation - config_name: eng_Latn-dgr_Latn data_files: - path: train/eng_Latn-dgr_Latn.jsonl.gz split: train - path: test/eng_Latn-dgr_Latn.jsonl.gz split: test - path: validation/eng_Latn-dgr_Latn.jsonl.gz split: validation - config_name: eng_Latn-bch_Latn data_files: - path: train/eng_Latn-bch_Latn.jsonl.gz split: train - path: test/eng_Latn-bch_Latn.jsonl.gz split: test - path: validation/eng_Latn-bch_Latn.jsonl.gz split: validation - config_name: eng_Latn-mcr_Latn data_files: - path: train/eng_Latn-mcr_Latn.jsonl.gz split: train - path: test/eng_Latn-mcr_Latn.jsonl.gz split: test - path: validation/eng_Latn-mcr_Latn.jsonl.gz split: validation - config_name: eng_Latn-bkx_Latn data_files: - path: train/eng_Latn-bkx_Latn.jsonl.gz split: train - path: test/eng_Latn-bkx_Latn.jsonl.gz split: test - path: validation/eng_Latn-bkx_Latn.jsonl.gz split: validation - config_name: eng_Latn-agr_Latn data_files: - path: train/eng_Latn-agr_Latn.jsonl.gz split: train - path: test/eng_Latn-agr_Latn.jsonl.gz split: test - path: validation/eng_Latn-agr_Latn.jsonl.gz split: validation - config_name: eng_Latn-chq_Latn data_files: - path: train/eng_Latn-chq_Latn.jsonl.gz split: train - path: test/eng_Latn-chq_Latn.jsonl.gz split: test - path: validation/eng_Latn-chq_Latn.jsonl.gz split: validation - config_name: eng_Latn-rwo_Latn data_files: - path: train/eng_Latn-rwo_Latn.jsonl.gz split: train - path: test/eng_Latn-rwo_Latn.jsonl.gz split: test - path: validation/eng_Latn-rwo_Latn.jsonl.gz split: validation - config_name: eng_Latn-esk_Latn data_files: - path: train/eng_Latn-esk_Latn.jsonl.gz split: train - path: test/eng_Latn-esk_Latn.jsonl.gz split: test - path: validation/eng_Latn-esk_Latn.jsonl.gz split: validation - config_name: eng_Latn-zpl_Latn data_files: - path: train/eng_Latn-zpl_Latn.jsonl.gz split: train - path: test/eng_Latn-zpl_Latn.jsonl.gz split: test - path: validation/eng_Latn-zpl_Latn.jsonl.gz split: validation - config_name: eng_Latn-bjr_Latn data_files: - path: train/eng_Latn-bjr_Latn.jsonl.gz split: train - path: test/eng_Latn-bjr_Latn.jsonl.gz split: test - path: validation/eng_Latn-bjr_Latn.jsonl.gz split: validation - config_name: eng_Latn-kiw_Latn data_files: - path: train/eng_Latn-kiw_Latn.jsonl.gz split: train - path: test/eng_Latn-kiw_Latn.jsonl.gz split: test - path: validation/eng_Latn-kiw_Latn.jsonl.gz split: validation - config_name: eng_Latn-azg_Latn data_files: - path: train/eng_Latn-azg_Latn.jsonl.gz split: train - path: test/eng_Latn-azg_Latn.jsonl.gz split: test - path: validation/eng_Latn-azg_Latn.jsonl.gz split: validation - config_name: eng_Latn-mbb_Latn data_files: - path: train/eng_Latn-mbb_Latn.jsonl.gz split: train - path: test/eng_Latn-mbb_Latn.jsonl.gz split: test - path: validation/eng_Latn-mbb_Latn.jsonl.gz split: validation - config_name: eng_Latn-knj_Latn data_files: - path: train/eng_Latn-knj_Latn.jsonl.gz split: train - path: test/eng_Latn-knj_Latn.jsonl.gz split: test - path: validation/eng_Latn-knj_Latn.jsonl.gz split: validation - config_name: eng_Latn-cao_Latn data_files: - path: train/eng_Latn-cao_Latn.jsonl.gz split: train - path: test/eng_Latn-cao_Latn.jsonl.gz split: test - path: validation/eng_Latn-cao_Latn.jsonl.gz split: validation - config_name: eng_Latn-dji_Latn data_files: - path: train/eng_Latn-dji_Latn.jsonl.gz split: train - path: test/eng_Latn-dji_Latn.jsonl.gz split: test - path: validation/eng_Latn-dji_Latn.jsonl.gz split: validation - config_name: eng_Latn-bss_Latn data_files: - path: train/eng_Latn-bss_Latn.jsonl.gz split: train - path: test/eng_Latn-bss_Latn.jsonl.gz split: test - path: validation/eng_Latn-bss_Latn.jsonl.gz split: validation - config_name: eng_Latn-bgs_Latn data_files: - path: train/eng_Latn-bgs_Latn.jsonl.gz split: train - path: test/eng_Latn-bgs_Latn.jsonl.gz split: test - path: validation/eng_Latn-bgs_Latn.jsonl.gz split: validation - config_name: eng_Latn-mek_Latn data_files: - path: train/eng_Latn-mek_Latn.jsonl.gz split: train - path: test/eng_Latn-mek_Latn.jsonl.gz split: test - path: validation/eng_Latn-mek_Latn.jsonl.gz split: validation - config_name: eng_Latn-yuj_Latn data_files: - path: train/eng_Latn-yuj_Latn.jsonl.gz split: train - path: test/eng_Latn-yuj_Latn.jsonl.gz split: test - path: validation/eng_Latn-yuj_Latn.jsonl.gz split: validation - config_name: eng_Latn-tpt_Latn data_files: - path: train/eng_Latn-tpt_Latn.jsonl.gz split: train - path: test/eng_Latn-tpt_Latn.jsonl.gz split: test - path: validation/eng_Latn-tpt_Latn.jsonl.gz split: validation - config_name: eng_Latn-zos_Latn data_files: - path: train/eng_Latn-zos_Latn.jsonl.gz split: train - path: test/eng_Latn-zos_Latn.jsonl.gz split: test - path: validation/eng_Latn-zos_Latn.jsonl.gz split: validation - config_name: eng_Latn-blw_Latn data_files: - path: train/eng_Latn-blw_Latn.jsonl.gz split: train - path: test/eng_Latn-blw_Latn.jsonl.gz split: test - path: validation/eng_Latn-blw_Latn.jsonl.gz split: validation - config_name: eng_Latn-viv_Latn data_files: - path: train/eng_Latn-viv_Latn.jsonl.gz split: train - path: test/eng_Latn-viv_Latn.jsonl.gz split: test - path: validation/eng_Latn-viv_Latn.jsonl.gz split: validation - config_name: eng_Latn-ikw_Latn data_files: - path: train/eng_Latn-ikw_Latn.jsonl.gz split: train - path: test/eng_Latn-ikw_Latn.jsonl.gz split: test - path: validation/eng_Latn-ikw_Latn.jsonl.gz split: validation - config_name: eng_Latn-tue_Latn data_files: - path: train/eng_Latn-tue_Latn.jsonl.gz split: train - path: test/eng_Latn-tue_Latn.jsonl.gz split: test - path: validation/eng_Latn-tue_Latn.jsonl.gz split: validation - config_name: eng_Latn-uvh_Latn data_files: - path: train/eng_Latn-uvh_Latn.jsonl.gz split: train - path: test/eng_Latn-uvh_Latn.jsonl.gz split: test - path: validation/eng_Latn-uvh_Latn.jsonl.gz split: validation - config_name: eng_Latn-yap_Latn data_files: - path: train/eng_Latn-yap_Latn.jsonl.gz split: train - path: test/eng_Latn-yap_Latn.jsonl.gz split: test - path: validation/eng_Latn-yap_Latn.jsonl.gz split: validation - config_name: eng_Latn-nca_Latn data_files: - path: train/eng_Latn-nca_Latn.jsonl.gz split: train - path: test/eng_Latn-nca_Latn.jsonl.gz split: test - path: validation/eng_Latn-nca_Latn.jsonl.gz split: validation - config_name: eng_Latn-luo_Latn data_files: - path: train/eng_Latn-luo_Latn.jsonl.gz split: train - path: test/eng_Latn-luo_Latn.jsonl.gz split: test - path: validation/eng_Latn-luo_Latn.jsonl.gz split: validation - config_name: eng_Latn-tmd_Latn data_files: - path: train/eng_Latn-tmd_Latn.jsonl.gz split: train - path: test/eng_Latn-tmd_Latn.jsonl.gz split: test - path: validation/eng_Latn-tmd_Latn.jsonl.gz split: validation - config_name: eng_Latn-txu_Latn data_files: - path: train/eng_Latn-txu_Latn.jsonl.gz split: train - path: test/eng_Latn-txu_Latn.jsonl.gz split: test - path: validation/eng_Latn-txu_Latn.jsonl.gz split: validation - config_name: eng_Latn-yor_Latn data_files: - path: train/eng_Latn-yor_Latn.jsonl.gz split: train - path: test/eng_Latn-yor_Latn.jsonl.gz split: test - path: validation/eng_Latn-yor_Latn.jsonl.gz split: validation - config_name: eng_Latn-amx_Latn data_files: - path: train/eng_Latn-amx_Latn.jsonl.gz split: train - path: test/eng_Latn-amx_Latn.jsonl.gz split: test - path: validation/eng_Latn-amx_Latn.jsonl.gz split: validation - config_name: eng_Latn-uli_Latn data_files: - path: train/eng_Latn-uli_Latn.jsonl.gz split: train - path: test/eng_Latn-uli_Latn.jsonl.gz split: test - path: validation/eng_Latn-uli_Latn.jsonl.gz split: validation - config_name: eng_Latn-dov_Latn data_files: - path: train/eng_Latn-dov_Latn.jsonl.gz split: train - path: test/eng_Latn-dov_Latn.jsonl.gz split: test - path: validation/eng_Latn-dov_Latn.jsonl.gz split: validation - config_name: eng_Latn-huv_Latn data_files: - path: train/eng_Latn-huv_Latn.jsonl.gz split: train - path: test/eng_Latn-huv_Latn.jsonl.gz split: test - path: validation/eng_Latn-huv_Latn.jsonl.gz split: validation - config_name: eng_Latn-msk_Latn data_files: - path: train/eng_Latn-msk_Latn.jsonl.gz split: train - path: test/eng_Latn-msk_Latn.jsonl.gz split: test - path: validation/eng_Latn-msk_Latn.jsonl.gz split: validation - config_name: eng_Latn-twi_Latn data_files: - path: train/eng_Latn-twi_Latn.jsonl.gz split: train - path: test/eng_Latn-twi_Latn.jsonl.gz split: test - path: validation/eng_Latn-twi_Latn.jsonl.gz split: validation - config_name: eng_Latn-aer_Latn data_files: - path: train/eng_Latn-aer_Latn.jsonl.gz split: train - path: test/eng_Latn-aer_Latn.jsonl.gz split: test - path: validation/eng_Latn-aer_Latn.jsonl.gz split: validation - config_name: eng_Latn-pib_Latn data_files: - path: train/eng_Latn-pib_Latn.jsonl.gz split: train - path: test/eng_Latn-pib_Latn.jsonl.gz split: test - path: validation/eng_Latn-pib_Latn.jsonl.gz split: validation - config_name: eng_Latn-ter_Latn data_files: - path: train/eng_Latn-ter_Latn.jsonl.gz split: train - path: test/eng_Latn-ter_Latn.jsonl.gz split: test - path: validation/eng_Latn-ter_Latn.jsonl.gz split: validation - config_name: eng_Latn-eri_Latn data_files: - path: train/eng_Latn-eri_Latn.jsonl.gz split: train - path: test/eng_Latn-eri_Latn.jsonl.gz split: test - path: validation/eng_Latn-eri_Latn.jsonl.gz split: validation - config_name: eng_Latn-cth_Latn data_files: - path: train/eng_Latn-cth_Latn.jsonl.gz split: train - path: test/eng_Latn-cth_Latn.jsonl.gz split: test - path: validation/eng_Latn-cth_Latn.jsonl.gz split: validation - config_name: eng_Latn-dwr_Latn data_files: - path: train/eng_Latn-dwr_Latn.jsonl.gz split: train - path: test/eng_Latn-dwr_Latn.jsonl.gz split: test - path: validation/eng_Latn-dwr_Latn.jsonl.gz split: validation - config_name: eng_Latn-srq_Latn data_files: - path: train/eng_Latn-srq_Latn.jsonl.gz split: train - path: test/eng_Latn-srq_Latn.jsonl.gz split: test - path: validation/eng_Latn-srq_Latn.jsonl.gz split: validation - config_name: eng_Latn-mmx_Latn data_files: - path: train/eng_Latn-mmx_Latn.jsonl.gz split: train - path: test/eng_Latn-mmx_Latn.jsonl.gz split: test - path: validation/eng_Latn-mmx_Latn.jsonl.gz split: validation - config_name: eng_Latn-cap_Latn data_files: - path: train/eng_Latn-cap_Latn.jsonl.gz split: train - path: test/eng_Latn-cap_Latn.jsonl.gz split: test - path: validation/eng_Latn-cap_Latn.jsonl.gz split: validation - config_name: eng_Latn-ces_Latn data_files: - path: train/eng_Latn-ces_Latn.jsonl.gz split: train - path: test/eng_Latn-ces_Latn.jsonl.gz split: test - path: validation/eng_Latn-ces_Latn.jsonl.gz split: validation - config_name: eng_Latn-cpu_Latn data_files: - path: train/eng_Latn-cpu_Latn.jsonl.gz split: train - path: test/eng_Latn-cpu_Latn.jsonl.gz split: test - path: validation/eng_Latn-cpu_Latn.jsonl.gz split: validation - config_name: eng_Latn-lww_Latn data_files: - path: train/eng_Latn-lww_Latn.jsonl.gz split: train - path: test/eng_Latn-lww_Latn.jsonl.gz split: test - path: validation/eng_Latn-lww_Latn.jsonl.gz split: validation - config_name: eng_Latn-hix_Latn data_files: - path: train/eng_Latn-hix_Latn.jsonl.gz split: train - path: test/eng_Latn-hix_Latn.jsonl.gz split: test - path: validation/eng_Latn-hix_Latn.jsonl.gz split: validation - config_name: eng_Latn-cab_Latn data_files: - path: train/eng_Latn-cab_Latn.jsonl.gz split: train - path: test/eng_Latn-cab_Latn.jsonl.gz split: test - path: validation/eng_Latn-cab_Latn.jsonl.gz split: validation - config_name: eng_Latn-fuf_Latn data_files: - path: train/eng_Latn-fuf_Latn.jsonl.gz split: train - path: test/eng_Latn-fuf_Latn.jsonl.gz split: test - path: validation/eng_Latn-fuf_Latn.jsonl.gz split: validation - config_name: eng_Latn-mcf_Latn data_files: - path: train/eng_Latn-mcf_Latn.jsonl.gz split: train - path: test/eng_Latn-mcf_Latn.jsonl.gz split: test - path: validation/eng_Latn-mcf_Latn.jsonl.gz split: validation - config_name: eng_Latn-shj_Latn data_files: - path: train/eng_Latn-shj_Latn.jsonl.gz split: train - path: test/eng_Latn-shj_Latn.jsonl.gz split: test - path: validation/eng_Latn-shj_Latn.jsonl.gz split: validation - config_name: eng_Latn-qwh_Latn data_files: - path: train/eng_Latn-qwh_Latn.jsonl.gz split: train - path: test/eng_Latn-qwh_Latn.jsonl.gz split: test - path: validation/eng_Latn-qwh_Latn.jsonl.gz split: validation - config_name: eng_Latn-zsr_Latn data_files: - path: train/eng_Latn-zsr_Latn.jsonl.gz split: train - path: test/eng_Latn-zsr_Latn.jsonl.gz split: test - path: validation/eng_Latn-zsr_Latn.jsonl.gz split: validation - config_name: eng_Latn-daa_Latn data_files: - path: train/eng_Latn-daa_Latn.jsonl.gz split: train - path: test/eng_Latn-daa_Latn.jsonl.gz split: test - path: validation/eng_Latn-daa_Latn.jsonl.gz split: validation - config_name: eng_Latn-sus_Arab data_files: - path: train/eng_Latn-sus_Arab.jsonl.gz split: train - path: test/eng_Latn-sus_Arab.jsonl.gz split: test - path: validation/eng_Latn-sus_Arab.jsonl.gz split: validation - config_name: eng_Latn-lbk_Latn data_files: - path: train/eng_Latn-lbk_Latn.jsonl.gz split: train - path: test/eng_Latn-lbk_Latn.jsonl.gz split: test - path: validation/eng_Latn-lbk_Latn.jsonl.gz split: validation - config_name: eng_Latn-nii_Latn data_files: - path: train/eng_Latn-nii_Latn.jsonl.gz split: train - path: test/eng_Latn-nii_Latn.jsonl.gz split: test - path: validation/eng_Latn-nii_Latn.jsonl.gz split: validation - config_name: eng_Latn-gvn_Latn data_files: - path: train/eng_Latn-gvn_Latn.jsonl.gz split: train - path: test/eng_Latn-gvn_Latn.jsonl.gz split: test - path: validation/eng_Latn-gvn_Latn.jsonl.gz split: validation - config_name: eng_Latn-yaa_Latn data_files: - path: train/eng_Latn-yaa_Latn.jsonl.gz split: train - path: test/eng_Latn-yaa_Latn.jsonl.gz split: test - path: validation/eng_Latn-yaa_Latn.jsonl.gz split: validation - config_name: eng_Latn-npi_Deva data_files: - path: train/eng_Latn-npi_Deva.jsonl.gz split: train - path: test/eng_Latn-npi_Deva.jsonl.gz split: test - path: validation/eng_Latn-npi_Deva.jsonl.gz split: validation - config_name: eng_Latn-uig_Latn data_files: - path: train/eng_Latn-uig_Latn.jsonl.gz split: train - path: test/eng_Latn-uig_Latn.jsonl.gz split: test - path: validation/eng_Latn-uig_Latn.jsonl.gz split: validation - config_name: eng_Latn-mmo_Latn data_files: - path: train/eng_Latn-mmo_Latn.jsonl.gz split: train - path: test/eng_Latn-mmo_Latn.jsonl.gz split: test - path: validation/eng_Latn-mmo_Latn.jsonl.gz split: validation - config_name: eng_Latn-ktm_Latn data_files: - path: train/eng_Latn-ktm_Latn.jsonl.gz split: train - path: test/eng_Latn-ktm_Latn.jsonl.gz split: test - path: validation/eng_Latn-ktm_Latn.jsonl.gz split: validation - config_name: eng_Latn-agu_Latn data_files: - path: train/eng_Latn-agu_Latn.jsonl.gz split: train - path: test/eng_Latn-agu_Latn.jsonl.gz split: test - path: validation/eng_Latn-agu_Latn.jsonl.gz split: validation - config_name: eng_Latn-agg_Latn data_files: - path: train/eng_Latn-agg_Latn.jsonl.gz split: train - path: test/eng_Latn-agg_Latn.jsonl.gz split: test - path: validation/eng_Latn-agg_Latn.jsonl.gz split: validation - config_name: eng_Latn-ken_Latn data_files: - path: train/eng_Latn-ken_Latn.jsonl.gz split: train - path: test/eng_Latn-ken_Latn.jsonl.gz split: test - path: validation/eng_Latn-ken_Latn.jsonl.gz split: validation - config_name: eng_Latn-beu_Latn data_files: - path: train/eng_Latn-beu_Latn.jsonl.gz split: train - path: test/eng_Latn-beu_Latn.jsonl.gz split: test - path: validation/eng_Latn-beu_Latn.jsonl.gz split: validation - config_name: eng_Latn-cac_Latn data_files: - path: train/eng_Latn-cac_Latn.jsonl.gz split: train - path: test/eng_Latn-cac_Latn.jsonl.gz split: test - path: validation/eng_Latn-cac_Latn.jsonl.gz split: validation - config_name: eng_Latn-uri_Latn data_files: - path: train/eng_Latn-uri_Latn.jsonl.gz split: train - path: test/eng_Latn-uri_Latn.jsonl.gz split: test - path: validation/eng_Latn-uri_Latn.jsonl.gz split: validation - config_name: eng_Latn-dah_Latn data_files: - path: train/eng_Latn-dah_Latn.jsonl.gz split: train - path: test/eng_Latn-dah_Latn.jsonl.gz split: test - path: validation/eng_Latn-dah_Latn.jsonl.gz split: validation - config_name: eng_Latn-otn_Latn data_files: - path: train/eng_Latn-otn_Latn.jsonl.gz split: train - path: test/eng_Latn-otn_Latn.jsonl.gz split: test - path: validation/eng_Latn-otn_Latn.jsonl.gz split: validation - config_name: eng_Latn-wos_Latn data_files: - path: train/eng_Latn-wos_Latn.jsonl.gz split: train - path: test/eng_Latn-wos_Latn.jsonl.gz split: test - path: validation/eng_Latn-wos_Latn.jsonl.gz split: validation - config_name: eng_Latn-hin_Deva data_files: - path: train/eng_Latn-hin_Deva.jsonl.gz split: train - path: test/eng_Latn-hin_Deva.jsonl.gz split: test - path: validation/eng_Latn-hin_Deva.jsonl.gz split: validation - config_name: eng_Latn-ctu_Latn data_files: - path: train/eng_Latn-ctu_Latn.jsonl.gz split: train - path: test/eng_Latn-ctu_Latn.jsonl.gz split: test - path: validation/eng_Latn-ctu_Latn.jsonl.gz split: validation - config_name: eng_Latn-pes_Arab data_files: - path: train/eng_Latn-pes_Arab.jsonl.gz split: train - path: test/eng_Latn-pes_Arab.jsonl.gz split: test - path: validation/eng_Latn-pes_Arab.jsonl.gz split: validation - config_name: eng_Latn-tbf_Latn data_files: - path: train/eng_Latn-tbf_Latn.jsonl.gz split: train - path: test/eng_Latn-tbf_Latn.jsonl.gz split: test - path: validation/eng_Latn-tbf_Latn.jsonl.gz split: validation - config_name: eng_Latn-bsj_Latn data_files: - path: train/eng_Latn-bsj_Latn.jsonl.gz split: train - path: test/eng_Latn-bsj_Latn.jsonl.gz split: test - path: validation/eng_Latn-bsj_Latn.jsonl.gz split: validation - config_name: eng_Latn-aey_Latn data_files: - path: train/eng_Latn-aey_Latn.jsonl.gz split: train - path: test/eng_Latn-aey_Latn.jsonl.gz split: test - path: validation/eng_Latn-aey_Latn.jsonl.gz split: validation - config_name: eng_Latn-qxn_Latn data_files: - path: train/eng_Latn-qxn_Latn.jsonl.gz split: train - path: test/eng_Latn-qxn_Latn.jsonl.gz split: test - path: validation/eng_Latn-qxn_Latn.jsonl.gz split: validation - config_name: eng_Latn-rug_Latn data_files: - path: train/eng_Latn-rug_Latn.jsonl.gz split: train - path: test/eng_Latn-rug_Latn.jsonl.gz split: test - path: validation/eng_Latn-rug_Latn.jsonl.gz split: validation - config_name: eng_Latn-nwi_Latn data_files: - path: train/eng_Latn-nwi_Latn.jsonl.gz split: train - path: test/eng_Latn-nwi_Latn.jsonl.gz split: test - path: validation/eng_Latn-nwi_Latn.jsonl.gz split: validation - config_name: eng_Latn-spl_Latn data_files: - path: train/eng_Latn-spl_Latn.jsonl.gz split: train - path: test/eng_Latn-spl_Latn.jsonl.gz split: test - path: validation/eng_Latn-spl_Latn.jsonl.gz split: validation - config_name: eng_Latn-kan_Knda data_files: - path: train/eng_Latn-kan_Knda.jsonl.gz split: train - path: test/eng_Latn-kan_Knda.jsonl.gz split: test - path: validation/eng_Latn-kan_Knda.jsonl.gz split: validation - config_name: eng_Latn-dif_Latn data_files: - path: train/eng_Latn-dif_Latn.jsonl.gz split: train - path: test/eng_Latn-dif_Latn.jsonl.gz split: test - path: validation/eng_Latn-dif_Latn.jsonl.gz split: validation - config_name: eng_Latn-cpa_Latn data_files: - path: train/eng_Latn-cpa_Latn.jsonl.gz split: train - path: test/eng_Latn-cpa_Latn.jsonl.gz split: test - path: validation/eng_Latn-cpa_Latn.jsonl.gz split: validation - config_name: eng_Latn-mau_Latn data_files: - path: train/eng_Latn-mau_Latn.jsonl.gz split: train - path: test/eng_Latn-mau_Latn.jsonl.gz split: test - path: validation/eng_Latn-mau_Latn.jsonl.gz split: validation - config_name: eng_Latn-ron_Latn data_files: - path: train/eng_Latn-ron_Latn.jsonl.gz split: train - path: test/eng_Latn-ron_Latn.jsonl.gz split: test - path: validation/eng_Latn-ron_Latn.jsonl.gz split: validation - config_name: eng_Latn-dop_Latn data_files: - path: train/eng_Latn-dop_Latn.jsonl.gz split: train - path: test/eng_Latn-dop_Latn.jsonl.gz split: test - path: validation/eng_Latn-dop_Latn.jsonl.gz split: validation - config_name: eng_Latn-hau_Latn data_files: - path: train/eng_Latn-hau_Latn.jsonl.gz split: train - path: test/eng_Latn-hau_Latn.jsonl.gz split: test - path: validation/eng_Latn-hau_Latn.jsonl.gz split: validation - config_name: eng_Latn-gnn_Latn data_files: - path: train/eng_Latn-gnn_Latn.jsonl.gz split: train - path: test/eng_Latn-gnn_Latn.jsonl.gz split: test - path: validation/eng_Latn-gnn_Latn.jsonl.gz split: validation - config_name: eng_Latn-bsn_Latn data_files: - path: train/eng_Latn-bsn_Latn.jsonl.gz split: train - path: test/eng_Latn-bsn_Latn.jsonl.gz split: test - path: validation/eng_Latn-bsn_Latn.jsonl.gz split: validation - config_name: eng_Latn-kpj_Latn data_files: - path: train/eng_Latn-kpj_Latn.jsonl.gz split: train - path: test/eng_Latn-kpj_Latn.jsonl.gz split: test - path: validation/eng_Latn-kpj_Latn.jsonl.gz split: validation - config_name: eng_Latn-wat_Latn data_files: - path: train/eng_Latn-wat_Latn.jsonl.gz split: train - path: test/eng_Latn-wat_Latn.jsonl.gz split: test - path: validation/eng_Latn-wat_Latn.jsonl.gz split: validation - config_name: eng_Latn-acr_Latn data_files: - path: train/eng_Latn-acr_Latn.jsonl.gz split: train - path: test/eng_Latn-acr_Latn.jsonl.gz split: test - path: validation/eng_Latn-acr_Latn.jsonl.gz split: validation - config_name: eng_Latn-caf_Latn data_files: - path: train/eng_Latn-caf_Latn.jsonl.gz split: train - path: test/eng_Latn-caf_Latn.jsonl.gz split: test - path: validation/eng_Latn-caf_Latn.jsonl.gz split: validation - config_name: eng_Latn-dhg_Latn data_files: - path: train/eng_Latn-dhg_Latn.jsonl.gz split: train - path: test/eng_Latn-dhg_Latn.jsonl.gz split: test - path: validation/eng_Latn-dhg_Latn.jsonl.gz split: validation - config_name: eng_Latn-yml_Latn data_files: - path: train/eng_Latn-yml_Latn.jsonl.gz split: train - path: test/eng_Latn-yml_Latn.jsonl.gz split: test - path: validation/eng_Latn-yml_Latn.jsonl.gz split: validation - config_name: eng_Latn-atd_Latn data_files: - path: train/eng_Latn-atd_Latn.jsonl.gz split: train - path: test/eng_Latn-atd_Latn.jsonl.gz split: test - path: validation/eng_Latn-atd_Latn.jsonl.gz split: validation - config_name: eng_Latn-bbb_Latn data_files: - path: train/eng_Latn-bbb_Latn.jsonl.gz split: train - path: test/eng_Latn-bbb_Latn.jsonl.gz split: test - path: validation/eng_Latn-bbb_Latn.jsonl.gz split: validation - config_name: eng_Latn-cle_Latn data_files: - path: train/eng_Latn-cle_Latn.jsonl.gz split: train - path: test/eng_Latn-cle_Latn.jsonl.gz split: test - path: validation/eng_Latn-cle_Latn.jsonl.gz split: validation - config_name: eng_Latn-myk_Latn data_files: - path: train/eng_Latn-myk_Latn.jsonl.gz split: train - path: test/eng_Latn-myk_Latn.jsonl.gz split: test - path: validation/eng_Latn-myk_Latn.jsonl.gz split: validation - config_name: eng_Latn-bxh_Latn data_files: - path: train/eng_Latn-bxh_Latn.jsonl.gz split: train - path: test/eng_Latn-bxh_Latn.jsonl.gz split: test - path: validation/eng_Latn-bxh_Latn.jsonl.gz split: validation - config_name: eng_Latn-tpa_Latn data_files: - path: train/eng_Latn-tpa_Latn.jsonl.gz split: train - path: test/eng_Latn-tpa_Latn.jsonl.gz split: test - path: validation/eng_Latn-tpa_Latn.jsonl.gz split: validation - config_name: eng_Latn-awk_Latn data_files: - path: train/eng_Latn-awk_Latn.jsonl.gz split: train - path: test/eng_Latn-awk_Latn.jsonl.gz split: test - path: validation/eng_Latn-awk_Latn.jsonl.gz split: validation - config_name: eng_Latn-gfk_Latn data_files: - path: train/eng_Latn-gfk_Latn.jsonl.gz split: train - path: test/eng_Latn-gfk_Latn.jsonl.gz split: test - path: validation/eng_Latn-gfk_Latn.jsonl.gz split: validation - config_name: eng_Latn-mph_Latn data_files: - path: train/eng_Latn-mph_Latn.jsonl.gz split: train - path: test/eng_Latn-mph_Latn.jsonl.gz split: test - path: validation/eng_Latn-mph_Latn.jsonl.gz split: validation - config_name: eng_Latn-csy_Latn data_files: - path: train/eng_Latn-csy_Latn.jsonl.gz split: train - path: test/eng_Latn-csy_Latn.jsonl.gz split: test - path: validation/eng_Latn-csy_Latn.jsonl.gz split: validation - config_name: eng_Latn-tgp_Latn data_files: - path: train/eng_Latn-tgp_Latn.jsonl.gz split: train - path: test/eng_Latn-tgp_Latn.jsonl.gz split: test - path: validation/eng_Latn-tgp_Latn.jsonl.gz split: validation - config_name: eng_Latn-zia_Latn data_files: - path: train/eng_Latn-zia_Latn.jsonl.gz split: train - path: test/eng_Latn-zia_Latn.jsonl.gz split: test - path: validation/eng_Latn-zia_Latn.jsonl.gz split: validation - config_name: eng_Latn-msm_Latn data_files: - path: train/eng_Latn-msm_Latn.jsonl.gz split: train - path: test/eng_Latn-msm_Latn.jsonl.gz split: test - path: validation/eng_Latn-msm_Latn.jsonl.gz split: validation - config_name: eng_Latn-kql_Latn data_files: - path: train/eng_Latn-kql_Latn.jsonl.gz split: train - path: test/eng_Latn-kql_Latn.jsonl.gz split: test - path: validation/eng_Latn-kql_Latn.jsonl.gz split: validation - config_name: eng_Latn-wnu_Latn data_files: - path: train/eng_Latn-wnu_Latn.jsonl.gz split: train - path: test/eng_Latn-wnu_Latn.jsonl.gz split: test - path: validation/eng_Latn-wnu_Latn.jsonl.gz split: validation - config_name: eng_Latn-nin_Latn data_files: - path: train/eng_Latn-nin_Latn.jsonl.gz split: train - path: test/eng_Latn-nin_Latn.jsonl.gz split: test - path: validation/eng_Latn-nin_Latn.jsonl.gz split: validation - config_name: eng_Latn-kmo_Latn data_files: - path: train/eng_Latn-kmo_Latn.jsonl.gz split: train - path: test/eng_Latn-kmo_Latn.jsonl.gz split: test - path: validation/eng_Latn-kmo_Latn.jsonl.gz split: validation - config_name: eng_Latn-mpx_Latn data_files: - path: train/eng_Latn-mpx_Latn.jsonl.gz split: train - path: test/eng_Latn-mpx_Latn.jsonl.gz split: test - path: validation/eng_Latn-mpx_Latn.jsonl.gz split: validation - config_name: eng_Latn-nas_Latn data_files: - path: train/eng_Latn-nas_Latn.jsonl.gz split: train - path: test/eng_Latn-nas_Latn.jsonl.gz split: test - path: validation/eng_Latn-nas_Latn.jsonl.gz split: validation - config_name: eng_Latn-ulk_Latn data_files: - path: train/eng_Latn-ulk_Latn.jsonl.gz split: train - path: test/eng_Latn-ulk_Latn.jsonl.gz split: test - path: validation/eng_Latn-ulk_Latn.jsonl.gz split: validation - config_name: eng_Latn-ipi_Latn data_files: - path: train/eng_Latn-ipi_Latn.jsonl.gz split: train - path: test/eng_Latn-ipi_Latn.jsonl.gz split: test - path: validation/eng_Latn-ipi_Latn.jsonl.gz split: validation - config_name: eng_Latn-mgc_Latn data_files: - path: train/eng_Latn-mgc_Latn.jsonl.gz split: train - path: test/eng_Latn-mgc_Latn.jsonl.gz split: test - path: validation/eng_Latn-mgc_Latn.jsonl.gz split: validation - config_name: eng_Latn-ape_Latn data_files: - path: train/eng_Latn-ape_Latn.jsonl.gz split: train - path: test/eng_Latn-ape_Latn.jsonl.gz split: test - path: validation/eng_Latn-ape_Latn.jsonl.gz split: validation - config_name: eng_Latn-tac_Latn data_files: - path: train/eng_Latn-tac_Latn.jsonl.gz split: train - path: test/eng_Latn-tac_Latn.jsonl.gz split: test - path: validation/eng_Latn-tac_Latn.jsonl.gz split: validation - config_name: eng_Latn-bzd_Latn data_files: - path: train/eng_Latn-bzd_Latn.jsonl.gz split: train - path: test/eng_Latn-bzd_Latn.jsonl.gz split: test - path: validation/eng_Latn-bzd_Latn.jsonl.gz split: validation - config_name: eng_Latn-amm_Latn data_files: - path: train/eng_Latn-amm_Latn.jsonl.gz split: train - path: test/eng_Latn-amm_Latn.jsonl.gz split: test - path: validation/eng_Latn-amm_Latn.jsonl.gz split: validation - config_name: eng_Latn-mic_Latn data_files: - path: train/eng_Latn-mic_Latn.jsonl.gz split: train - path: test/eng_Latn-mic_Latn.jsonl.gz split: test - path: validation/eng_Latn-mic_Latn.jsonl.gz split: validation - config_name: eng_Latn-sxb_Latn data_files: - path: train/eng_Latn-sxb_Latn.jsonl.gz split: train - path: test/eng_Latn-sxb_Latn.jsonl.gz split: test - path: validation/eng_Latn-sxb_Latn.jsonl.gz split: validation - config_name: eng_Latn-cux_Latn data_files: - path: train/eng_Latn-cux_Latn.jsonl.gz split: train - path: test/eng_Latn-cux_Latn.jsonl.gz split: test - path: validation/eng_Latn-cux_Latn.jsonl.gz split: validation - config_name: eng_Latn-ixl_Latn data_files: - path: train/eng_Latn-ixl_Latn.jsonl.gz split: train - path: test/eng_Latn-ixl_Latn.jsonl.gz split: test - path: validation/eng_Latn-ixl_Latn.jsonl.gz split: validation - config_name: eng_Latn-nif_Latn data_files: - path: train/eng_Latn-nif_Latn.jsonl.gz split: train - path: test/eng_Latn-nif_Latn.jsonl.gz split: test - path: validation/eng_Latn-nif_Latn.jsonl.gz split: validation - config_name: eng_Latn-isn_Latn data_files: - path: train/eng_Latn-isn_Latn.jsonl.gz split: train - path: test/eng_Latn-isn_Latn.jsonl.gz split: test - path: validation/eng_Latn-isn_Latn.jsonl.gz split: validation - config_name: eng_Latn-cmn_Hans data_files: - path: train/eng_Latn-cmn_Hans.jsonl.gz split: train - path: test/eng_Latn-cmn_Hans.jsonl.gz split: test - path: validation/eng_Latn-cmn_Hans.jsonl.gz split: validation - config_name: eng_Latn-kyf_Latn data_files: - path: train/eng_Latn-kyf_Latn.jsonl.gz split: train - path: test/eng_Latn-kyf_Latn.jsonl.gz split: test - path: validation/eng_Latn-kyf_Latn.jsonl.gz split: validation - config_name: eng_Latn-cut_Latn data_files: - path: train/eng_Latn-cut_Latn.jsonl.gz split: train - path: test/eng_Latn-cut_Latn.jsonl.gz split: test - path: validation/eng_Latn-cut_Latn.jsonl.gz split: validation - config_name: eng_Latn-lcm_Latn data_files: - path: train/eng_Latn-lcm_Latn.jsonl.gz split: train - path: test/eng_Latn-lcm_Latn.jsonl.gz split: test - path: validation/eng_Latn-lcm_Latn.jsonl.gz split: validation - config_name: eng_Latn-nya_Latn data_files: - path: train/eng_Latn-nya_Latn.jsonl.gz split: train - path: test/eng_Latn-nya_Latn.jsonl.gz split: test - path: validation/eng_Latn-nya_Latn.jsonl.gz split: validation - config_name: eng_Latn-kjs_Latn data_files: - path: train/eng_Latn-kjs_Latn.jsonl.gz split: train - path: test/eng_Latn-kjs_Latn.jsonl.gz split: test - path: validation/eng_Latn-kjs_Latn.jsonl.gz split: validation - config_name: eng_Latn-ton_Latn data_files: - path: train/eng_Latn-ton_Latn.jsonl.gz split: train - path: test/eng_Latn-ton_Latn.jsonl.gz split: test - path: validation/eng_Latn-ton_Latn.jsonl.gz split: validation - config_name: eng_Latn-qvs_Latn data_files: - path: train/eng_Latn-qvs_Latn.jsonl.gz split: train - path: test/eng_Latn-qvs_Latn.jsonl.gz split: test - path: validation/eng_Latn-qvs_Latn.jsonl.gz split: validation - config_name: eng_Latn-ino_Latn data_files: - path: train/eng_Latn-ino_Latn.jsonl.gz split: train - path: test/eng_Latn-ino_Latn.jsonl.gz split: test - path: validation/eng_Latn-ino_Latn.jsonl.gz split: validation - config_name: eng_Latn-zca_Latn data_files: - path: train/eng_Latn-zca_Latn.jsonl.gz split: train - path: test/eng_Latn-zca_Latn.jsonl.gz split: test - path: validation/eng_Latn-zca_Latn.jsonl.gz split: validation - config_name: eng_Latn-xav_Latn data_files: - path: train/eng_Latn-xav_Latn.jsonl.gz split: train - path: test/eng_Latn-xav_Latn.jsonl.gz split: test - path: validation/eng_Latn-xav_Latn.jsonl.gz split: validation - config_name: eng_Latn-jac_Latn data_files: - path: train/eng_Latn-jac_Latn.jsonl.gz split: train - path: test/eng_Latn-jac_Latn.jsonl.gz split: test - path: validation/eng_Latn-jac_Latn.jsonl.gz split: validation - config_name: eng_Latn-quc_Latn data_files: - path: train/eng_Latn-quc_Latn.jsonl.gz split: train - path: test/eng_Latn-quc_Latn.jsonl.gz split: test - path: validation/eng_Latn-quc_Latn.jsonl.gz split: validation - config_name: eng_Latn-npl_Latn data_files: - path: train/eng_Latn-npl_Latn.jsonl.gz split: train - path: test/eng_Latn-npl_Latn.jsonl.gz split: test - path: validation/eng_Latn-npl_Latn.jsonl.gz split: validation - config_name: eng_Latn-usa_Latn data_files: - path: train/eng_Latn-usa_Latn.jsonl.gz split: train - path: test/eng_Latn-usa_Latn.jsonl.gz split: test - path: validation/eng_Latn-usa_Latn.jsonl.gz split: validation - config_name: eng_Latn-kvg_Latn data_files: - path: train/eng_Latn-kvg_Latn.jsonl.gz split: train - path: test/eng_Latn-kvg_Latn.jsonl.gz split: test - path: validation/eng_Latn-kvg_Latn.jsonl.gz split: validation - config_name: eng_Latn-tee_Latn data_files: - path: train/eng_Latn-tee_Latn.jsonl.gz split: train - path: test/eng_Latn-tee_Latn.jsonl.gz split: test - path: validation/eng_Latn-tee_Latn.jsonl.gz split: validation - config_name: eng_Latn-hot_Latn data_files: - path: train/eng_Latn-hot_Latn.jsonl.gz split: train - path: test/eng_Latn-hot_Latn.jsonl.gz split: test - path: validation/eng_Latn-hot_Latn.jsonl.gz split: validation - config_name: eng_Latn-acf_Latn data_files: - path: train/eng_Latn-acf_Latn.jsonl.gz split: train - path: test/eng_Latn-acf_Latn.jsonl.gz split: test - path: validation/eng_Latn-acf_Latn.jsonl.gz split: validation - config_name: eng_Latn-wiu_Latn data_files: - path: train/eng_Latn-wiu_Latn.jsonl.gz split: train - path: test/eng_Latn-wiu_Latn.jsonl.gz split: test - path: validation/eng_Latn-wiu_Latn.jsonl.gz split: validation - config_name: eng_Latn-rmc_Latn data_files: - path: train/eng_Latn-rmc_Latn.jsonl.gz split: train - path: test/eng_Latn-rmc_Latn.jsonl.gz split: test - path: validation/eng_Latn-rmc_Latn.jsonl.gz split: validation - config_name: eng_Latn-snx_Latn data_files: - path: train/eng_Latn-snx_Latn.jsonl.gz split: train - path: test/eng_Latn-snx_Latn.jsonl.gz split: test - path: validation/eng_Latn-snx_Latn.jsonl.gz split: validation - config_name: eng_Latn-jpn_Jpan data_files: - path: train/eng_Latn-jpn_Jpan.jsonl.gz split: train - path: test/eng_Latn-jpn_Jpan.jsonl.gz split: test - path: validation/eng_Latn-jpn_Jpan.jsonl.gz split: validation - config_name: eng_Latn-tbg_Latn data_files: - path: train/eng_Latn-tbg_Latn.jsonl.gz split: train - path: test/eng_Latn-tbg_Latn.jsonl.gz split: test - path: validation/eng_Latn-tbg_Latn.jsonl.gz split: validation - config_name: eng_Latn-pwg_Latn data_files: - path: train/eng_Latn-pwg_Latn.jsonl.gz split: train - path: test/eng_Latn-pwg_Latn.jsonl.gz split: test - path: validation/eng_Latn-pwg_Latn.jsonl.gz split: validation - config_name: eng_Latn-nhr_Latn data_files: - path: train/eng_Latn-nhr_Latn.jsonl.gz split: train - path: test/eng_Latn-nhr_Latn.jsonl.gz split: test - path: validation/eng_Latn-nhr_Latn.jsonl.gz split: validation - config_name: eng_Latn-mwe_Latn data_files: - path: train/eng_Latn-mwe_Latn.jsonl.gz split: train - path: test/eng_Latn-mwe_Latn.jsonl.gz split: test - path: validation/eng_Latn-mwe_Latn.jsonl.gz split: validation - config_name: eng_Latn-kbq_Latn data_files: - path: train/eng_Latn-kbq_Latn.jsonl.gz split: train - path: test/eng_Latn-kbq_Latn.jsonl.gz split: test - path: validation/eng_Latn-kbq_Latn.jsonl.gz split: validation - config_name: eng_Latn-myw_Latn data_files: - path: train/eng_Latn-myw_Latn.jsonl.gz split: train - path: test/eng_Latn-myw_Latn.jsonl.gz split: test - path: validation/eng_Latn-myw_Latn.jsonl.gz split: validation - config_name: eng_Latn-jni_Latn data_files: - path: train/eng_Latn-jni_Latn.jsonl.gz split: train - path: test/eng_Latn-jni_Latn.jsonl.gz split: test - path: validation/eng_Latn-jni_Latn.jsonl.gz split: validation - config_name: eng_Latn-vmy_Latn data_files: - path: train/eng_Latn-vmy_Latn.jsonl.gz split: train - path: test/eng_Latn-vmy_Latn.jsonl.gz split: test - path: validation/eng_Latn-vmy_Latn.jsonl.gz split: validation - config_name: eng_Latn-zpv_Latn data_files: - path: train/eng_Latn-zpv_Latn.jsonl.gz split: train - path: test/eng_Latn-zpv_Latn.jsonl.gz split: test - path: validation/eng_Latn-zpv_Latn.jsonl.gz split: validation - config_name: eng_Latn-heb_Hebr data_files: - path: train/eng_Latn-heb_Hebr.jsonl.gz split: train - path: test/eng_Latn-heb_Hebr.jsonl.gz split: test - path: validation/eng_Latn-heb_Hebr.jsonl.gz split: validation - config_name: eng_Latn-bki_Latn data_files: - path: train/eng_Latn-bki_Latn.jsonl.gz split: train - path: test/eng_Latn-bki_Latn.jsonl.gz split: test - path: validation/eng_Latn-bki_Latn.jsonl.gz split: validation - config_name: eng_Latn-mee_Latn data_files: - path: train/eng_Latn-mee_Latn.jsonl.gz split: train - path: test/eng_Latn-mee_Latn.jsonl.gz split: test - path: validation/eng_Latn-mee_Latn.jsonl.gz split: validation - config_name: eng_Latn-aau_Latn data_files: - path: train/eng_Latn-aau_Latn.jsonl.gz split: train - path: test/eng_Latn-aau_Latn.jsonl.gz split: test - path: validation/eng_Latn-aau_Latn.jsonl.gz split: validation - config_name: eng_Latn-aaz_Latn data_files: - path: train/eng_Latn-aaz_Latn.jsonl.gz split: train - path: test/eng_Latn-aaz_Latn.jsonl.gz split: test - path: validation/eng_Latn-aaz_Latn.jsonl.gz split: validation - config_name: eng_Latn-aoi_Latn data_files: - path: train/eng_Latn-aoi_Latn.jsonl.gz split: train - path: test/eng_Latn-aoi_Latn.jsonl.gz split: test - path: validation/eng_Latn-aoi_Latn.jsonl.gz split: validation - config_name: eng_Latn-caa_Latn data_files: - path: train/eng_Latn-caa_Latn.jsonl.gz split: train - path: test/eng_Latn-caa_Latn.jsonl.gz split: test - path: validation/eng_Latn-caa_Latn.jsonl.gz split: validation - config_name: eng_Latn-zap_Latn data_files: - path: train/eng_Latn-zap_Latn.jsonl.gz split: train - path: test/eng_Latn-zap_Latn.jsonl.gz split: test - path: validation/eng_Latn-zap_Latn.jsonl.gz split: validation - config_name: eng_Latn-amk_Latn data_files: - path: train/eng_Latn-amk_Latn.jsonl.gz split: train - path: test/eng_Latn-amk_Latn.jsonl.gz split: test - path: validation/eng_Latn-amk_Latn.jsonl.gz split: validation - config_name: eng_Latn-zpo_Latn data_files: - path: train/eng_Latn-zpo_Latn.jsonl.gz split: train - path: test/eng_Latn-zpo_Latn.jsonl.gz split: test - path: validation/eng_Latn-zpo_Latn.jsonl.gz split: validation - config_name: eng_Latn-aom_Latn data_files: - path: train/eng_Latn-aom_Latn.jsonl.gz split: train - path: test/eng_Latn-aom_Latn.jsonl.gz split: test - path: validation/eng_Latn-aom_Latn.jsonl.gz split: validation - config_name: eng_Latn-zpu_Latn data_files: - path: train/eng_Latn-zpu_Latn.jsonl.gz split: train - path: test/eng_Latn-zpu_Latn.jsonl.gz split: test - path: validation/eng_Latn-zpu_Latn.jsonl.gz split: validation - config_name: eng_Latn-bdd_Latn data_files: - path: train/eng_Latn-bdd_Latn.jsonl.gz split: train - path: test/eng_Latn-bdd_Latn.jsonl.gz split: test - path: validation/eng_Latn-bdd_Latn.jsonl.gz split: validation - config_name: eng_Latn-acu_Latn data_files: - path: train/eng_Latn-acu_Latn.jsonl.gz split: train - path: test/eng_Latn-acu_Latn.jsonl.gz split: test - path: validation/eng_Latn-acu_Latn.jsonl.gz split: validation - config_name: eng_Latn-beo_Latn data_files: - path: train/eng_Latn-beo_Latn.jsonl.gz split: train - path: test/eng_Latn-beo_Latn.jsonl.gz split: test - path: validation/eng_Latn-beo_Latn.jsonl.gz split: validation - config_name: eng_Latn-cuc_Latn data_files: - path: train/eng_Latn-cuc_Latn.jsonl.gz split: train - path: test/eng_Latn-cuc_Latn.jsonl.gz split: test - path: validation/eng_Latn-cuc_Latn.jsonl.gz split: validation - config_name: eng_Latn-otm_Latn data_files: - path: train/eng_Latn-otm_Latn.jsonl.gz split: train - path: test/eng_Latn-otm_Latn.jsonl.gz split: test - path: validation/eng_Latn-otm_Latn.jsonl.gz split: validation - config_name: eng_Latn-tos_Latn data_files: - path: train/eng_Latn-tos_Latn.jsonl.gz split: train - path: test/eng_Latn-tos_Latn.jsonl.gz split: test - path: validation/eng_Latn-tos_Latn.jsonl.gz split: validation - config_name: eng_Latn-apu_Latn data_files: - path: train/eng_Latn-apu_Latn.jsonl.gz split: train - path: test/eng_Latn-apu_Latn.jsonl.gz split: test - path: validation/eng_Latn-apu_Latn.jsonl.gz split: validation - config_name: eng_Latn-jic_Latn data_files: - path: train/eng_Latn-jic_Latn.jsonl.gz split: train - path: test/eng_Latn-jic_Latn.jsonl.gz split: test - path: validation/eng_Latn-jic_Latn.jsonl.gz split: validation - config_name: eng_Latn-cek_Latn data_files: - path: train/eng_Latn-cek_Latn.jsonl.gz split: train - path: test/eng_Latn-cek_Latn.jsonl.gz split: test - path: validation/eng_Latn-cek_Latn.jsonl.gz split: validation - config_name: eng_Latn-tnp_Latn data_files: - path: train/eng_Latn-tnp_Latn.jsonl.gz split: train - path: test/eng_Latn-tnp_Latn.jsonl.gz split: test - path: validation/eng_Latn-tnp_Latn.jsonl.gz split: validation - config_name: eng_Latn-hns_Latn data_files: - path: train/eng_Latn-hns_Latn.jsonl.gz split: train - path: test/eng_Latn-hns_Latn.jsonl.gz split: test - path: validation/eng_Latn-hns_Latn.jsonl.gz split: validation - config_name: eng_Latn-mpt_Latn data_files: - path: train/eng_Latn-mpt_Latn.jsonl.gz split: train - path: test/eng_Latn-mpt_Latn.jsonl.gz split: test - path: validation/eng_Latn-mpt_Latn.jsonl.gz split: validation - config_name: eng_Latn-kmg_Latn data_files: - path: train/eng_Latn-kmg_Latn.jsonl.gz split: train - path: test/eng_Latn-kmg_Latn.jsonl.gz split: test - path: validation/eng_Latn-kmg_Latn.jsonl.gz split: validation - config_name: eng_Latn-nhg_Latn data_files: - path: train/eng_Latn-nhg_Latn.jsonl.gz split: train - path: test/eng_Latn-nhg_Latn.jsonl.gz split: test - path: validation/eng_Latn-nhg_Latn.jsonl.gz split: validation - config_name: eng_Latn-yle_Latn data_files: - path: train/eng_Latn-yle_Latn.jsonl.gz split: train - path: test/eng_Latn-yle_Latn.jsonl.gz split: test - path: validation/eng_Latn-yle_Latn.jsonl.gz split: validation - config_name: eng_Latn-yka_Latn data_files: - path: train/eng_Latn-yka_Latn.jsonl.gz split: train - path: test/eng_Latn-yka_Latn.jsonl.gz split: test - path: validation/eng_Latn-yka_Latn.jsonl.gz split: validation - config_name: eng_Latn-maj_Latn data_files: - path: train/eng_Latn-maj_Latn.jsonl.gz split: train - path: test/eng_Latn-maj_Latn.jsonl.gz split: test - path: validation/eng_Latn-maj_Latn.jsonl.gz split: validation - config_name: eng_Latn-agt_Latn data_files: - path: train/eng_Latn-agt_Latn.jsonl.gz split: train - path: test/eng_Latn-agt_Latn.jsonl.gz split: test - path: validation/eng_Latn-agt_Latn.jsonl.gz split: validation - config_name: eng_Latn-san_Latn data_files: - path: train/eng_Latn-san_Latn.jsonl.gz split: train - path: test/eng_Latn-san_Latn.jsonl.gz split: test - path: validation/eng_Latn-san_Latn.jsonl.gz split: validation - config_name: eng_Latn-kew_Latn data_files: - path: train/eng_Latn-kew_Latn.jsonl.gz split: train - path: test/eng_Latn-kew_Latn.jsonl.gz split: test - path: validation/eng_Latn-kew_Latn.jsonl.gz split: validation - config_name: eng_Latn-nop_Latn data_files: - path: train/eng_Latn-nop_Latn.jsonl.gz split: train - path: test/eng_Latn-nop_Latn.jsonl.gz split: test - path: validation/eng_Latn-nop_Latn.jsonl.gz split: validation - config_name: eng_Latn-zyp_Latn data_files: - path: train/eng_Latn-zyp_Latn.jsonl.gz split: train - path: test/eng_Latn-zyp_Latn.jsonl.gz split: test - path: validation/eng_Latn-zyp_Latn.jsonl.gz split: validation - config_name: eng_Latn-qvm_Latn data_files: - path: train/eng_Latn-qvm_Latn.jsonl.gz split: train - path: test/eng_Latn-qvm_Latn.jsonl.gz split: test - path: validation/eng_Latn-qvm_Latn.jsonl.gz split: validation - config_name: eng_Latn-mwp_Latn data_files: - path: train/eng_Latn-mwp_Latn.jsonl.gz split: train - path: test/eng_Latn-mwp_Latn.jsonl.gz split: test - path: validation/eng_Latn-mwp_Latn.jsonl.gz split: validation - config_name: eng_Latn-nhw_Latn data_files: - path: train/eng_Latn-nhw_Latn.jsonl.gz split: train - path: test/eng_Latn-nhw_Latn.jsonl.gz split: test - path: validation/eng_Latn-nhw_Latn.jsonl.gz split: validation - config_name: eng_Latn-als_Latn data_files: - path: train/eng_Latn-als_Latn.jsonl.gz split: train - path: test/eng_Latn-als_Latn.jsonl.gz split: test - path: validation/eng_Latn-als_Latn.jsonl.gz split: validation - config_name: eng_Latn-cof_Latn data_files: - path: train/eng_Latn-cof_Latn.jsonl.gz split: train - path: test/eng_Latn-cof_Latn.jsonl.gz split: test - path: validation/eng_Latn-cof_Latn.jsonl.gz split: validation - config_name: eng_Latn-auy_Latn data_files: - path: train/eng_Latn-auy_Latn.jsonl.gz split: train - path: test/eng_Latn-auy_Latn.jsonl.gz split: test - path: validation/eng_Latn-auy_Latn.jsonl.gz split: validation - config_name: eng_Latn-pol_Latn data_files: - path: train/eng_Latn-pol_Latn.jsonl.gz split: train - path: test/eng_Latn-pol_Latn.jsonl.gz split: test - path: validation/eng_Latn-pol_Latn.jsonl.gz split: validation - config_name: eng_Latn-klt_Latn data_files: - path: train/eng_Latn-klt_Latn.jsonl.gz split: train - path: test/eng_Latn-klt_Latn.jsonl.gz split: test - path: validation/eng_Latn-klt_Latn.jsonl.gz split: validation - config_name: eng_Latn-soy_Latn data_files: - path: train/eng_Latn-soy_Latn.jsonl.gz split: train - path: test/eng_Latn-soy_Latn.jsonl.gz split: test - path: validation/eng_Latn-soy_Latn.jsonl.gz split: validation - config_name: eng_Latn-ita_Latn data_files: - path: train/eng_Latn-ita_Latn.jsonl.gz split: train - path: test/eng_Latn-ita_Latn.jsonl.gz split: test - path: validation/eng_Latn-ita_Latn.jsonl.gz split: validation - config_name: eng_Latn-arn_Latn data_files: - path: train/eng_Latn-arn_Latn.jsonl.gz split: train - path: test/eng_Latn-arn_Latn.jsonl.gz split: test - path: validation/eng_Latn-arn_Latn.jsonl.gz split: validation - config_name: eng_Latn-tbz_Latn data_files: - path: train/eng_Latn-tbz_Latn.jsonl.gz split: train - path: test/eng_Latn-tbz_Latn.jsonl.gz split: test - path: validation/eng_Latn-tbz_Latn.jsonl.gz split: validation - config_name: eng_Latn-zaa_Latn data_files: - path: train/eng_Latn-zaa_Latn.jsonl.gz split: train - path: test/eng_Latn-zaa_Latn.jsonl.gz split: test - path: validation/eng_Latn-zaa_Latn.jsonl.gz split: validation - config_name: eng_Latn-meu_Latn data_files: - path: train/eng_Latn-meu_Latn.jsonl.gz split: train - path: test/eng_Latn-meu_Latn.jsonl.gz split: test - path: validation/eng_Latn-meu_Latn.jsonl.gz split: validation - config_name: eng_Latn-zao_Latn data_files: - path: train/eng_Latn-zao_Latn.jsonl.gz split: train - path: test/eng_Latn-zao_Latn.jsonl.gz split: test - path: validation/eng_Latn-zao_Latn.jsonl.gz split: validation - config_name: eng_Latn-mxp_Latn data_files: - path: train/eng_Latn-mxp_Latn.jsonl.gz split: train - path: test/eng_Latn-mxp_Latn.jsonl.gz split: test - path: validation/eng_Latn-mxp_Latn.jsonl.gz split: validation - config_name: eng_Latn-rgu_Latn data_files: - path: train/eng_Latn-rgu_Latn.jsonl.gz split: train - path: test/eng_Latn-rgu_Latn.jsonl.gz split: test - path: validation/eng_Latn-rgu_Latn.jsonl.gz split: validation - config_name: eng_Latn-tnn_Latn data_files: - path: train/eng_Latn-tnn_Latn.jsonl.gz split: train - path: test/eng_Latn-tnn_Latn.jsonl.gz split: test - path: validation/eng_Latn-tnn_Latn.jsonl.gz split: validation - config_name: eng_Latn-uvl_Latn data_files: - path: train/eng_Latn-uvl_Latn.jsonl.gz split: train - path: test/eng_Latn-uvl_Latn.jsonl.gz split: test - path: validation/eng_Latn-uvl_Latn.jsonl.gz split: validation - config_name: eng_Latn-eko_Latn data_files: - path: train/eng_Latn-eko_Latn.jsonl.gz split: train - path: test/eng_Latn-eko_Latn.jsonl.gz split: test - path: validation/eng_Latn-eko_Latn.jsonl.gz split: validation - config_name: eng_Latn-wmt_Latn data_files: - path: train/eng_Latn-wmt_Latn.jsonl.gz split: train - path: test/eng_Latn-wmt_Latn.jsonl.gz split: test - path: validation/eng_Latn-wmt_Latn.jsonl.gz split: validation - config_name: eng_Latn-kup_Latn data_files: - path: train/eng_Latn-kup_Latn.jsonl.gz split: train - path: test/eng_Latn-kup_Latn.jsonl.gz split: test - path: validation/eng_Latn-kup_Latn.jsonl.gz split: validation - config_name: eng_Latn-zai_Latn data_files: - path: train/eng_Latn-zai_Latn.jsonl.gz split: train - path: test/eng_Latn-zai_Latn.jsonl.gz split: test - path: validation/eng_Latn-zai_Latn.jsonl.gz split: validation - config_name: eng_Latn-ebk_Latn data_files: - path: train/eng_Latn-ebk_Latn.jsonl.gz split: train - path: test/eng_Latn-ebk_Latn.jsonl.gz split: test - path: validation/eng_Latn-ebk_Latn.jsonl.gz split: validation - config_name: eng_Latn-vie_Latn data_files: - path: train/eng_Latn-vie_Latn.jsonl.gz split: train - path: test/eng_Latn-vie_Latn.jsonl.gz split: test - path: validation/eng_Latn-vie_Latn.jsonl.gz split: validation - config_name: eng_Latn-azz_Latn data_files: - path: train/eng_Latn-azz_Latn.jsonl.gz split: train - path: test/eng_Latn-azz_Latn.jsonl.gz split: test - path: validation/eng_Latn-azz_Latn.jsonl.gz split: validation - config_name: eng_Latn-wbp_Latn data_files: - path: train/eng_Latn-wbp_Latn.jsonl.gz split: train - path: test/eng_Latn-wbp_Latn.jsonl.gz split: test - path: validation/eng_Latn-wbp_Latn.jsonl.gz split: validation - config_name: eng_Latn-tvk_Latn data_files: - path: train/eng_Latn-tvk_Latn.jsonl.gz split: train - path: test/eng_Latn-tvk_Latn.jsonl.gz split: test - path: validation/eng_Latn-tvk_Latn.jsonl.gz split: validation - config_name: eng_Latn-ote_Latn data_files: - path: train/eng_Latn-ote_Latn.jsonl.gz split: train - path: test/eng_Latn-ote_Latn.jsonl.gz split: test - path: validation/eng_Latn-ote_Latn.jsonl.gz split: validation - config_name: eng_Latn-ubu_Latn data_files: - path: train/eng_Latn-ubu_Latn.jsonl.gz split: train - path: test/eng_Latn-ubu_Latn.jsonl.gz split: test - path: validation/eng_Latn-ubu_Latn.jsonl.gz split: validation - config_name: eng_Latn-zga_Latn data_files: - path: train/eng_Latn-zga_Latn.jsonl.gz split: train - path: test/eng_Latn-zga_Latn.jsonl.gz split: test - path: validation/eng_Latn-zga_Latn.jsonl.gz split: validation - config_name: eng_Latn-bps_Latn data_files: - path: train/eng_Latn-bps_Latn.jsonl.gz split: train - path: test/eng_Latn-bps_Latn.jsonl.gz split: test - path: validation/eng_Latn-bps_Latn.jsonl.gz split: validation - config_name: eng_Latn-swh_Latn data_files: - path: train/eng_Latn-swh_Latn.jsonl.gz split: train - path: test/eng_Latn-swh_Latn.jsonl.gz split: test - path: validation/eng_Latn-swh_Latn.jsonl.gz split: validation - config_name: eng_Latn-ntp_Latn data_files: - path: train/eng_Latn-ntp_Latn.jsonl.gz split: train - path: test/eng_Latn-ntp_Latn.jsonl.gz split: test - path: validation/eng_Latn-ntp_Latn.jsonl.gz split: validation - config_name: eng_Latn-tav_Latn data_files: - path: train/eng_Latn-tav_Latn.jsonl.gz split: train - path: test/eng_Latn-tav_Latn.jsonl.gz split: test - path: validation/eng_Latn-tav_Latn.jsonl.gz split: validation - config_name: eng_Latn-kms_Latn data_files: - path: train/eng_Latn-kms_Latn.jsonl.gz split: train - path: test/eng_Latn-kms_Latn.jsonl.gz split: test - path: validation/eng_Latn-kms_Latn.jsonl.gz split: validation - config_name: eng_Latn-pio_Latn data_files: - path: train/eng_Latn-pio_Latn.jsonl.gz split: train - path: test/eng_Latn-pio_Latn.jsonl.gz split: test - path: validation/eng_Latn-pio_Latn.jsonl.gz split: validation - config_name: eng_Latn-guj_Gujr data_files: - path: train/eng_Latn-guj_Gujr.jsonl.gz split: train - path: test/eng_Latn-guj_Gujr.jsonl.gz split: test - path: validation/eng_Latn-guj_Gujr.jsonl.gz split: validation - config_name: eng_Latn-mbl_Latn data_files: - path: train/eng_Latn-mbl_Latn.jsonl.gz split: train - path: test/eng_Latn-mbl_Latn.jsonl.gz split: test - path: validation/eng_Latn-mbl_Latn.jsonl.gz split: validation - config_name: eng_Latn-aii_Syrc data_files: - path: train/eng_Latn-aii_Syrc.jsonl.gz split: train - path: test/eng_Latn-aii_Syrc.jsonl.gz split: test - path: validation/eng_Latn-aii_Syrc.jsonl.gz split: validation - config_name: eng_Latn-mle_Latn data_files: - path: train/eng_Latn-mle_Latn.jsonl.gz split: train - path: test/eng_Latn-mle_Latn.jsonl.gz split: test - path: validation/eng_Latn-mle_Latn.jsonl.gz split: validation - config_name: eng_Latn-zam_Latn data_files: - path: train/eng_Latn-zam_Latn.jsonl.gz split: train - path: test/eng_Latn-zam_Latn.jsonl.gz split: test - path: validation/eng_Latn-zam_Latn.jsonl.gz split: validation - config_name: eng_Latn-urt_Latn data_files: - path: train/eng_Latn-urt_Latn.jsonl.gz split: train - path: test/eng_Latn-urt_Latn.jsonl.gz split: test - path: validation/eng_Latn-urt_Latn.jsonl.gz split: validation - config_name: eng_Latn-guo_Latn data_files: - path: train/eng_Latn-guo_Latn.jsonl.gz split: train - path: test/eng_Latn-guo_Latn.jsonl.gz split: test - path: validation/eng_Latn-guo_Latn.jsonl.gz split: validation - config_name: eng_Latn-bkd_Latn data_files: - path: train/eng_Latn-bkd_Latn.jsonl.gz split: train - path: test/eng_Latn-bkd_Latn.jsonl.gz split: test - path: validation/eng_Latn-bkd_Latn.jsonl.gz split: validation - config_name: eng_Latn-rmy_Latn data_files: - path: train/eng_Latn-rmy_Latn.jsonl.gz split: train - path: test/eng_Latn-rmy_Latn.jsonl.gz split: test - path: validation/eng_Latn-rmy_Latn.jsonl.gz split: validation - config_name: eng_Latn-ong_Latn data_files: - path: train/eng_Latn-ong_Latn.jsonl.gz split: train - path: test/eng_Latn-ong_Latn.jsonl.gz split: test - path: validation/eng_Latn-ong_Latn.jsonl.gz split: validation - config_name: eng_Latn-mlp_Latn data_files: - path: train/eng_Latn-mlp_Latn.jsonl.gz split: train - path: test/eng_Latn-mlp_Latn.jsonl.gz split: test - path: validation/eng_Latn-mlp_Latn.jsonl.gz split: validation - config_name: eng_Latn-mir_Latn data_files: - path: train/eng_Latn-mir_Latn.jsonl.gz split: train - path: test/eng_Latn-mir_Latn.jsonl.gz split: test - path: validation/eng_Latn-mir_Latn.jsonl.gz split: validation - config_name: eng_Latn-med_Latn data_files: - path: train/eng_Latn-med_Latn.jsonl.gz split: train - path: test/eng_Latn-med_Latn.jsonl.gz split: test - path: validation/eng_Latn-med_Latn.jsonl.gz split: validation - config_name: eng_Latn-bef_Latn data_files: - path: train/eng_Latn-bef_Latn.jsonl.gz split: train - path: test/eng_Latn-bef_Latn.jsonl.gz split: test - path: validation/eng_Latn-bef_Latn.jsonl.gz split: validation - config_name: eng_Latn-yuw_Latn data_files: - path: train/eng_Latn-yuw_Latn.jsonl.gz split: train - path: test/eng_Latn-yuw_Latn.jsonl.gz split: test - path: validation/eng_Latn-yuw_Latn.jsonl.gz split: validation - config_name: eng_Latn-ded_Latn data_files: - path: train/eng_Latn-ded_Latn.jsonl.gz split: train - path: test/eng_Latn-ded_Latn.jsonl.gz split: test - path: validation/eng_Latn-ded_Latn.jsonl.gz split: validation - config_name: eng_Latn-ame_Latn data_files: - path: train/eng_Latn-ame_Latn.jsonl.gz split: train - path: test/eng_Latn-ame_Latn.jsonl.gz split: test - path: validation/eng_Latn-ame_Latn.jsonl.gz split: validation - config_name: eng_Latn-car_Latn data_files: - path: train/eng_Latn-car_Latn.jsonl.gz split: train - path: test/eng_Latn-car_Latn.jsonl.gz split: test - path: validation/eng_Latn-car_Latn.jsonl.gz split: validation - config_name: eng_Latn-chz_Latn data_files: - path: train/eng_Latn-chz_Latn.jsonl.gz split: train - path: test/eng_Latn-chz_Latn.jsonl.gz split: test - path: validation/eng_Latn-chz_Latn.jsonl.gz split: validation - config_name: eng_Latn-ubr_Latn data_files: - path: train/eng_Latn-ubr_Latn.jsonl.gz split: train - path: test/eng_Latn-ubr_Latn.jsonl.gz split: test - path: validation/eng_Latn-ubr_Latn.jsonl.gz split: validation - config_name: eng_Latn-mar_Deva data_files: - path: train/eng_Latn-mar_Deva.jsonl.gz split: train - path: test/eng_Latn-mar_Deva.jsonl.gz split: test - path: validation/eng_Latn-mar_Deva.jsonl.gz split: validation - config_name: eng_Latn-gun_Latn data_files: - path: train/eng_Latn-gun_Latn.jsonl.gz split: train - path: test/eng_Latn-gun_Latn.jsonl.gz split: test - path: validation/eng_Latn-gun_Latn.jsonl.gz split: validation - config_name: eng_Latn-pir_Latn data_files: - path: train/eng_Latn-pir_Latn.jsonl.gz split: train - path: test/eng_Latn-pir_Latn.jsonl.gz split: test - path: validation/eng_Latn-pir_Latn.jsonl.gz split: validation - config_name: eng_Latn-inb_Latn data_files: - path: train/eng_Latn-inb_Latn.jsonl.gz split: train - path: test/eng_Latn-inb_Latn.jsonl.gz split: test - path: validation/eng_Latn-inb_Latn.jsonl.gz split: validation - config_name: eng_Latn-gym_Latn data_files: - path: train/eng_Latn-gym_Latn.jsonl.gz split: train - path: test/eng_Latn-gym_Latn.jsonl.gz split: test - path: validation/eng_Latn-gym_Latn.jsonl.gz split: validation - config_name: eng_Latn-mit_Latn data_files: - path: train/eng_Latn-mit_Latn.jsonl.gz split: train - path: test/eng_Latn-mit_Latn.jsonl.gz split: test - path: validation/eng_Latn-mit_Latn.jsonl.gz split: validation - config_name: eng_Latn-enq_Latn data_files: - path: train/eng_Latn-enq_Latn.jsonl.gz split: train - path: test/eng_Latn-enq_Latn.jsonl.gz split: test - path: validation/eng_Latn-enq_Latn.jsonl.gz split: validation - config_name: eng_Latn-kqf_Latn data_files: - path: train/eng_Latn-kqf_Latn.jsonl.gz split: train - path: test/eng_Latn-kqf_Latn.jsonl.gz split: test - path: validation/eng_Latn-kqf_Latn.jsonl.gz split: validation - config_name: eng_Latn-mbh_Latn data_files: - path: train/eng_Latn-mbh_Latn.jsonl.gz split: train - path: test/eng_Latn-mbh_Latn.jsonl.gz split: test - path: validation/eng_Latn-mbh_Latn.jsonl.gz split: validation - config_name: eng_Latn-xbi_Latn data_files: - path: train/eng_Latn-xbi_Latn.jsonl.gz split: train - path: test/eng_Latn-xbi_Latn.jsonl.gz split: test - path: validation/eng_Latn-xbi_Latn.jsonl.gz split: validation - config_name: eng_Latn-gof_Latn data_files: - path: train/eng_Latn-gof_Latn.jsonl.gz split: train - path: test/eng_Latn-gof_Latn.jsonl.gz split: test - path: validation/eng_Latn-gof_Latn.jsonl.gz split: validation - config_name: eng_Latn-lat_Latn data_files: - path: train/eng_Latn-lat_Latn.jsonl.gz split: train - path: test/eng_Latn-lat_Latn.jsonl.gz split: test - path: validation/eng_Latn-lat_Latn.jsonl.gz split: validation - config_name: eng_Latn-gah_Latn data_files: - path: train/eng_Latn-gah_Latn.jsonl.gz split: train - path: test/eng_Latn-gah_Latn.jsonl.gz split: test - path: validation/eng_Latn-gah_Latn.jsonl.gz split: validation - config_name: eng_Latn-zav_Latn data_files: - path: train/eng_Latn-zav_Latn.jsonl.gz split: train - path: test/eng_Latn-zav_Latn.jsonl.gz split: test - path: validation/eng_Latn-zav_Latn.jsonl.gz split: validation - config_name: eng_Latn-tnc_Latn data_files: - path: train/eng_Latn-tnc_Latn.jsonl.gz split: train - path: test/eng_Latn-tnc_Latn.jsonl.gz split: test - path: validation/eng_Latn-tnc_Latn.jsonl.gz split: validation - config_name: eng_Latn-aso_Latn data_files: - path: train/eng_Latn-aso_Latn.jsonl.gz split: train - path: test/eng_Latn-aso_Latn.jsonl.gz split: test - path: validation/eng_Latn-aso_Latn.jsonl.gz split: validation - config_name: eng_Latn-cax_Latn data_files: - path: train/eng_Latn-cax_Latn.jsonl.gz split: train - path: test/eng_Latn-cax_Latn.jsonl.gz split: test - path: validation/eng_Latn-cax_Latn.jsonl.gz split: validation - config_name: eng_Latn-xtm_Latn data_files: - path: train/eng_Latn-xtm_Latn.jsonl.gz split: train - path: test/eng_Latn-xtm_Latn.jsonl.gz split: test - path: validation/eng_Latn-xtm_Latn.jsonl.gz split: validation - config_name: eng_Latn-llg_Latn data_files: - path: train/eng_Latn-llg_Latn.jsonl.gz split: train - path: test/eng_Latn-llg_Latn.jsonl.gz split: test - path: validation/eng_Latn-llg_Latn.jsonl.gz split: validation - config_name: eng_Latn-pls_Latn data_files: - path: train/eng_Latn-pls_Latn.jsonl.gz split: train - path: test/eng_Latn-pls_Latn.jsonl.gz split: test - path: validation/eng_Latn-pls_Latn.jsonl.gz split: validation - config_name: eng_Latn-nhi_Latn data_files: - path: train/eng_Latn-nhi_Latn.jsonl.gz split: train - path: test/eng_Latn-nhi_Latn.jsonl.gz split: test - path: validation/eng_Latn-nhi_Latn.jsonl.gz split: validation - config_name: eng_Latn-leu_Latn data_files: - path: train/eng_Latn-leu_Latn.jsonl.gz split: train - path: test/eng_Latn-leu_Latn.jsonl.gz split: test - path: validation/eng_Latn-leu_Latn.jsonl.gz split: validation - config_name: eng_Latn-agn_Latn data_files: - path: train/eng_Latn-agn_Latn.jsonl.gz split: train - path: test/eng_Latn-agn_Latn.jsonl.gz split: test - path: validation/eng_Latn-agn_Latn.jsonl.gz split: validation - config_name: eng_Latn-hus_Latn data_files: - path: train/eng_Latn-hus_Latn.jsonl.gz split: train - path: test/eng_Latn-hus_Latn.jsonl.gz split: test - path: validation/eng_Latn-hus_Latn.jsonl.gz split: validation - config_name: eng_Latn-hvn_Latn data_files: - path: train/eng_Latn-hvn_Latn.jsonl.gz split: train - path: test/eng_Latn-hvn_Latn.jsonl.gz split: test - path: validation/eng_Latn-hvn_Latn.jsonl.gz split: validation - config_name: eng_Latn-gup_Latn data_files: - path: train/eng_Latn-gup_Latn.jsonl.gz split: train - path: test/eng_Latn-gup_Latn.jsonl.gz split: test - path: validation/eng_Latn-gup_Latn.jsonl.gz split: validation - config_name: eng_Latn-ncu_Latn data_files: - path: train/eng_Latn-ncu_Latn.jsonl.gz split: train - path: test/eng_Latn-ncu_Latn.jsonl.gz split: test - path: validation/eng_Latn-ncu_Latn.jsonl.gz split: validation - config_name: eng_Latn-ilo_Latn data_files: - path: train/eng_Latn-ilo_Latn.jsonl.gz split: train - path: test/eng_Latn-ilo_Latn.jsonl.gz split: test - path: validation/eng_Latn-ilo_Latn.jsonl.gz split: validation - config_name: eng_Latn-cjv_Latn data_files: - path: train/eng_Latn-cjv_Latn.jsonl.gz split: train - path: test/eng_Latn-cjv_Latn.jsonl.gz split: test - path: validation/eng_Latn-cjv_Latn.jsonl.gz split: validation - config_name: eng_Latn-cbi_Latn data_files: - path: train/eng_Latn-cbi_Latn.jsonl.gz split: train - path: test/eng_Latn-cbi_Latn.jsonl.gz split: test - path: validation/eng_Latn-cbi_Latn.jsonl.gz split: validation - config_name: eng_Latn-sll_Latn data_files: - path: train/eng_Latn-sll_Latn.jsonl.gz split: train - path: test/eng_Latn-sll_Latn.jsonl.gz split: test - path: validation/eng_Latn-sll_Latn.jsonl.gz split: validation - config_name: eng_Latn-gvf_Latn data_files: - path: train/eng_Latn-gvf_Latn.jsonl.gz split: train - path: test/eng_Latn-gvf_Latn.jsonl.gz split: test - path: validation/eng_Latn-gvf_Latn.jsonl.gz split: validation - config_name: eng_Latn-cbk_Latn data_files: - path: train/eng_Latn-cbk_Latn.jsonl.gz split: train - path: test/eng_Latn-cbk_Latn.jsonl.gz split: test - path: validation/eng_Latn-cbk_Latn.jsonl.gz split: validation - config_name: eng_Latn-ctp_Latn data_files: - path: train/eng_Latn-ctp_Latn.jsonl.gz split: train - path: test/eng_Latn-ctp_Latn.jsonl.gz split: test - path: validation/eng_Latn-ctp_Latn.jsonl.gz split: validation - config_name: eng_Latn-rus_Cyrl data_files: - path: train/eng_Latn-rus_Cyrl.jsonl.gz split: train - path: test/eng_Latn-rus_Cyrl.jsonl.gz split: test - path: validation/eng_Latn-rus_Cyrl.jsonl.gz split: validation - config_name: eng_Latn-zpc_Latn data_files: - path: train/eng_Latn-zpc_Latn.jsonl.gz split: train - path: test/eng_Latn-zpc_Latn.jsonl.gz split: test - path: validation/eng_Latn-zpc_Latn.jsonl.gz split: validation - config_name: eng_Latn-dww_Latn data_files: - path: train/eng_Latn-dww_Latn.jsonl.gz split: train - path: test/eng_Latn-dww_Latn.jsonl.gz split: test - path: validation/eng_Latn-dww_Latn.jsonl.gz split: validation - config_name: eng_Latn-haw_Latn data_files: - path: train/eng_Latn-haw_Latn.jsonl.gz split: train - path: test/eng_Latn-haw_Latn.jsonl.gz split: test - path: validation/eng_Latn-haw_Latn.jsonl.gz split: validation - config_name: eng_Latn-hrv_Latn data_files: - path: train/eng_Latn-hrv_Latn.jsonl.gz split: train - path: test/eng_Latn-hrv_Latn.jsonl.gz split: test - path: validation/eng_Latn-hrv_Latn.jsonl.gz split: validation - config_name: eng_Latn-bhg_Latn data_files: - path: train/eng_Latn-bhg_Latn.jsonl.gz split: train - path: test/eng_Latn-bhg_Latn.jsonl.gz split: test - path: validation/eng_Latn-bhg_Latn.jsonl.gz split: validation - config_name: eng_Latn-kyg_Latn data_files: - path: train/eng_Latn-kyg_Latn.jsonl.gz split: train - path: test/eng_Latn-kyg_Latn.jsonl.gz split: test - path: validation/eng_Latn-kyg_Latn.jsonl.gz split: validation - config_name: eng_Latn-are_Latn data_files: - path: train/eng_Latn-are_Latn.jsonl.gz split: train - path: test/eng_Latn-are_Latn.jsonl.gz split: test - path: validation/eng_Latn-are_Latn.jsonl.gz split: validation - config_name: eng_Latn-pma_Latn data_files: - path: train/eng_Latn-pma_Latn.jsonl.gz split: train - path: test/eng_Latn-pma_Latn.jsonl.gz split: test - path: validation/eng_Latn-pma_Latn.jsonl.gz split: validation - config_name: eng_Latn-tcz_Latn data_files: - path: train/eng_Latn-tcz_Latn.jsonl.gz split: train - path: test/eng_Latn-tcz_Latn.jsonl.gz split: test - path: validation/eng_Latn-tcz_Latn.jsonl.gz split: validation - config_name: eng_Latn-mop_Latn data_files: - path: train/eng_Latn-mop_Latn.jsonl.gz split: train - path: test/eng_Latn-mop_Latn.jsonl.gz split: test - path: validation/eng_Latn-mop_Latn.jsonl.gz split: validation - config_name: eng_Latn-maa_Latn data_files: - path: train/eng_Latn-maa_Latn.jsonl.gz split: train - path: test/eng_Latn-maa_Latn.jsonl.gz split: test - path: validation/eng_Latn-maa_Latn.jsonl.gz split: validation - config_name: eng_Latn-row_Latn data_files: - path: train/eng_Latn-row_Latn.jsonl.gz split: train - path: test/eng_Latn-row_Latn.jsonl.gz split: test - path: validation/eng_Latn-row_Latn.jsonl.gz split: validation - config_name: eng_Latn-mcp_Latn data_files: - path: train/eng_Latn-mcp_Latn.jsonl.gz split: train - path: test/eng_Latn-mcp_Latn.jsonl.gz split: test - path: validation/eng_Latn-mcp_Latn.jsonl.gz split: validation - config_name: eng_Latn-bjv_Latn data_files: - path: train/eng_Latn-bjv_Latn.jsonl.gz split: train - path: test/eng_Latn-bjv_Latn.jsonl.gz split: test - path: validation/eng_Latn-bjv_Latn.jsonl.gz split: validation - config_name: eng_Latn-dan_Latn data_files: - path: train/eng_Latn-dan_Latn.jsonl.gz split: train - path: test/eng_Latn-dan_Latn.jsonl.gz split: test - path: validation/eng_Latn-dan_Latn.jsonl.gz split: validation - config_name: eng_Latn-kpw_Latn data_files: - path: train/eng_Latn-kpw_Latn.jsonl.gz split: train - path: test/eng_Latn-kpw_Latn.jsonl.gz split: test - path: validation/eng_Latn-kpw_Latn.jsonl.gz split: validation - config_name: eng_Latn-yal_Latn data_files: - path: train/eng_Latn-yal_Latn.jsonl.gz split: train - path: test/eng_Latn-yal_Latn.jsonl.gz split: test - path: validation/eng_Latn-yal_Latn.jsonl.gz split: validation - config_name: eng_Latn-yrb_Latn data_files: - path: train/eng_Latn-yrb_Latn.jsonl.gz split: train - path: test/eng_Latn-yrb_Latn.jsonl.gz split: test - path: validation/eng_Latn-yrb_Latn.jsonl.gz split: validation - config_name: eng_Latn-piu_Latn data_files: - path: train/eng_Latn-piu_Latn.jsonl.gz split: train - path: test/eng_Latn-piu_Latn.jsonl.gz split: test - path: validation/eng_Latn-piu_Latn.jsonl.gz split: validation - config_name: eng_Latn-kqa_Latn data_files: - path: train/eng_Latn-kqa_Latn.jsonl.gz split: train - path: test/eng_Latn-kqa_Latn.jsonl.gz split: test - path: validation/eng_Latn-kqa_Latn.jsonl.gz split: validation - config_name: eng_Latn-buk_Latn data_files: - path: train/eng_Latn-buk_Latn.jsonl.gz split: train - path: test/eng_Latn-buk_Latn.jsonl.gz split: test - path: validation/eng_Latn-buk_Latn.jsonl.gz split: validation - config_name: eng_Latn-taw_Latn data_files: - path: train/eng_Latn-taw_Latn.jsonl.gz split: train - path: test/eng_Latn-taw_Latn.jsonl.gz split: test - path: validation/eng_Latn-taw_Latn.jsonl.gz split: validation - config_name: eng_Latn-bzj_Latn data_files: - path: train/eng_Latn-bzj_Latn.jsonl.gz split: train - path: test/eng_Latn-bzj_Latn.jsonl.gz split: test - path: validation/eng_Latn-bzj_Latn.jsonl.gz split: validation - config_name: eng_Latn-boa_Latn data_files: - path: train/eng_Latn-boa_Latn.jsonl.gz split: train - path: test/eng_Latn-boa_Latn.jsonl.gz split: test - path: validation/eng_Latn-boa_Latn.jsonl.gz split: validation - config_name: eng_Latn-sua_Latn data_files: - path: train/eng_Latn-sua_Latn.jsonl.gz split: train - path: test/eng_Latn-sua_Latn.jsonl.gz split: test - path: validation/eng_Latn-sua_Latn.jsonl.gz split: validation - config_name: eng_Latn-mwf_Latn data_files: - path: train/eng_Latn-mwf_Latn.jsonl.gz split: train - path: test/eng_Latn-mwf_Latn.jsonl.gz split: test - path: validation/eng_Latn-mwf_Latn.jsonl.gz split: validation - config_name: eng_Latn-deu_Latn data_files: - path: train/eng_Latn-deu_Latn.jsonl.gz split: train - path: test/eng_Latn-deu_Latn.jsonl.gz split: test - path: validation/eng_Latn-deu_Latn.jsonl.gz split: validation - config_name: eng_Latn-ura_Latn data_files: - path: train/eng_Latn-ura_Latn.jsonl.gz split: train - path: test/eng_Latn-ura_Latn.jsonl.gz split: test - path: validation/eng_Latn-ura_Latn.jsonl.gz split: validation - config_name: eng_Latn-aui_Latn data_files: - path: train/eng_Latn-aui_Latn.jsonl.gz split: train - path: test/eng_Latn-aui_Latn.jsonl.gz split: test - path: validation/eng_Latn-aui_Latn.jsonl.gz split: validation - config_name: eng_Latn-wim_Latn data_files: - path: train/eng_Latn-wim_Latn.jsonl.gz split: train - path: test/eng_Latn-wim_Latn.jsonl.gz split: test - path: validation/eng_Latn-wim_Latn.jsonl.gz split: validation - config_name: eng_Latn-bzh_Latn data_files: - path: train/eng_Latn-bzh_Latn.jsonl.gz split: train - path: test/eng_Latn-bzh_Latn.jsonl.gz split: test - path: validation/eng_Latn-bzh_Latn.jsonl.gz split: validation - config_name: eng_Latn-nld_Latn data_files: - path: train/eng_Latn-nld_Latn.jsonl.gz split: train - path: test/eng_Latn-nld_Latn.jsonl.gz split: test - path: validation/eng_Latn-nld_Latn.jsonl.gz split: validation - config_name: eng_Latn-ory_Orya data_files: - path: train/eng_Latn-ory_Orya.jsonl.gz split: train - path: test/eng_Latn-ory_Orya.jsonl.gz split: test - path: validation/eng_Latn-ory_Orya.jsonl.gz split: validation - config_name: eng_Latn-ppo_Latn data_files: - path: train/eng_Latn-ppo_Latn.jsonl.gz split: train - path: test/eng_Latn-ppo_Latn.jsonl.gz split: test - path: validation/eng_Latn-ppo_Latn.jsonl.gz split: validation - config_name: eng_Latn-epo_Latn data_files: - path: train/eng_Latn-epo_Latn.jsonl.gz split: train - path: test/eng_Latn-epo_Latn.jsonl.gz split: test - path: validation/eng_Latn-epo_Latn.jsonl.gz split: validation - config_name: eng_Latn-hop_Latn data_files: - path: train/eng_Latn-hop_Latn.jsonl.gz split: train - path: test/eng_Latn-hop_Latn.jsonl.gz split: test - path: validation/eng_Latn-hop_Latn.jsonl.gz split: validation - config_name: eng_Latn-gdn_Latn data_files: - path: train/eng_Latn-gdn_Latn.jsonl.gz split: train - path: test/eng_Latn-gdn_Latn.jsonl.gz split: test - path: validation/eng_Latn-gdn_Latn.jsonl.gz split: validation - config_name: eng_Latn-tlf_Latn data_files: - path: train/eng_Latn-tlf_Latn.jsonl.gz split: train - path: test/eng_Latn-tlf_Latn.jsonl.gz split: test - path: validation/eng_Latn-tlf_Latn.jsonl.gz split: validation - config_name: eng_Latn-tiw_Latn data_files: - path: train/eng_Latn-tiw_Latn.jsonl.gz split: train - path: test/eng_Latn-tiw_Latn.jsonl.gz split: test - path: validation/eng_Latn-tiw_Latn.jsonl.gz split: validation - config_name: eng_Latn-sja_Latn data_files: - path: train/eng_Latn-sja_Latn.jsonl.gz split: train - path: test/eng_Latn-sja_Latn.jsonl.gz split: test - path: validation/eng_Latn-sja_Latn.jsonl.gz split: validation - config_name: eng_Latn-kdl_Latn data_files: - path: train/eng_Latn-kdl_Latn.jsonl.gz split: train - path: test/eng_Latn-kdl_Latn.jsonl.gz split: test - path: validation/eng_Latn-kdl_Latn.jsonl.gz split: validation - config_name: eng_Latn-chk_Latn data_files: - path: train/eng_Latn-chk_Latn.jsonl.gz split: train - path: test/eng_Latn-chk_Latn.jsonl.gz split: test - path: validation/eng_Latn-chk_Latn.jsonl.gz split: validation - config_name: eng_Latn-kdc_Latn data_files: - path: train/eng_Latn-kdc_Latn.jsonl.gz split: train - path: test/eng_Latn-kdc_Latn.jsonl.gz split: test - path: validation/eng_Latn-kdc_Latn.jsonl.gz split: validation - config_name: eng_Latn-gng_Latn data_files: - path: train/eng_Latn-gng_Latn.jsonl.gz split: train - path: test/eng_Latn-gng_Latn.jsonl.gz split: test - path: validation/eng_Latn-gng_Latn.jsonl.gz split: validation - config_name: eng_Latn-nko_Latn data_files: - path: train/eng_Latn-nko_Latn.jsonl.gz split: train - path: test/eng_Latn-nko_Latn.jsonl.gz split: test - path: validation/eng_Latn-nko_Latn.jsonl.gz split: validation - config_name: eng_Latn-wer_Latn data_files: - path: train/eng_Latn-wer_Latn.jsonl.gz split: train - path: test/eng_Latn-wer_Latn.jsonl.gz split: test - path: validation/eng_Latn-wer_Latn.jsonl.gz split: validation - config_name: eng_Latn-mhl_Latn data_files: - path: train/eng_Latn-mhl_Latn.jsonl.gz split: train - path: test/eng_Latn-mhl_Latn.jsonl.gz split: test - path: validation/eng_Latn-mhl_Latn.jsonl.gz split: validation - config_name: eng_Latn-toc_Latn data_files: - path: train/eng_Latn-toc_Latn.jsonl.gz split: train - path: test/eng_Latn-toc_Latn.jsonl.gz split: test - path: validation/eng_Latn-toc_Latn.jsonl.gz split: validation - config_name: eng_Latn-cbs_Latn data_files: - path: train/eng_Latn-cbs_Latn.jsonl.gz split: train - path: test/eng_Latn-cbs_Latn.jsonl.gz split: test - path: validation/eng_Latn-cbs_Latn.jsonl.gz split: validation - config_name: eng_Latn-qub_Latn data_files: - path: train/eng_Latn-qub_Latn.jsonl.gz split: train - path: test/eng_Latn-qub_Latn.jsonl.gz split: test - path: validation/eng_Latn-qub_Latn.jsonl.gz split: validation - config_name: eng_Latn-auc_Latn data_files: - path: train/eng_Latn-auc_Latn.jsonl.gz split: train - path: test/eng_Latn-auc_Latn.jsonl.gz split: test - path: validation/eng_Latn-auc_Latn.jsonl.gz split: validation - config_name: eng_Latn-kpr_Latn data_files: - path: train/eng_Latn-kpr_Latn.jsonl.gz split: train - path: test/eng_Latn-kpr_Latn.jsonl.gz split: test - path: validation/eng_Latn-kpr_Latn.jsonl.gz split: validation - config_name: eng_Latn-hat_Latn data_files: - path: train/eng_Latn-hat_Latn.jsonl.gz split: train - path: test/eng_Latn-hat_Latn.jsonl.gz split: test - path: validation/eng_Latn-hat_Latn.jsonl.gz split: validation - config_name: eng_Latn-sny_Latn data_files: - path: train/eng_Latn-sny_Latn.jsonl.gz split: train - path: test/eng_Latn-sny_Latn.jsonl.gz split: test - path: validation/eng_Latn-sny_Latn.jsonl.gz split: validation - config_name: eng_Latn-byr_Latn data_files: - path: train/eng_Latn-byr_Latn.jsonl.gz split: train - path: test/eng_Latn-byr_Latn.jsonl.gz split: test - path: validation/eng_Latn-byr_Latn.jsonl.gz split: validation - config_name: eng_Latn-emp_Latn data_files: - path: train/eng_Latn-emp_Latn.jsonl.gz split: train - path: test/eng_Latn-emp_Latn.jsonl.gz split: test - path: validation/eng_Latn-emp_Latn.jsonl.gz split: validation - config_name: eng_Latn-kwi_Latn data_files: - path: train/eng_Latn-kwi_Latn.jsonl.gz split: train - path: test/eng_Latn-kwi_Latn.jsonl.gz split: test - path: validation/eng_Latn-kwi_Latn.jsonl.gz split: validation - config_name: eng_Latn-gum_Latn data_files: - path: train/eng_Latn-gum_Latn.jsonl.gz split: train - path: test/eng_Latn-gum_Latn.jsonl.gz split: test - path: validation/eng_Latn-gum_Latn.jsonl.gz split: validation - config_name: eng_Latn-mbj_Latn data_files: - path: train/eng_Latn-mbj_Latn.jsonl.gz split: train - path: test/eng_Latn-mbj_Latn.jsonl.gz split: test - path: validation/eng_Latn-mbj_Latn.jsonl.gz split: validation - config_name: eng_Latn-sey_Latn data_files: - path: train/eng_Latn-sey_Latn.jsonl.gz split: train - path: test/eng_Latn-sey_Latn.jsonl.gz split: test - path: validation/eng_Latn-sey_Latn.jsonl.gz split: validation - config_name: eng_Latn-alp_Latn data_files: - path: train/eng_Latn-alp_Latn.jsonl.gz split: train - path: test/eng_Latn-alp_Latn.jsonl.gz split: test - path: validation/eng_Latn-alp_Latn.jsonl.gz split: validation - config_name: eng_Latn-gmv_Latn data_files: - path: train/eng_Latn-gmv_Latn.jsonl.gz split: train - path: test/eng_Latn-gmv_Latn.jsonl.gz split: test - path: validation/eng_Latn-gmv_Latn.jsonl.gz split: validation - config_name: eng_Latn-poe_Latn data_files: - path: train/eng_Latn-poe_Latn.jsonl.gz split: train - path: test/eng_Latn-poe_Latn.jsonl.gz split: test - path: validation/eng_Latn-poe_Latn.jsonl.gz split: validation - config_name: eng_Latn-etr_Latn data_files: - path: train/eng_Latn-etr_Latn.jsonl.gz split: train - path: test/eng_Latn-etr_Latn.jsonl.gz split: test - path: validation/eng_Latn-etr_Latn.jsonl.gz split: validation - config_name: eng_Latn-abt_Latn data_files: - path: train/eng_Latn-abt_Latn.jsonl.gz split: train - path: test/eng_Latn-abt_Latn.jsonl.gz split: test - path: validation/eng_Latn-abt_Latn.jsonl.gz split: validation - config_name: eng_Latn-tuf_Latn data_files: - path: train/eng_Latn-tuf_Latn.jsonl.gz split: train - path: test/eng_Latn-tuf_Latn.jsonl.gz split: test - path: validation/eng_Latn-tuf_Latn.jsonl.gz split: validation - config_name: eng_Latn-dob_Latn data_files: - path: train/eng_Latn-dob_Latn.jsonl.gz split: train - path: test/eng_Latn-dob_Latn.jsonl.gz split: test - path: validation/eng_Latn-dob_Latn.jsonl.gz split: validation - config_name: eng_Latn-nys_Latn data_files: - path: train/eng_Latn-nys_Latn.jsonl.gz split: train - path: test/eng_Latn-nys_Latn.jsonl.gz split: test - path: validation/eng_Latn-nys_Latn.jsonl.gz split: validation - config_name: eng_Latn-srn_Latn data_files: - path: train/eng_Latn-srn_Latn.jsonl.gz split: train - path: test/eng_Latn-srn_Latn.jsonl.gz split: test - path: validation/eng_Latn-srn_Latn.jsonl.gz split: validation - config_name: eng_Latn-kpf_Latn data_files: - path: train/eng_Latn-kpf_Latn.jsonl.gz split: train - path: test/eng_Latn-kpf_Latn.jsonl.gz split: test - path: validation/eng_Latn-kpf_Latn.jsonl.gz split: validation - config_name: eng_Latn-mbt_Latn data_files: - path: train/eng_Latn-mbt_Latn.jsonl.gz split: train - path: test/eng_Latn-mbt_Latn.jsonl.gz split: test - path: validation/eng_Latn-mbt_Latn.jsonl.gz split: validation - config_name: eng_Latn-stp_Latn data_files: - path: train/eng_Latn-stp_Latn.jsonl.gz split: train - path: test/eng_Latn-stp_Latn.jsonl.gz split: test - path: validation/eng_Latn-stp_Latn.jsonl.gz split: validation - config_name: eng_Latn-trc_Latn data_files: - path: train/eng_Latn-trc_Latn.jsonl.gz split: train - path: test/eng_Latn-trc_Latn.jsonl.gz split: test - path: validation/eng_Latn-trc_Latn.jsonl.gz split: validation - config_name: eng_Latn-for_Latn data_files: - path: train/eng_Latn-for_Latn.jsonl.gz split: train - path: test/eng_Latn-for_Latn.jsonl.gz split: test - path: validation/eng_Latn-for_Latn.jsonl.gz split: validation - config_name: eng_Latn-yad_Latn data_files: - path: train/eng_Latn-yad_Latn.jsonl.gz split: train - path: test/eng_Latn-yad_Latn.jsonl.gz split: test - path: validation/eng_Latn-yad_Latn.jsonl.gz split: validation - config_name: eng_Latn-cme_Latn data_files: - path: train/eng_Latn-cme_Latn.jsonl.gz split: train - path: test/eng_Latn-cme_Latn.jsonl.gz split: test - path: validation/eng_Latn-cme_Latn.jsonl.gz split: validation - config_name: eng_Latn-bba_Latn data_files: - path: train/eng_Latn-bba_Latn.jsonl.gz split: train - path: test/eng_Latn-bba_Latn.jsonl.gz split: test - path: validation/eng_Latn-bba_Latn.jsonl.gz split: validation - config_name: eng_Latn-mxq_Latn data_files: - path: train/eng_Latn-mxq_Latn.jsonl.gz split: train - path: test/eng_Latn-mxq_Latn.jsonl.gz split: test - path: validation/eng_Latn-mxq_Latn.jsonl.gz split: validation - config_name: eng_Latn-dwy_Latn data_files: - path: train/eng_Latn-dwy_Latn.jsonl.gz split: train - path: test/eng_Latn-dwy_Latn.jsonl.gz split: test - path: validation/eng_Latn-dwy_Latn.jsonl.gz split: validation - config_name: eng_Latn-atg_Latn data_files: - path: train/eng_Latn-atg_Latn.jsonl.gz split: train - path: test/eng_Latn-atg_Latn.jsonl.gz split: test - path: validation/eng_Latn-atg_Latn.jsonl.gz split: validation - config_name: eng_Latn-ncj_Latn data_files: - path: train/eng_Latn-ncj_Latn.jsonl.gz split: train - path: test/eng_Latn-ncj_Latn.jsonl.gz split: test - path: validation/eng_Latn-ncj_Latn.jsonl.gz split: validation - config_name: eng_Latn-mpm_Latn data_files: - path: train/eng_Latn-mpm_Latn.jsonl.gz split: train - path: test/eng_Latn-mpm_Latn.jsonl.gz split: test - path: validation/eng_Latn-mpm_Latn.jsonl.gz split: validation - config_name: eng_Latn-kqc_Latn data_files: - path: train/eng_Latn-kqc_Latn.jsonl.gz split: train - path: test/eng_Latn-kqc_Latn.jsonl.gz split: test - path: validation/eng_Latn-kqc_Latn.jsonl.gz split: validation - config_name: eng_Latn-knv_Latn data_files: - path: train/eng_Latn-knv_Latn.jsonl.gz split: train - path: test/eng_Latn-knv_Latn.jsonl.gz split: test - path: validation/eng_Latn-knv_Latn.jsonl.gz split: validation - config_name: eng_Latn-upv_Latn data_files: - path: train/eng_Latn-upv_Latn.jsonl.gz split: train - path: test/eng_Latn-upv_Latn.jsonl.gz split: test - path: validation/eng_Latn-upv_Latn.jsonl.gz split: validation - config_name: eng_Latn-yut_Latn data_files: - path: train/eng_Latn-yut_Latn.jsonl.gz split: train - path: test/eng_Latn-yut_Latn.jsonl.gz split: test - path: validation/eng_Latn-yut_Latn.jsonl.gz split: validation - config_name: eng_Latn-kje_Latn data_files: - path: train/eng_Latn-kje_Latn.jsonl.gz split: train - path: test/eng_Latn-kje_Latn.jsonl.gz split: test - path: validation/eng_Latn-kje_Latn.jsonl.gz split: validation - config_name: eng_Latn-okv_Latn data_files: - path: train/eng_Latn-okv_Latn.jsonl.gz split: train - path: test/eng_Latn-okv_Latn.jsonl.gz split: test - path: validation/eng_Latn-okv_Latn.jsonl.gz split: validation - config_name: eng_Latn-tof_Latn data_files: - path: train/eng_Latn-tof_Latn.jsonl.gz split: train - path: test/eng_Latn-tof_Latn.jsonl.gz split: test - path: validation/eng_Latn-tof_Latn.jsonl.gz split: validation - config_name: eng_Latn-faa_Latn data_files: - path: train/eng_Latn-faa_Latn.jsonl.gz split: train - path: test/eng_Latn-faa_Latn.jsonl.gz split: test - path: validation/eng_Latn-faa_Latn.jsonl.gz split: validation - config_name: eng_Latn-mya_Latn data_files: - path: train/eng_Latn-mya_Latn.jsonl.gz split: train - path: test/eng_Latn-mya_Latn.jsonl.gz split: test - path: validation/eng_Latn-mya_Latn.jsonl.gz split: validation - config_name: eng_Latn-hto_Latn data_files: - path: train/eng_Latn-hto_Latn.jsonl.gz split: train - path: test/eng_Latn-hto_Latn.jsonl.gz split: test - path: validation/eng_Latn-hto_Latn.jsonl.gz split: validation - config_name: eng_Latn-wiv_Latn data_files: - path: train/eng_Latn-wiv_Latn.jsonl.gz split: train - path: test/eng_Latn-wiv_Latn.jsonl.gz split: test - path: validation/eng_Latn-wiv_Latn.jsonl.gz split: validation - config_name: eng_Latn-vid_Latn data_files: - path: train/eng_Latn-vid_Latn.jsonl.gz split: train - path: test/eng_Latn-vid_Latn.jsonl.gz split: test - path: validation/eng_Latn-vid_Latn.jsonl.gz split: validation - config_name: eng_Latn-xla_Latn data_files: - path: train/eng_Latn-xla_Latn.jsonl.gz split: train - path: test/eng_Latn-xla_Latn.jsonl.gz split: test - path: validation/eng_Latn-xla_Latn.jsonl.gz split: validation - config_name: eng_Latn-snn_Latn data_files: - path: train/eng_Latn-snn_Latn.jsonl.gz split: train - path: test/eng_Latn-snn_Latn.jsonl.gz split: test - path: validation/eng_Latn-snn_Latn.jsonl.gz split: validation - config_name: eng_Latn-ycn_Latn data_files: - path: train/eng_Latn-ycn_Latn.jsonl.gz split: train - path: test/eng_Latn-ycn_Latn.jsonl.gz split: test - path: validation/eng_Latn-ycn_Latn.jsonl.gz split: validation - config_name: eng_Latn-mcb_Latn data_files: - path: train/eng_Latn-mcb_Latn.jsonl.gz split: train - path: test/eng_Latn-mcb_Latn.jsonl.gz split: test - path: validation/eng_Latn-mcb_Latn.jsonl.gz split: validation - config_name: eng_Latn-mal_Mlym data_files: - path: train/eng_Latn-mal_Mlym.jsonl.gz split: train - path: test/eng_Latn-mal_Mlym.jsonl.gz split: test - path: validation/eng_Latn-mal_Mlym.jsonl.gz split: validation - config_name: eng_Latn-sgb_Latn data_files: - path: train/eng_Latn-sgb_Latn.jsonl.gz split: train - path: test/eng_Latn-sgb_Latn.jsonl.gz split: test - path: validation/eng_Latn-sgb_Latn.jsonl.gz split: validation - config_name: eng_Latn-box_Latn data_files: - path: train/eng_Latn-box_Latn.jsonl.gz split: train - path: test/eng_Latn-box_Latn.jsonl.gz split: test - path: validation/eng_Latn-box_Latn.jsonl.gz split: validation - config_name: eng_Latn-amu_Latn data_files: - path: train/eng_Latn-amu_Latn.jsonl.gz split: train - path: test/eng_Latn-amu_Latn.jsonl.gz split: test - path: validation/eng_Latn-amu_Latn.jsonl.gz split: validation - config_name: eng_Latn-cni_Latn data_files: - path: train/eng_Latn-cni_Latn.jsonl.gz split: train - path: test/eng_Latn-cni_Latn.jsonl.gz split: test - path: validation/eng_Latn-cni_Latn.jsonl.gz split: validation - config_name: eng_Latn-byx_Latn data_files: - path: train/eng_Latn-byx_Latn.jsonl.gz split: train - path: test/eng_Latn-byx_Latn.jsonl.gz split: test - path: validation/eng_Latn-byx_Latn.jsonl.gz split: validation - config_name: eng_Latn-udu_Latn data_files: - path: train/eng_Latn-udu_Latn.jsonl.gz split: train - path: test/eng_Latn-udu_Latn.jsonl.gz split: test - path: validation/eng_Latn-udu_Latn.jsonl.gz split: validation - config_name: eng_Latn-jid_Latn data_files: - path: train/eng_Latn-jid_Latn.jsonl.gz split: train - path: test/eng_Latn-jid_Latn.jsonl.gz split: test - path: validation/eng_Latn-jid_Latn.jsonl.gz split: validation - config_name: eng_Latn-nlg_Latn data_files: - path: train/eng_Latn-nlg_Latn.jsonl.gz split: train - path: test/eng_Latn-nlg_Latn.jsonl.gz split: test - path: validation/eng_Latn-nlg_Latn.jsonl.gz split: validation - config_name: eng_Latn-wuv_Latn data_files: - path: train/eng_Latn-wuv_Latn.jsonl.gz split: train - path: test/eng_Latn-wuv_Latn.jsonl.gz split: test - path: validation/eng_Latn-wuv_Latn.jsonl.gz split: validation - config_name: eng_Latn-mto_Latn data_files: - path: train/eng_Latn-mto_Latn.jsonl.gz split: train - path: test/eng_Latn-mto_Latn.jsonl.gz split: test - path: validation/eng_Latn-mto_Latn.jsonl.gz split: validation - config_name: eng_Latn-mcd_Latn data_files: - path: train/eng_Latn-mcd_Latn.jsonl.gz split: train - path: test/eng_Latn-mcd_Latn.jsonl.gz split: test - path: validation/eng_Latn-mcd_Latn.jsonl.gz split: validation - config_name: eng_Latn-bus_Latn data_files: - path: train/eng_Latn-bus_Latn.jsonl.gz split: train - path: test/eng_Latn-bus_Latn.jsonl.gz split: test - path: validation/eng_Latn-bus_Latn.jsonl.gz split: validation - config_name: eng_Latn-glk_Arab data_files: - path: train/eng_Latn-glk_Arab.jsonl.gz split: train - path: test/eng_Latn-glk_Arab.jsonl.gz split: test - path: validation/eng_Latn-glk_Arab.jsonl.gz split: validation - config_name: eng_Latn-too_Latn data_files: - path: train/eng_Latn-too_Latn.jsonl.gz split: train - path: test/eng_Latn-too_Latn.jsonl.gz split: test - path: validation/eng_Latn-too_Latn.jsonl.gz split: validation - config_name: eng_Latn-mpp_Latn data_files: - path: train/eng_Latn-mpp_Latn.jsonl.gz split: train - path: test/eng_Latn-mpp_Latn.jsonl.gz split: test - path: validation/eng_Latn-mpp_Latn.jsonl.gz split: validation - config_name: eng_Latn-zaj_Latn data_files: - path: train/eng_Latn-zaj_Latn.jsonl.gz split: train - path: test/eng_Latn-zaj_Latn.jsonl.gz split: test - path: validation/eng_Latn-zaj_Latn.jsonl.gz split: validation - config_name: eng_Latn-yva_Latn data_files: - path: train/eng_Latn-yva_Latn.jsonl.gz split: train - path: test/eng_Latn-yva_Latn.jsonl.gz split: test - path: validation/eng_Latn-yva_Latn.jsonl.gz split: validation - config_name: eng_Latn-awx_Latn data_files: - path: train/eng_Latn-awx_Latn.jsonl.gz split: train - path: test/eng_Latn-awx_Latn.jsonl.gz split: test - path: validation/eng_Latn-awx_Latn.jsonl.gz split: validation - config_name: eng_Latn-ian_Latn data_files: - path: train/eng_Latn-ian_Latn.jsonl.gz split: train - path: test/eng_Latn-ian_Latn.jsonl.gz split: test - path: validation/eng_Latn-ian_Latn.jsonl.gz split: validation - config_name: eng_Latn-otq_Latn data_files: - path: train/eng_Latn-otq_Latn.jsonl.gz split: train - path: test/eng_Latn-otq_Latn.jsonl.gz split: test - path: validation/eng_Latn-otq_Latn.jsonl.gz split: validation - config_name: eng_Latn-fra_Latn data_files: - path: train/eng_Latn-fra_Latn.jsonl.gz split: train - path: test/eng_Latn-fra_Latn.jsonl.gz split: test - path: validation/eng_Latn-fra_Latn.jsonl.gz split: validation - config_name: eng_Latn-zlm_Latn data_files: - path: train/eng_Latn-zlm_Latn.jsonl.gz split: train - path: test/eng_Latn-zlm_Latn.jsonl.gz split: test - path: validation/eng_Latn-zlm_Latn.jsonl.gz split: validation - config_name: eng_Latn-ptu_Latn data_files: - path: train/eng_Latn-ptu_Latn.jsonl.gz split: train - path: test/eng_Latn-ptu_Latn.jsonl.gz split: test - path: validation/eng_Latn-ptu_Latn.jsonl.gz split: validation - config_name: eng_Latn-apr_Latn data_files: - path: train/eng_Latn-apr_Latn.jsonl.gz split: train - path: test/eng_Latn-apr_Latn.jsonl.gz split: test - path: validation/eng_Latn-apr_Latn.jsonl.gz split: validation - config_name: eng_Latn-zab_Latn data_files: - path: train/eng_Latn-zab_Latn.jsonl.gz split: train - path: test/eng_Latn-zab_Latn.jsonl.gz split: test - path: validation/eng_Latn-zab_Latn.jsonl.gz split: validation - config_name: eng_Latn-kwf_Latn data_files: - path: train/eng_Latn-kwf_Latn.jsonl.gz split: train - path: test/eng_Latn-kwf_Latn.jsonl.gz split: test - path: validation/eng_Latn-kwf_Latn.jsonl.gz split: validation - config_name: eng_Latn-cya_Latn data_files: - path: train/eng_Latn-cya_Latn.jsonl.gz split: train - path: test/eng_Latn-cya_Latn.jsonl.gz split: test - path: validation/eng_Latn-cya_Latn.jsonl.gz split: validation - config_name: eng_Latn-nna_Latn data_files: - path: train/eng_Latn-nna_Latn.jsonl.gz split: train - path: test/eng_Latn-nna_Latn.jsonl.gz split: test - path: validation/eng_Latn-nna_Latn.jsonl.gz split: validation - config_name: eng_Latn-wnc_Latn data_files: - path: train/eng_Latn-wnc_Latn.jsonl.gz split: train - path: test/eng_Latn-wnc_Latn.jsonl.gz split: test - path: validation/eng_Latn-wnc_Latn.jsonl.gz split: validation - config_name: eng_Latn-dad_Latn data_files: - path: train/eng_Latn-dad_Latn.jsonl.gz split: train - path: test/eng_Latn-dad_Latn.jsonl.gz split: test - path: validation/eng_Latn-dad_Latn.jsonl.gz split: validation - config_name: eng_Latn-opm_Latn data_files: - path: train/eng_Latn-opm_Latn.jsonl.gz split: train - path: test/eng_Latn-opm_Latn.jsonl.gz split: test - path: validation/eng_Latn-opm_Latn.jsonl.gz split: validation - config_name: eng_Latn-zaw_Latn data_files: - path: train/eng_Latn-zaw_Latn.jsonl.gz split: train - path: test/eng_Latn-zaw_Latn.jsonl.gz split: test - path: validation/eng_Latn-zaw_Latn.jsonl.gz split: validation - config_name: eng_Latn-agd_Latn data_files: - path: train/eng_Latn-agd_Latn.jsonl.gz split: train - path: test/eng_Latn-agd_Latn.jsonl.gz split: test - path: validation/eng_Latn-agd_Latn.jsonl.gz split: validation - config_name: eng_Latn-qxo_Latn data_files: - path: train/eng_Latn-qxo_Latn.jsonl.gz split: train - path: test/eng_Latn-qxo_Latn.jsonl.gz split: test - path: validation/eng_Latn-qxo_Latn.jsonl.gz split: validation - config_name: eng_Latn-ign_Latn data_files: - path: train/eng_Latn-ign_Latn.jsonl.gz split: train - path: test/eng_Latn-ign_Latn.jsonl.gz split: test - path: validation/eng_Latn-ign_Latn.jsonl.gz split: validation - config_name: eng_Latn-cak_Latn data_files: - path: train/eng_Latn-cak_Latn.jsonl.gz split: train - path: test/eng_Latn-cak_Latn.jsonl.gz split: test - path: validation/eng_Latn-cak_Latn.jsonl.gz split: validation - config_name: eng_Latn-top_Latn data_files: - path: train/eng_Latn-top_Latn.jsonl.gz split: train - path: test/eng_Latn-top_Latn.jsonl.gz split: test - path: validation/eng_Latn-top_Latn.jsonl.gz split: validation - config_name: eng_Latn-tgk_Cyrl data_files: - path: train/eng_Latn-tgk_Cyrl.jsonl.gz split: train - path: test/eng_Latn-tgk_Cyrl.jsonl.gz split: test - path: validation/eng_Latn-tgk_Cyrl.jsonl.gz split: validation - config_name: eng_Latn-awb_Latn data_files: - path: train/eng_Latn-awb_Latn.jsonl.gz split: train - path: test/eng_Latn-awb_Latn.jsonl.gz split: test - path: validation/eng_Latn-awb_Latn.jsonl.gz split: validation - config_name: eng_Latn-cnl_Latn data_files: - path: train/eng_Latn-cnl_Latn.jsonl.gz split: train - path: test/eng_Latn-cnl_Latn.jsonl.gz split: test - path: validation/eng_Latn-cnl_Latn.jsonl.gz split: validation - config_name: eng_Latn-kgp_Latn data_files: - path: train/eng_Latn-kgp_Latn.jsonl.gz split: train - path: test/eng_Latn-kgp_Latn.jsonl.gz split: test - path: validation/eng_Latn-kgp_Latn.jsonl.gz split: validation - config_name: eng_Latn-khs_Latn data_files: - path: train/eng_Latn-khs_Latn.jsonl.gz split: train - path: test/eng_Latn-khs_Latn.jsonl.gz split: test - path: validation/eng_Latn-khs_Latn.jsonl.gz split: validation - config_name: eng_Latn-abx_Latn data_files: - path: train/eng_Latn-abx_Latn.jsonl.gz split: train - path: test/eng_Latn-abx_Latn.jsonl.gz split: test - path: validation/eng_Latn-abx_Latn.jsonl.gz split: validation - config_name: eng_Latn-mcq_Latn data_files: - path: train/eng_Latn-mcq_Latn.jsonl.gz split: train - path: test/eng_Latn-mcq_Latn.jsonl.gz split: test - path: validation/eng_Latn-mcq_Latn.jsonl.gz split: validation - config_name: eng_Latn-chd_Latn data_files: - path: train/eng_Latn-chd_Latn.jsonl.gz split: train - path: test/eng_Latn-chd_Latn.jsonl.gz split: test - path: validation/eng_Latn-chd_Latn.jsonl.gz split: validation - config_name: eng_Latn-kud_Latn data_files: - path: train/eng_Latn-kud_Latn.jsonl.gz split: train - path: test/eng_Latn-kud_Latn.jsonl.gz split: test - path: validation/eng_Latn-kud_Latn.jsonl.gz split: validation - config_name: eng_Latn-nak_Latn data_files: - path: train/eng_Latn-nak_Latn.jsonl.gz split: train - path: test/eng_Latn-nak_Latn.jsonl.gz split: test - path: validation/eng_Latn-nak_Latn.jsonl.gz split: validation - config_name: eng_Latn-mux_Latn data_files: - path: train/eng_Latn-mux_Latn.jsonl.gz split: train - path: test/eng_Latn-mux_Latn.jsonl.gz split: test - path: validation/eng_Latn-mux_Latn.jsonl.gz split: validation - config_name: eng_Latn-tzo_Latn data_files: - path: train/eng_Latn-tzo_Latn.jsonl.gz split: train - path: test/eng_Latn-tzo_Latn.jsonl.gz split: test - path: validation/eng_Latn-tzo_Latn.jsonl.gz split: validation - config_name: eng_Latn-mav_Latn data_files: - path: train/eng_Latn-mav_Latn.jsonl.gz split: train - path: test/eng_Latn-mav_Latn.jsonl.gz split: test - path: validation/eng_Latn-mav_Latn.jsonl.gz split: validation - config_name: eng_Latn-avt_Latn data_files: - path: train/eng_Latn-avt_Latn.jsonl.gz split: train - path: test/eng_Latn-avt_Latn.jsonl.gz split: test - path: validation/eng_Latn-avt_Latn.jsonl.gz split: validation - config_name: eng_Latn-bjz_Latn data_files: - path: train/eng_Latn-bjz_Latn.jsonl.gz split: train - path: test/eng_Latn-bjz_Latn.jsonl.gz split: test - path: validation/eng_Latn-bjz_Latn.jsonl.gz split: validation - config_name: eng_Latn-ptp_Latn data_files: - path: train/eng_Latn-ptp_Latn.jsonl.gz split: train - path: test/eng_Latn-ptp_Latn.jsonl.gz split: test - path: validation/eng_Latn-ptp_Latn.jsonl.gz split: validation - config_name: eng_Latn-gnw_Latn data_files: - path: train/eng_Latn-gnw_Latn.jsonl.gz split: train - path: test/eng_Latn-gnw_Latn.jsonl.gz split: test - path: validation/eng_Latn-gnw_Latn.jsonl.gz split: validation - config_name: eng_Latn-cub_Latn data_files: - path: train/eng_Latn-cub_Latn.jsonl.gz split: train - path: test/eng_Latn-cub_Latn.jsonl.gz split: test - path: validation/eng_Latn-cub_Latn.jsonl.gz split: validation - config_name: eng_Latn-hmo_Latn data_files: - path: train/eng_Latn-hmo_Latn.jsonl.gz split: train - path: test/eng_Latn-hmo_Latn.jsonl.gz split: test - path: validation/eng_Latn-hmo_Latn.jsonl.gz split: validation - config_name: eng_Latn-kkl_Latn data_files: - path: train/eng_Latn-kkl_Latn.jsonl.gz split: train - path: test/eng_Latn-kkl_Latn.jsonl.gz split: test - path: validation/eng_Latn-kkl_Latn.jsonl.gz split: validation - config_name: eng_Latn-nou_Latn data_files: - path: train/eng_Latn-nou_Latn.jsonl.gz split: train - path: test/eng_Latn-nou_Latn.jsonl.gz split: test - path: validation/eng_Latn-nou_Latn.jsonl.gz split: validation - config_name: eng_Latn-bre_Latn data_files: - path: train/eng_Latn-bre_Latn.jsonl.gz split: train - path: test/eng_Latn-bre_Latn.jsonl.gz split: test - path: validation/eng_Latn-bre_Latn.jsonl.gz split: validation - config_name: eng_Latn-sim_Latn data_files: - path: train/eng_Latn-sim_Latn.jsonl.gz split: train - path: test/eng_Latn-sim_Latn.jsonl.gz split: test - path: validation/eng_Latn-sim_Latn.jsonl.gz split: validation - config_name: eng_Latn-sbk_Latn data_files: - path: train/eng_Latn-sbk_Latn.jsonl.gz split: train - path: test/eng_Latn-sbk_Latn.jsonl.gz split: test - path: validation/eng_Latn-sbk_Latn.jsonl.gz split: validation - config_name: eng_Latn-nsn_Latn data_files: - path: train/eng_Latn-nsn_Latn.jsonl.gz split: train - path: test/eng_Latn-nsn_Latn.jsonl.gz split: test - path: validation/eng_Latn-nsn_Latn.jsonl.gz split: validation - config_name: eng_Latn-mva_Latn data_files: - path: train/eng_Latn-mva_Latn.jsonl.gz split: train - path: test/eng_Latn-mva_Latn.jsonl.gz split: test - path: validation/eng_Latn-mva_Latn.jsonl.gz split: validation - config_name: eng_Latn-kkc_Latn data_files: - path: train/eng_Latn-kkc_Latn.jsonl.gz split: train - path: test/eng_Latn-kkc_Latn.jsonl.gz split: test - path: validation/eng_Latn-kkc_Latn.jsonl.gz split: validation - config_name: eng_Latn-gvc_Latn data_files: - path: train/eng_Latn-gvc_Latn.jsonl.gz split: train - path: test/eng_Latn-gvc_Latn.jsonl.gz split: test - path: validation/eng_Latn-gvc_Latn.jsonl.gz split: validation - config_name: eng_Latn-jao_Latn data_files: - path: train/eng_Latn-jao_Latn.jsonl.gz split: train - path: test/eng_Latn-jao_Latn.jsonl.gz split: test - path: validation/eng_Latn-jao_Latn.jsonl.gz split: validation - config_name: eng_Latn-kek_Latn data_files: - path: train/eng_Latn-kek_Latn.jsonl.gz split: train - path: test/eng_Latn-kek_Latn.jsonl.gz split: test - path: validation/eng_Latn-kek_Latn.jsonl.gz split: validation - config_name: eng_Latn-nfa_Latn data_files: - path: train/eng_Latn-nfa_Latn.jsonl.gz split: train - path: test/eng_Latn-nfa_Latn.jsonl.gz split: test - path: validation/eng_Latn-nfa_Latn.jsonl.gz split: validation - config_name: eng_Latn-lid_Latn data_files: - path: train/eng_Latn-lid_Latn.jsonl.gz split: train - path: test/eng_Latn-lid_Latn.jsonl.gz split: test - path: validation/eng_Latn-lid_Latn.jsonl.gz split: validation - config_name: eng_Latn-kmu_Latn data_files: - path: train/eng_Latn-kmu_Latn.jsonl.gz split: train - path: test/eng_Latn-kmu_Latn.jsonl.gz split: test - path: validation/eng_Latn-kmu_Latn.jsonl.gz split: validation - config_name: eng_Latn-hbo_Hebr data_files: - path: train/eng_Latn-hbo_Hebr.jsonl.gz split: train - path: test/eng_Latn-hbo_Hebr.jsonl.gz split: test - path: validation/eng_Latn-hbo_Hebr.jsonl.gz split: validation - config_name: eng_Latn-bkq_Latn data_files: - path: train/eng_Latn-bkq_Latn.jsonl.gz split: train - path: test/eng_Latn-bkq_Latn.jsonl.gz split: test - path: validation/eng_Latn-bkq_Latn.jsonl.gz split: validation - config_name: eng_Latn-mig_Latn data_files: - path: train/eng_Latn-mig_Latn.jsonl.gz split: train - path: test/eng_Latn-mig_Latn.jsonl.gz split: test - path: validation/eng_Latn-mig_Latn.jsonl.gz split: validation - config_name: eng_Latn-jae_Latn data_files: - path: train/eng_Latn-jae_Latn.jsonl.gz split: train - path: test/eng_Latn-jae_Latn.jsonl.gz split: test - path: validation/eng_Latn-jae_Latn.jsonl.gz split: validation - config_name: eng_Latn-ben_Beng data_files: - path: train/eng_Latn-ben_Beng.jsonl.gz split: train - path: test/eng_Latn-ben_Beng.jsonl.gz split: test - path: validation/eng_Latn-ben_Beng.jsonl.gz split: validation - config_name: eng_Latn-spy_Latn data_files: - path: train/eng_Latn-spy_Latn.jsonl.gz split: train - path: test/eng_Latn-spy_Latn.jsonl.gz split: test - path: validation/eng_Latn-spy_Latn.jsonl.gz split: validation - config_name: eng_Latn-bvd_Latn data_files: - path: train/eng_Latn-bvd_Latn.jsonl.gz split: train - path: test/eng_Latn-bvd_Latn.jsonl.gz split: test - path: validation/eng_Latn-bvd_Latn.jsonl.gz split: validation - config_name: eng_Latn-bvr_Latn data_files: - path: train/eng_Latn-bvr_Latn.jsonl.gz split: train - path: test/eng_Latn-bvr_Latn.jsonl.gz split: test - path: validation/eng_Latn-bvr_Latn.jsonl.gz split: validation - config_name: eng_Latn-kto_Latn data_files: - path: train/eng_Latn-kto_Latn.jsonl.gz split: train - path: test/eng_Latn-kto_Latn.jsonl.gz split: test - path: validation/eng_Latn-kto_Latn.jsonl.gz split: validation - config_name: eng_Latn-amn_Latn data_files: - path: train/eng_Latn-amn_Latn.jsonl.gz split: train - path: test/eng_Latn-amn_Latn.jsonl.gz split: test - path: validation/eng_Latn-amn_Latn.jsonl.gz split: validation - config_name: eng_Latn-spp_Latn data_files: - path: train/eng_Latn-spp_Latn.jsonl.gz split: train - path: test/eng_Latn-spp_Latn.jsonl.gz split: test - path: validation/eng_Latn-spp_Latn.jsonl.gz split: validation - config_name: eng_Latn-ncl_Latn data_files: - path: train/eng_Latn-ncl_Latn.jsonl.gz split: train - path: test/eng_Latn-ncl_Latn.jsonl.gz split: test - path: validation/eng_Latn-ncl_Latn.jsonl.gz split: validation - config_name: eng_Latn-tdt_Latn data_files: - path: train/eng_Latn-tdt_Latn.jsonl.gz split: train - path: test/eng_Latn-tdt_Latn.jsonl.gz split: test - path: validation/eng_Latn-tdt_Latn.jsonl.gz split: validation - config_name: eng_Latn-urw_Latn data_files: - path: train/eng_Latn-urw_Latn.jsonl.gz split: train - path: test/eng_Latn-urw_Latn.jsonl.gz split: test - path: validation/eng_Latn-urw_Latn.jsonl.gz split: validation - config_name: eng_Latn-shp_Latn data_files: - path: train/eng_Latn-shp_Latn.jsonl.gz split: train - path: test/eng_Latn-shp_Latn.jsonl.gz split: test - path: validation/eng_Latn-shp_Latn.jsonl.gz split: validation - config_name: eng_Latn-met_Latn data_files: - path: train/eng_Latn-met_Latn.jsonl.gz split: train - path: test/eng_Latn-met_Latn.jsonl.gz split: test - path: validation/eng_Latn-met_Latn.jsonl.gz split: validation - config_name: eng_Latn-pon_Latn data_files: - path: train/eng_Latn-pon_Latn.jsonl.gz split: train - path: test/eng_Latn-pon_Latn.jsonl.gz split: test - path: validation/eng_Latn-pon_Latn.jsonl.gz split: validation - config_name: eng_Latn-tiy_Latn data_files: - path: train/eng_Latn-tiy_Latn.jsonl.gz split: train - path: test/eng_Latn-tiy_Latn.jsonl.gz split: test - path: validation/eng_Latn-tiy_Latn.jsonl.gz split: validation - config_name: eng_Latn-nhy_Latn data_files: - path: train/eng_Latn-nhy_Latn.jsonl.gz split: train - path: test/eng_Latn-nhy_Latn.jsonl.gz split: test - path: validation/eng_Latn-nhy_Latn.jsonl.gz split: validation - config_name: eng_Latn-cpc_Latn data_files: - path: train/eng_Latn-cpc_Latn.jsonl.gz split: train - path: test/eng_Latn-cpc_Latn.jsonl.gz split: test - path: validation/eng_Latn-cpc_Latn.jsonl.gz split: validation - config_name: eng_Latn-bel_Cyrl data_files: - path: train/eng_Latn-bel_Cyrl.jsonl.gz split: train - path: test/eng_Latn-bel_Cyrl.jsonl.gz split: test - path: validation/eng_Latn-bel_Cyrl.jsonl.gz split: validation - config_name: eng_Latn-cbv_Latn data_files: - path: train/eng_Latn-cbv_Latn.jsonl.gz split: train - path: test/eng_Latn-cbv_Latn.jsonl.gz split: test - path: validation/eng_Latn-cbv_Latn.jsonl.gz split: validation - config_name: eng_Latn-pab_Latn data_files: - path: train/eng_Latn-pab_Latn.jsonl.gz split: train - path: test/eng_Latn-pab_Latn.jsonl.gz split: test - path: validation/eng_Latn-pab_Latn.jsonl.gz split: validation - config_name: eng_Latn-dgz_Latn data_files: - path: train/eng_Latn-dgz_Latn.jsonl.gz split: train - path: test/eng_Latn-dgz_Latn.jsonl.gz split: test - path: validation/eng_Latn-dgz_Latn.jsonl.gz split: validation - config_name: eng_Latn-pri_Latn data_files: - path: train/eng_Latn-pri_Latn.jsonl.gz split: train - path: test/eng_Latn-pri_Latn.jsonl.gz split: test - path: validation/eng_Latn-pri_Latn.jsonl.gz split: validation - config_name: eng_Latn-hch_Latn data_files: - path: train/eng_Latn-hch_Latn.jsonl.gz split: train - path: test/eng_Latn-hch_Latn.jsonl.gz split: test - path: validation/eng_Latn-hch_Latn.jsonl.gz split: validation - config_name: eng_Latn-wed_Latn data_files: - path: train/eng_Latn-wed_Latn.jsonl.gz split: train - path: test/eng_Latn-wed_Latn.jsonl.gz split: test - path: validation/eng_Latn-wed_Latn.jsonl.gz split: validation - config_name: eng_Latn-suz_Latn data_files: - path: train/eng_Latn-suz_Latn.jsonl.gz split: train - path: test/eng_Latn-suz_Latn.jsonl.gz split: test - path: validation/eng_Latn-suz_Latn.jsonl.gz split: validation - config_name: eng_Latn-usp_Latn data_files: - path: train/eng_Latn-usp_Latn.jsonl.gz split: train - path: test/eng_Latn-usp_Latn.jsonl.gz split: test - path: validation/eng_Latn-usp_Latn.jsonl.gz split: validation - config_name: eng_Latn-mkl_Latn data_files: - path: train/eng_Latn-mkl_Latn.jsonl.gz split: train - path: test/eng_Latn-mkl_Latn.jsonl.gz split: test - path: validation/eng_Latn-mkl_Latn.jsonl.gz split: validation - config_name: eng_Latn-cbt_Latn data_files: - path: train/eng_Latn-cbt_Latn.jsonl.gz split: train - path: test/eng_Latn-cbt_Latn.jsonl.gz split: test - path: validation/eng_Latn-cbt_Latn.jsonl.gz split: validation - config_name: eng_Latn-kpg_Latn data_files: - path: train/eng_Latn-kpg_Latn.jsonl.gz split: train - path: test/eng_Latn-kpg_Latn.jsonl.gz split: test - path: validation/eng_Latn-kpg_Latn.jsonl.gz split: validation - config_name: eng_Latn-kue_Latn data_files: - path: train/eng_Latn-kue_Latn.jsonl.gz split: train - path: test/eng_Latn-kue_Latn.jsonl.gz split: test - path: validation/eng_Latn-kue_Latn.jsonl.gz split: validation - config_name: eng_Latn-sbs_Latn data_files: - path: train/eng_Latn-sbs_Latn.jsonl.gz split: train - path: test/eng_Latn-sbs_Latn.jsonl.gz split: test - path: validation/eng_Latn-sbs_Latn.jsonl.gz split: validation - config_name: eng_Latn-qvz_Latn data_files: - path: train/eng_Latn-qvz_Latn.jsonl.gz split: train - path: test/eng_Latn-qvz_Latn.jsonl.gz split: test - path: validation/eng_Latn-qvz_Latn.jsonl.gz split: validation - config_name: eng_Latn-seh_Latn data_files: - path: train/eng_Latn-seh_Latn.jsonl.gz split: train - path: test/eng_Latn-seh_Latn.jsonl.gz split: test - path: validation/eng_Latn-seh_Latn.jsonl.gz split: validation - config_name: eng_Latn-wrs_Latn data_files: - path: train/eng_Latn-wrs_Latn.jsonl.gz split: train - path: test/eng_Latn-wrs_Latn.jsonl.gz split: test - path: validation/eng_Latn-wrs_Latn.jsonl.gz split: validation - config_name: eng_Latn-snc_Latn data_files: - path: train/eng_Latn-snc_Latn.jsonl.gz split: train - path: test/eng_Latn-snc_Latn.jsonl.gz split: test - path: validation/eng_Latn-snc_Latn.jsonl.gz split: validation - config_name: eng_Latn-bjp_Latn data_files: - path: train/eng_Latn-bjp_Latn.jsonl.gz split: train - path: test/eng_Latn-bjp_Latn.jsonl.gz split: test - path: validation/eng_Latn-bjp_Latn.jsonl.gz split: validation - config_name: eng_Latn-kyz_Latn data_files: - path: train/eng_Latn-kyz_Latn.jsonl.gz split: train - path: test/eng_Latn-kyz_Latn.jsonl.gz split: test - path: validation/eng_Latn-kyz_Latn.jsonl.gz split: validation - config_name: eng_Latn-noa_Latn data_files: - path: train/eng_Latn-noa_Latn.jsonl.gz split: train - path: test/eng_Latn-noa_Latn.jsonl.gz split: test - path: validation/eng_Latn-noa_Latn.jsonl.gz split: validation - config_name: eng_Latn-ssx_Latn data_files: - path: train/eng_Latn-ssx_Latn.jsonl.gz split: train - path: test/eng_Latn-ssx_Latn.jsonl.gz split: test - path: validation/eng_Latn-ssx_Latn.jsonl.gz split: validation - config_name: eng_Latn-nbq_Latn data_files: - path: train/eng_Latn-nbq_Latn.jsonl.gz split: train - path: test/eng_Latn-nbq_Latn.jsonl.gz split: test - path: validation/eng_Latn-nbq_Latn.jsonl.gz split: validation - config_name: eng_Latn-msb_Latn data_files: - path: train/eng_Latn-msb_Latn.jsonl.gz split: train - path: test/eng_Latn-msb_Latn.jsonl.gz split: test - path: validation/eng_Latn-msb_Latn.jsonl.gz split: validation - config_name: eng_Latn-sue_Latn data_files: - path: train/eng_Latn-sue_Latn.jsonl.gz split: train - path: test/eng_Latn-sue_Latn.jsonl.gz split: test - path: validation/eng_Latn-sue_Latn.jsonl.gz split: validation - config_name: eng_Latn-asm_Beng data_files: - path: train/eng_Latn-asm_Beng.jsonl.gz split: train - path: test/eng_Latn-asm_Beng.jsonl.gz split: test - path: validation/eng_Latn-asm_Beng.jsonl.gz split: validation - config_name: eng_Latn-som_Latn data_files: - path: train/eng_Latn-som_Latn.jsonl.gz split: train - path: test/eng_Latn-som_Latn.jsonl.gz split: test - path: validation/eng_Latn-som_Latn.jsonl.gz split: validation - config_name: eng_Latn-xon_Latn data_files: - path: train/eng_Latn-xon_Latn.jsonl.gz split: train - path: test/eng_Latn-xon_Latn.jsonl.gz split: test - path: validation/eng_Latn-xon_Latn.jsonl.gz split: validation - config_name: eng_Latn-qvh_Latn data_files: - path: train/eng_Latn-qvh_Latn.jsonl.gz split: train - path: test/eng_Latn-qvh_Latn.jsonl.gz split: test - path: validation/eng_Latn-qvh_Latn.jsonl.gz split: validation - config_name: eng_Latn-mib_Latn data_files: - path: train/eng_Latn-mib_Latn.jsonl.gz split: train - path: test/eng_Latn-mib_Latn.jsonl.gz split: test - path: validation/eng_Latn-mib_Latn.jsonl.gz split: validation - config_name: eng_Latn-wap_Latn data_files: - path: train/eng_Latn-wap_Latn.jsonl.gz split: train - path: test/eng_Latn-wap_Latn.jsonl.gz split: test - path: validation/eng_Latn-wap_Latn.jsonl.gz split: validation - config_name: eng_Latn-gai_Latn data_files: - path: train/eng_Latn-gai_Latn.jsonl.gz split: train - path: test/eng_Latn-gai_Latn.jsonl.gz split: test - path: validation/eng_Latn-gai_Latn.jsonl.gz split: validation - config_name: eng_Latn-mkn_Latn data_files: - path: train/eng_Latn-mkn_Latn.jsonl.gz split: train - path: test/eng_Latn-mkn_Latn.jsonl.gz split: test - path: validation/eng_Latn-mkn_Latn.jsonl.gz split: validation - config_name: eng_Latn-xnn_Latn data_files: - path: train/eng_Latn-xnn_Latn.jsonl.gz split: train - path: test/eng_Latn-xnn_Latn.jsonl.gz split: test - path: validation/eng_Latn-xnn_Latn.jsonl.gz split: validation - config_name: eng_Latn-amf_Latn data_files: - path: train/eng_Latn-amf_Latn.jsonl.gz split: train - path: test/eng_Latn-amf_Latn.jsonl.gz split: test - path: validation/eng_Latn-amf_Latn.jsonl.gz split: validation - config_name: eng_Latn-nhe_Latn data_files: - path: train/eng_Latn-nhe_Latn.jsonl.gz split: train - path: test/eng_Latn-nhe_Latn.jsonl.gz split: test - path: validation/eng_Latn-nhe_Latn.jsonl.gz split: validation - config_name: eng_Latn-kmk_Latn data_files: - path: train/eng_Latn-kmk_Latn.jsonl.gz split: train - path: test/eng_Latn-kmk_Latn.jsonl.gz split: test - path: validation/eng_Latn-kmk_Latn.jsonl.gz split: validation - config_name: eng_Latn-tam_Taml data_files: - path: train/eng_Latn-tam_Taml.jsonl.gz split: train - path: test/eng_Latn-tam_Taml.jsonl.gz split: test - path: validation/eng_Latn-tam_Taml.jsonl.gz split: validation - config_name: eng_Latn-nab_Latn data_files: - path: train/eng_Latn-nab_Latn.jsonl.gz split: train - path: test/eng_Latn-nab_Latn.jsonl.gz split: test - path: validation/eng_Latn-nab_Latn.jsonl.gz split: validation - config_name: eng_Latn-dik_Latn data_files: - path: train/eng_Latn-dik_Latn.jsonl.gz split: train - path: test/eng_Latn-dik_Latn.jsonl.gz split: test - path: validation/eng_Latn-dik_Latn.jsonl.gz split: validation - config_name: eng_Latn-cpy_Latn data_files: - path: train/eng_Latn-cpy_Latn.jsonl.gz split: train - path: test/eng_Latn-cpy_Latn.jsonl.gz split: test - path: validation/eng_Latn-cpy_Latn.jsonl.gz split: validation - config_name: eng_Latn-arl_Latn data_files: - path: train/eng_Latn-arl_Latn.jsonl.gz split: train - path: test/eng_Latn-arl_Latn.jsonl.gz split: test - path: validation/eng_Latn-arl_Latn.jsonl.gz split: validation - config_name: eng_Latn-tuc_Latn data_files: - path: train/eng_Latn-tuc_Latn.jsonl.gz split: train - path: test/eng_Latn-tuc_Latn.jsonl.gz split: test - path: validation/eng_Latn-tuc_Latn.jsonl.gz split: validation - config_name: eng_Latn-ngu_Latn data_files: - path: train/eng_Latn-ngu_Latn.jsonl.gz split: train - path: test/eng_Latn-ngu_Latn.jsonl.gz split: test - path: validation/eng_Latn-ngu_Latn.jsonl.gz split: validation - config_name: eng_Latn-zad_Latn data_files: - path: train/eng_Latn-zad_Latn.jsonl.gz split: train - path: test/eng_Latn-zad_Latn.jsonl.gz split: test - path: validation/eng_Latn-zad_Latn.jsonl.gz split: validation - config_name: eng_Latn-kmh_Latn data_files: - path: train/eng_Latn-kmh_Latn.jsonl.gz split: train - path: test/eng_Latn-kmh_Latn.jsonl.gz split: test - path: validation/eng_Latn-kmh_Latn.jsonl.gz split: validation - config_name: eng_Latn-quh_Latn data_files: - path: train/eng_Latn-quh_Latn.jsonl.gz split: train - path: test/eng_Latn-quh_Latn.jsonl.gz split: test - path: validation/eng_Latn-quh_Latn.jsonl.gz split: validation - config_name: eng_Latn-alq_Latn data_files: - path: train/eng_Latn-alq_Latn.jsonl.gz split: train - path: test/eng_Latn-alq_Latn.jsonl.gz split: test - path: validation/eng_Latn-alq_Latn.jsonl.gz split: validation - config_name: eng_Latn-grc_Grek data_files: - path: train/eng_Latn-grc_Grek.jsonl.gz split: train - path: test/eng_Latn-grc_Grek.jsonl.gz split: test - path: validation/eng_Latn-grc_Grek.jsonl.gz split: validation - config_name: eng_Latn-kaq_Latn data_files: - path: train/eng_Latn-kaq_Latn.jsonl.gz split: train - path: test/eng_Latn-kaq_Latn.jsonl.gz split: test - path: validation/eng_Latn-kaq_Latn.jsonl.gz split: validation - config_name: eng_Latn-zpm_Latn data_files: - path: train/eng_Latn-zpm_Latn.jsonl.gz split: train - path: test/eng_Latn-zpm_Latn.jsonl.gz split: test - path: validation/eng_Latn-zpm_Latn.jsonl.gz split: validation - config_name: eng_Latn-obo_Latn data_files: - path: train/eng_Latn-obo_Latn.jsonl.gz split: train - path: test/eng_Latn-obo_Latn.jsonl.gz split: test - path: validation/eng_Latn-obo_Latn.jsonl.gz split: validation - config_name: eng_Latn-cha_Latn data_files: - path: train/eng_Latn-cha_Latn.jsonl.gz split: train - path: test/eng_Latn-cha_Latn.jsonl.gz split: test - path: validation/eng_Latn-cha_Latn.jsonl.gz split: validation - config_name: eng_Latn-mbs_Latn data_files: - path: train/eng_Latn-mbs_Latn.jsonl.gz split: train - path: test/eng_Latn-mbs_Latn.jsonl.gz split: test - path: validation/eng_Latn-mbs_Latn.jsonl.gz split: validation - config_name: eng_Latn-poi_Latn data_files: - path: train/eng_Latn-poi_Latn.jsonl.gz split: train - path: test/eng_Latn-poi_Latn.jsonl.gz split: test - path: validation/eng_Latn-poi_Latn.jsonl.gz split: validation - config_name: eng_Latn-spm_Latn data_files: - path: train/eng_Latn-spm_Latn.jsonl.gz split: train - path: test/eng_Latn-spm_Latn.jsonl.gz split: test - path: validation/eng_Latn-spm_Latn.jsonl.gz split: validation - config_name: eng_Latn-cpb_Latn data_files: - path: train/eng_Latn-cpb_Latn.jsonl.gz split: train - path: test/eng_Latn-cpb_Latn.jsonl.gz split: test - path: validation/eng_Latn-cpb_Latn.jsonl.gz split: validation - config_name: eng_Latn-omw_Latn data_files: - path: train/eng_Latn-omw_Latn.jsonl.gz split: train - path: test/eng_Latn-omw_Latn.jsonl.gz split: test - path: validation/eng_Latn-omw_Latn.jsonl.gz split: validation - config_name: eng_Latn-klv_Latn data_files: - path: train/eng_Latn-klv_Latn.jsonl.gz split: train - path: test/eng_Latn-klv_Latn.jsonl.gz split: test - path: validation/eng_Latn-klv_Latn.jsonl.gz split: validation - config_name: eng_Latn-sbe_Latn data_files: - path: train/eng_Latn-sbe_Latn.jsonl.gz split: train - path: test/eng_Latn-sbe_Latn.jsonl.gz split: test - path: validation/eng_Latn-sbe_Latn.jsonl.gz split: validation - config_name: eng_Latn-ntu_Latn data_files: - path: train/eng_Latn-ntu_Latn.jsonl.gz split: train - path: test/eng_Latn-ntu_Latn.jsonl.gz split: test - path: validation/eng_Latn-ntu_Latn.jsonl.gz split: validation - config_name: eng_Latn-zat_Latn data_files: - path: train/eng_Latn-zat_Latn.jsonl.gz split: train - path: test/eng_Latn-zat_Latn.jsonl.gz split: test - path: validation/eng_Latn-zat_Latn.jsonl.gz split: validation - config_name: eng_Latn-bsp_Latn data_files: - path: train/eng_Latn-bsp_Latn.jsonl.gz split: train - path: test/eng_Latn-bsp_Latn.jsonl.gz split: test - path: validation/eng_Latn-bsp_Latn.jsonl.gz split: validation - config_name: eng_Latn-mps_Latn data_files: - path: train/eng_Latn-mps_Latn.jsonl.gz split: train - path: test/eng_Latn-mps_Latn.jsonl.gz split: test - path: validation/eng_Latn-mps_Latn.jsonl.gz split: validation - config_name: eng_Latn-mks_Latn data_files: - path: train/eng_Latn-mks_Latn.jsonl.gz split: train - path: test/eng_Latn-mks_Latn.jsonl.gz split: test - path: validation/eng_Latn-mks_Latn.jsonl.gz split: validation - config_name: eng_Latn-bmh_Latn data_files: - path: train/eng_Latn-bmh_Latn.jsonl.gz split: train - path: test/eng_Latn-bmh_Latn.jsonl.gz split: test - path: validation/eng_Latn-bmh_Latn.jsonl.gz split: validation - config_name: eng_Latn-tpz_Latn data_files: - path: train/eng_Latn-tpz_Latn.jsonl.gz split: train - path: test/eng_Latn-tpz_Latn.jsonl.gz split: test - path: validation/eng_Latn-tpz_Latn.jsonl.gz split: validation - config_name: eng_Latn-amr_Latn data_files: - path: train/eng_Latn-amr_Latn.jsonl.gz split: train - path: test/eng_Latn-amr_Latn.jsonl.gz split: test - path: validation/eng_Latn-amr_Latn.jsonl.gz split: validation - config_name: eng_Latn-cjo_Latn data_files: - path: train/eng_Latn-cjo_Latn.jsonl.gz split: train - path: test/eng_Latn-cjo_Latn.jsonl.gz split: test - path: validation/eng_Latn-cjo_Latn.jsonl.gz split: validation - config_name: eng_Latn-ksr_Latn data_files: - path: train/eng_Latn-ksr_Latn.jsonl.gz split: train - path: test/eng_Latn-ksr_Latn.jsonl.gz split: test - path: validation/eng_Latn-ksr_Latn.jsonl.gz split: validation - config_name: eng_Latn-tgo_Latn data_files: - path: train/eng_Latn-tgo_Latn.jsonl.gz split: train - path: test/eng_Latn-tgo_Latn.jsonl.gz split: test - path: validation/eng_Latn-tgo_Latn.jsonl.gz split: validation - config_name: eng_Latn-tke_Latn data_files: - path: train/eng_Latn-tke_Latn.jsonl.gz split: train - path: test/eng_Latn-tke_Latn.jsonl.gz split: test - path: validation/eng_Latn-tke_Latn.jsonl.gz split: validation - config_name: eng_Latn-lac_Latn data_files: - path: train/eng_Latn-lac_Latn.jsonl.gz split: train - path: test/eng_Latn-lac_Latn.jsonl.gz split: test - path: validation/eng_Latn-lac_Latn.jsonl.gz split: validation - config_name: eng_Latn-nhu_Latn data_files: - path: train/eng_Latn-nhu_Latn.jsonl.gz split: train - path: test/eng_Latn-nhu_Latn.jsonl.gz split: test - path: validation/eng_Latn-nhu_Latn.jsonl.gz split: validation - config_name: eng_Latn-ssd_Latn data_files: - path: train/eng_Latn-ssd_Latn.jsonl.gz split: train - path: test/eng_Latn-ssd_Latn.jsonl.gz split: test - path: validation/eng_Latn-ssd_Latn.jsonl.gz split: validation - config_name: eng_Latn-bon_Latn data_files: - path: train/eng_Latn-bon_Latn.jsonl.gz split: train - path: test/eng_Latn-bon_Latn.jsonl.gz split: test - path: validation/eng_Latn-bon_Latn.jsonl.gz split: validation - config_name: eng_Latn-cso_Latn data_files: - path: train/eng_Latn-cso_Latn.jsonl.gz split: train - path: test/eng_Latn-cso_Latn.jsonl.gz split: test - path: validation/eng_Latn-cso_Latn.jsonl.gz split: validation - config_name: eng_Latn-naf_Latn data_files: - path: train/eng_Latn-naf_Latn.jsonl.gz split: train - path: test/eng_Latn-naf_Latn.jsonl.gz split: test - path: validation/eng_Latn-naf_Latn.jsonl.gz split: validation - config_name: eng_Latn-kbh_Latn data_files: - path: train/eng_Latn-kbh_Latn.jsonl.gz split: train - path: test/eng_Latn-kbh_Latn.jsonl.gz split: test - path: validation/eng_Latn-kbh_Latn.jsonl.gz split: validation - config_name: eng_Latn-hun_Latn data_files: - path: train/eng_Latn-hun_Latn.jsonl.gz split: train - path: test/eng_Latn-hun_Latn.jsonl.gz split: test - path: validation/eng_Latn-hun_Latn.jsonl.gz split: validation - config_name: eng_Latn-tte_Latn data_files: - path: train/eng_Latn-tte_Latn.jsonl.gz split: train - path: test/eng_Latn-tte_Latn.jsonl.gz split: test - path: validation/eng_Latn-tte_Latn.jsonl.gz split: validation - config_name: eng_Latn-amo_Latn data_files: - path: train/eng_Latn-amo_Latn.jsonl.gz split: train - path: test/eng_Latn-amo_Latn.jsonl.gz split: test - path: validation/eng_Latn-amo_Latn.jsonl.gz split: validation - config_name: eng_Latn-kiz_Latn data_files: - path: train/eng_Latn-kiz_Latn.jsonl.gz split: train - path: test/eng_Latn-kiz_Latn.jsonl.gz split: test - path: validation/eng_Latn-kiz_Latn.jsonl.gz split: validation - config_name: eng_Latn-wsk_Latn data_files: - path: train/eng_Latn-wsk_Latn.jsonl.gz split: train - path: test/eng_Latn-wsk_Latn.jsonl.gz split: test - path: validation/eng_Latn-wsk_Latn.jsonl.gz split: validation - config_name: eng_Latn-kwd_Latn data_files: - path: train/eng_Latn-kwd_Latn.jsonl.gz split: train - path: test/eng_Latn-kwd_Latn.jsonl.gz split: test - path: validation/eng_Latn-kwd_Latn.jsonl.gz split: validation - config_name: eng_Latn-geb_Latn data_files: - path: train/eng_Latn-geb_Latn.jsonl.gz split: train - path: test/eng_Latn-geb_Latn.jsonl.gz split: test - path: validation/eng_Latn-geb_Latn.jsonl.gz split: validation - config_name: eng_Latn-mdy_Latn data_files: - path: train/eng_Latn-mdy_Latn.jsonl.gz split: train - path: test/eng_Latn-mdy_Latn.jsonl.gz split: test - path: validation/eng_Latn-mdy_Latn.jsonl.gz split: validation - config_name: eng_Latn-kgk_Latn data_files: - path: train/eng_Latn-kgk_Latn.jsonl.gz split: train - path: test/eng_Latn-kgk_Latn.jsonl.gz split: test - path: validation/eng_Latn-kgk_Latn.jsonl.gz split: validation - config_name: eng_Latn-kqw_Latn data_files: - path: train/eng_Latn-kqw_Latn.jsonl.gz split: train - path: test/eng_Latn-kqw_Latn.jsonl.gz split: test - path: validation/eng_Latn-kqw_Latn.jsonl.gz split: validation - config_name: eng_Latn-gaw_Latn data_files: - path: train/eng_Latn-gaw_Latn.jsonl.gz split: train - path: test/eng_Latn-gaw_Latn.jsonl.gz split: test - path: validation/eng_Latn-gaw_Latn.jsonl.gz split: validation - config_name: eng_Latn-mox_Latn data_files: - path: train/eng_Latn-mox_Latn.jsonl.gz split: train - path: test/eng_Latn-mox_Latn.jsonl.gz split: test - path: validation/eng_Latn-mox_Latn.jsonl.gz split: validation - config_name: eng_Latn-cav_Latn data_files: - path: train/eng_Latn-cav_Latn.jsonl.gz split: train - path: test/eng_Latn-cav_Latn.jsonl.gz split: test - path: validation/eng_Latn-cav_Latn.jsonl.gz split: validation - config_name: eng_Latn-tzj_Latn data_files: - path: train/eng_Latn-tzj_Latn.jsonl.gz split: train - path: test/eng_Latn-tzj_Latn.jsonl.gz split: test - path: validation/eng_Latn-tzj_Latn.jsonl.gz split: validation - config_name: eng_Latn-kze_Latn data_files: - path: train/eng_Latn-kze_Latn.jsonl.gz split: train - path: test/eng_Latn-kze_Latn.jsonl.gz split: test - path: validation/eng_Latn-kze_Latn.jsonl.gz split: validation - config_name: eng_Latn-not_Latn data_files: - path: train/eng_Latn-not_Latn.jsonl.gz split: train - path: test/eng_Latn-not_Latn.jsonl.gz split: test - path: validation/eng_Latn-not_Latn.jsonl.gz split: validation - config_name: eng_Latn-lin_Latn data_files: - path: train/eng_Latn-lin_Latn.jsonl.gz split: train - path: test/eng_Latn-lin_Latn.jsonl.gz split: test - path: validation/eng_Latn-lin_Latn.jsonl.gz split: validation - config_name: eng_Latn-urd_Arab data_files: - path: train/eng_Latn-urd_Arab.jsonl.gz split: train - path: test/eng_Latn-urd_Arab.jsonl.gz split: test - path: validation/eng_Latn-urd_Arab.jsonl.gz split: validation - config_name: eng_Latn-mlh_Latn data_files: - path: train/eng_Latn-mlh_Latn.jsonl.gz split: train - path: test/eng_Latn-mlh_Latn.jsonl.gz split: test - path: validation/eng_Latn-mlh_Latn.jsonl.gz split: validation - config_name: eng_Latn-muy_Latn data_files: - path: train/eng_Latn-muy_Latn.jsonl.gz split: train - path: test/eng_Latn-muy_Latn.jsonl.gz split: test - path: validation/eng_Latn-muy_Latn.jsonl.gz split: validation - config_name: eng_Latn-iws_Latn data_files: - path: train/eng_Latn-iws_Latn.jsonl.gz split: train - path: test/eng_Latn-iws_Latn.jsonl.gz split: test - path: validation/eng_Latn-iws_Latn.jsonl.gz split: validation - config_name: eng_Latn-tur_Latn data_files: - path: train/eng_Latn-tur_Latn.jsonl.gz split: train - path: test/eng_Latn-tur_Latn.jsonl.gz split: test - path: validation/eng_Latn-tur_Latn.jsonl.gz split: validation - config_name: eng_Latn-gam_Latn data_files: - path: train/eng_Latn-gam_Latn.jsonl.gz split: train - path: test/eng_Latn-gam_Latn.jsonl.gz split: test - path: validation/eng_Latn-gam_Latn.jsonl.gz split: validation - config_name: eng_Latn-kbc_Latn data_files: - path: train/eng_Latn-kbc_Latn.jsonl.gz split: train - path: test/eng_Latn-kbc_Latn.jsonl.gz split: test - path: validation/eng_Latn-kbc_Latn.jsonl.gz split: validation - config_name: eng_Latn-kgf_Latn data_files: - path: train/eng_Latn-kgf_Latn.jsonl.gz split: train - path: test/eng_Latn-kgf_Latn.jsonl.gz split: test - path: validation/eng_Latn-kgf_Latn.jsonl.gz split: validation - config_name: eng_Latn-maz_Latn data_files: - path: train/eng_Latn-maz_Latn.jsonl.gz split: train - path: test/eng_Latn-maz_Latn.jsonl.gz split: test - path: validation/eng_Latn-maz_Latn.jsonl.gz split: validation - config_name: eng_Latn-nss_Latn data_files: - path: train/eng_Latn-nss_Latn.jsonl.gz split: train - path: test/eng_Latn-nss_Latn.jsonl.gz split: test - path: validation/eng_Latn-nss_Latn.jsonl.gz split: validation - config_name: eng_Latn-ake_Latn data_files: - path: train/eng_Latn-ake_Latn.jsonl.gz split: train - path: test/eng_Latn-ake_Latn.jsonl.gz split: test - path: validation/eng_Latn-ake_Latn.jsonl.gz split: validation - config_name: eng_Latn-nuy_Latn data_files: - path: train/eng_Latn-nuy_Latn.jsonl.gz split: train - path: test/eng_Latn-nuy_Latn.jsonl.gz split: test - path: validation/eng_Latn-nuy_Latn.jsonl.gz split: validation - config_name: eng_Latn-bjk_Latn data_files: - path: train/eng_Latn-bjk_Latn.jsonl.gz split: train - path: test/eng_Latn-bjk_Latn.jsonl.gz split: test - path: validation/eng_Latn-bjk_Latn.jsonl.gz split: validation - config_name: eng_Latn-mzz_Latn data_files: - path: train/eng_Latn-mzz_Latn.jsonl.gz split: train - path: test/eng_Latn-mzz_Latn.jsonl.gz split: test - path: validation/eng_Latn-mzz_Latn.jsonl.gz split: validation - config_name: eng_Latn-msy_Latn data_files: - path: train/eng_Latn-msy_Latn.jsonl.gz split: train - path: test/eng_Latn-msy_Latn.jsonl.gz split: test - path: validation/eng_Latn-msy_Latn.jsonl.gz split: validation - config_name: eng_Latn-anh_Latn data_files: - path: train/eng_Latn-anh_Latn.jsonl.gz split: train - path: test/eng_Latn-anh_Latn.jsonl.gz split: test - path: validation/eng_Latn-anh_Latn.jsonl.gz split: validation - config_name: eng_Latn-bea_Latn data_files: - path: train/eng_Latn-bea_Latn.jsonl.gz split: train - path: test/eng_Latn-bea_Latn.jsonl.gz split: test - path: validation/eng_Latn-bea_Latn.jsonl.gz split: validation - config_name: eng_Latn-ntj_Latn data_files: - path: train/eng_Latn-ntj_Latn.jsonl.gz split: train - path: test/eng_Latn-ntj_Latn.jsonl.gz split: test - path: validation/eng_Latn-ntj_Latn.jsonl.gz split: validation - config_name: eng_Latn-anv_Latn data_files: - path: train/eng_Latn-anv_Latn.jsonl.gz split: train - path: test/eng_Latn-anv_Latn.jsonl.gz split: test - path: validation/eng_Latn-anv_Latn.jsonl.gz split: validation - config_name: eng_Latn-xed_Latn data_files: - path: train/eng_Latn-xed_Latn.jsonl.gz split: train - path: test/eng_Latn-xed_Latn.jsonl.gz split: test - path: validation/eng_Latn-xed_Latn.jsonl.gz split: validation - config_name: eng_Latn-nho_Latn data_files: - path: train/eng_Latn-nho_Latn.jsonl.gz split: train - path: test/eng_Latn-nho_Latn.jsonl.gz split: test - path: validation/eng_Latn-nho_Latn.jsonl.gz split: validation - config_name: eng_Latn-cbc_Latn data_files: - path: train/eng_Latn-cbc_Latn.jsonl.gz split: train - path: test/eng_Latn-cbc_Latn.jsonl.gz split: test - path: validation/eng_Latn-cbc_Latn.jsonl.gz split: validation - config_name: eng_Latn-qve_Latn data_files: - path: train/eng_Latn-qve_Latn.jsonl.gz split: train - path: test/eng_Latn-qve_Latn.jsonl.gz split: test - path: validation/eng_Latn-qve_Latn.jsonl.gz split: validation - config_name: eng_Latn-amp_Latn data_files: - path: train/eng_Latn-amp_Latn.jsonl.gz split: train - path: test/eng_Latn-amp_Latn.jsonl.gz split: test - path: validation/eng_Latn-amp_Latn.jsonl.gz split: validation - config_name: eng_Latn-qvc_Latn data_files: - path: train/eng_Latn-qvc_Latn.jsonl.gz split: train - path: test/eng_Latn-qvc_Latn.jsonl.gz split: test - path: validation/eng_Latn-qvc_Latn.jsonl.gz split: validation - config_name: eng_Latn-aka_Latn data_files: - path: train/eng_Latn-aka_Latn.jsonl.gz split: train - path: test/eng_Latn-aka_Latn.jsonl.gz split: test - path: validation/eng_Latn-aka_Latn.jsonl.gz split: validation - config_name: eng_Latn-aby_Latn data_files: - path: train/eng_Latn-aby_Latn.jsonl.gz split: train - path: test/eng_Latn-aby_Latn.jsonl.gz split: test - path: validation/eng_Latn-aby_Latn.jsonl.gz split: validation - config_name: eng_Latn-myu_Latn data_files: - path: train/eng_Latn-myu_Latn.jsonl.gz split: train - path: test/eng_Latn-myu_Latn.jsonl.gz split: test - path: validation/eng_Latn-myu_Latn.jsonl.gz split: validation - config_name: eng_Latn-aak_Arab data_files: - path: train/eng_Latn-aak_Arab.jsonl.gz split: train - path: test/eng_Latn-aak_Arab.jsonl.gz split: test - path: validation/eng_Latn-aak_Arab.jsonl.gz split: validation - config_name: eng_Latn-soq_Latn data_files: - path: train/eng_Latn-soq_Latn.jsonl.gz split: train - path: test/eng_Latn-soq_Latn.jsonl.gz split: test - path: validation/eng_Latn-soq_Latn.jsonl.gz split: validation - config_name: eng_Latn-tif_Latn data_files: - path: train/eng_Latn-tif_Latn.jsonl.gz split: train - path: test/eng_Latn-tif_Latn.jsonl.gz split: test - path: validation/eng_Latn-tif_Latn.jsonl.gz split: validation - config_name: eng_Latn-aai_Latn data_files: - path: train/eng_Latn-aai_Latn.jsonl.gz split: train - path: test/eng_Latn-aai_Latn.jsonl.gz split: test - path: validation/eng_Latn-aai_Latn.jsonl.gz split: validation - config_name: eng_Latn-nnq_Latn data_files: - path: train/eng_Latn-nnq_Latn.jsonl.gz split: train - path: test/eng_Latn-nnq_Latn.jsonl.gz split: test - path: validation/eng_Latn-nnq_Latn.jsonl.gz split: validation - config_name: eng_Latn-sab_Latn data_files: - path: train/eng_Latn-sab_Latn.jsonl.gz split: train - path: test/eng_Latn-sab_Latn.jsonl.gz split: test - path: validation/eng_Latn-sab_Latn.jsonl.gz split: validation - config_name: eng_Latn-wmw_Latn data_files: - path: train/eng_Latn-wmw_Latn.jsonl.gz split: train - path: test/eng_Latn-wmw_Latn.jsonl.gz split: test - path: validation/eng_Latn-wmw_Latn.jsonl.gz split: validation - config_name: eng_Latn-dgc_Latn data_files: - path: train/eng_Latn-dgc_Latn.jsonl.gz split: train - path: test/eng_Latn-dgc_Latn.jsonl.gz split: test - path: validation/eng_Latn-dgc_Latn.jsonl.gz split: validation - config_name: eng_Latn-roo_Latn data_files: - path: train/eng_Latn-roo_Latn.jsonl.gz split: train - path: test/eng_Latn-roo_Latn.jsonl.gz split: test - path: validation/eng_Latn-roo_Latn.jsonl.gz split: validation - config_name: eng_Latn-tcs_Latn data_files: - path: train/eng_Latn-tcs_Latn.jsonl.gz split: train - path: test/eng_Latn-tcs_Latn.jsonl.gz split: test - path: validation/eng_Latn-tcs_Latn.jsonl.gz split: validation - config_name: eng_Latn-mxb_Latn data_files: - path: train/eng_Latn-mxb_Latn.jsonl.gz split: train - path: test/eng_Latn-mxb_Latn.jsonl.gz split: test - path: validation/eng_Latn-mxb_Latn.jsonl.gz split: validation - config_name: eng_Latn-kde_Latn data_files: - path: train/eng_Latn-kde_Latn.jsonl.gz split: train - path: test/eng_Latn-kde_Latn.jsonl.gz split: test - path: validation/eng_Latn-kde_Latn.jsonl.gz split: validation --- This dataset pre-computes all English-centric directions from [bible-nlp/biblenlp-corpus](https://huggingface.co/datasets/bible-nlp/biblenlp-corpus), and as a result loading is significantly faster. Loading example: ```python >>> from datasets import load_dataset >>> dataset = load_dataset("davidstap/biblenlp-corpus-mmteb", "eng-arb", trust_remote_code=True) >>> dataset DatasetDict({ train: Dataset({ features: ['eng', 'arb'], num_rows: 28723 }) validation: Dataset({ features: ['eng', 'arb'], num_rows: 1578 }) test: Dataset({ features: ['eng', 'arb'], num_rows: 1551 }) }) >>> ``` Note that in all possible configurations, `eng` comes before the other language.

open-web-math/open-web-math

open-web-math

"2023-10-17T20:14:00Z"

18,540

312

[ "size_categories:1M<n<10M", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "arxiv:2310.06786", "region:us" ]

null

"2023-09-06T00:25:12Z"

--- dataset_info: features: - name: url dtype: string - name: text dtype: string - name: date dtype: string - name: metadata dtype: string splits: - name: train num_bytes: 56651995057 num_examples: 6315233 download_size: 16370689925 dataset_size: 56651995057 license: odc-by task_categories: - text-generation language: - en pretty_name: OpenWebMath size_categories: - 10B<n<100B --- <img src="imgs/OpenWebMath-left.png" width="300"> [Keiran Paster](https://keirp.com)\*, [Marco Dos Santos](https://marco-dossantos.github.io/)\*, [Zhangir Azerbayev](https://zhangir-azerbayev.github.io/), [Jimmy Ba](https://jimmylba.github.io/) [GitHub ](https://github.com/keirp/OpenWebMath) | [ArXiv](https://arxiv.org/abs/2310.06786) | [PDF](https://arxiv.org/pdf/2310.06786.pdf) **OpenWebMath** is a dataset containing the majority of the high-quality, mathematical text from the internet. It is filtered and extracted from over 200B HTML files on Common Crawl down to a set of **6.3 million documents** containing a total of **14.7B tokens**. OpenWebMath is intended for use in _pretraining_ and _finetuning_ large language models. You can download the dataset using Hugging Face: ```python from datasets import load_dataset ds = load_dataset("open-web-math/open-web-math") ``` # OpenWebMath Contents The dataset is structured as follows: ```python { "text": ..., # document text. "url": ..., # document url. "date": ..., # date the page was crawled. "metadata": ..., # JSON containing information from the extraction process. } ``` OpenWebMath contains documents from over 130k different domains, including data from forums, educational pages, and blogs. The dataset contains documents covering mathematics, physics, statistics, computer science, and more. The following table shows the most common domains in OpenWebMath by character count. | Domain | # Characters | % Characters | | ----------------- | ------------- | ------------ | | stackexchange.com | 4,655,132,784 | 9.55% | | nature.com | 1,529,935,838 | 3.14% | | wordpress.com | 1,294,166,938 | 2.66% | | physicsforums.com | 1,160,137,919 | 2.38% | | github.io | 725,689,722 | 1.49% | | zbmath.org | 620,019,503 | 1.27% | | wikipedia.org | 618,024,754 | 1.27% | | groundai.com | 545,214,990 | 1.12% | | blogspot.com | 520,392,333 | 1.07% | | mathoverflow.net | 499,102,560 | 1.02% | # OpenWebMath Pipeline <img src="imgs/pipeline.png" alt="Overview of the OpenWebMath Pipeline"> OpenWebMath builds on the massive [Common Crawl](https://commoncrawl.org/) dataset, which contains over 200B HTML documents. We filtered the data to only include documents that are: (1) in English, (2) contain mathematical content, and (3) are of high quality. We also put a strong emphasis on extracting LaTeX content from the HTML documents as well as reducing boilerplate in comparison to other web datasets. The OpenWebMath pipeline consists of five steps: 1. **Prefiltering HTML Documents**: - We apply a simple prefilter to all HTML documents in Common Crawl in order to skip documents without mathematical content to unnecessary processing time. 2. **Text Extraction**: - Extract text, including LaTeX content, from the HTML documents while removing boilerplate. 3. **Content Classification and Filtering**: - Apply a [FastText language identification model](https://fasttext.cc/docs/en/language-identification.html) to keep only English documents. - Filter high perplexity documents using a [KenLM](https://github.com/kpu/kenlm) model trained on [Proof-Pile](https://huggingface.co/datasets/hoskinson-center/proof-pile). - Filter non-mathematical documents using our own _MathScore_ model. 4. **Deduplication**: - Deduplicate the dataset using SimHash in [text-dedup](https://github.com/ChenghaoMou/text-dedup). 5. **Manual Inspection**: - Inspect the documents gathered from previous steps and remove low quality pages. For a detailed discussion on the processing pipeline, please refer to our paper. # License OpenWebMath is made available under an ODC-By 1.0 license; users should also abide by the CommonCrawl ToU: [https://commoncrawl.org/terms-of-use/](https://commoncrawl.org/terms-of-use/). We do not alter the license of any of the underlying data. # Citation Information ``` @misc{paster2023openwebmath, title={OpenWebMath: An Open Dataset of High-Quality Mathematical Web Text}, author={Keiran Paster and Marco Dos Santos and Zhangir Azerbayev and Jimmy Ba}, year={2023}, eprint={2310.06786}, archivePrefix={arXiv}, primaryClass={cs.AI} } ```

hails/bigbench

hails

"2023-11-17T16:05:10Z"

18,449

4

[ "size_categories:1M<n<10M", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]

null

"2023-10-03T19:55:51Z"

--- dataset_info: - config_name: abstract_narrative_understanding_zero_shot 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: 0 dataset_size: 13120138 - config_name: anachronisms_zero_shot 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: 0 dataset_size: 97652 - config_name: analogical_similarity_zero_shot 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: 0 dataset_size: 2747630 - config_name: analytic_entailment_zero_shot 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: 0 dataset_size: 34632 - config_name: arithmetic_zero_shot 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: 0 dataset_size: 7666544 - config_name: ascii_word_recognition_zero_shot 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: 0 dataset_size: 9969324 - config_name: authorship_verification_zero_shot 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: 0 dataset_size: 28237184 - config_name: auto_categorization_zero_shot 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: 0 dataset_size: 81098 - config_name: auto_debugging_zero_shot 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: 5112 num_examples: 34 - name: train num_bytes: 2651 num_examples: 18 - name: validation num_bytes: 2461 num_examples: 16 download_size: 0 dataset_size: 10224 - config_name: bbq_lite_json_zero_shot 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: 0 dataset_size: 13780986 - config_name: bridging_anaphora_resolution_barqa_zero_shot 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: 0 dataset_size: 3942030 - config_name: causal_judgment_zero_shot 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: 0 dataset_size: 409756 - config_name: cause_and_effect_zero_shot 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: 0 dataset_size: 98628 - config_name: checkmate_in_one_zero_shot 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: 0 dataset_size: 6246512 - config_name: chess_state_tracking_zero_shot 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: 0 dataset_size: 6539864 - config_name: chinese_remainder_theorem_zero_shot 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: 0 dataset_size: 306444 - config_name: cifar10_classification_zero_shot 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: 0 dataset_size: 222044400 - config_name: code_line_description_zero_shot 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: 0 dataset_size: 67340 - config_name: codenames_zero_shot 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: 0 dataset_size: 50390 - config_name: color_zero_shot 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: 0 dataset_size: 3266526 - config_name: common_morpheme_zero_shot 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: 0 dataset_size: 24776 - config_name: conceptual_combinations_zero_shot 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: 0 dataset_size: 117718 - config_name: conlang_translation_zero_shot 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: 0 dataset_size: 430380 - config_name: contextual_parametric_knowledge_conflicts_zero_shot 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: 0 dataset_size: 29175108 - config_name: crash_blossom_zero_shot 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: 0 dataset_size: 24388 - config_name: crass_ai_zero_shot 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: 0 dataset_size: 45740 - config_name: cryobiology_spanish_zero_shot 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: 0 dataset_size: 77348 - config_name: cryptonite_zero_shot 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: 0 dataset_size: 5688804 - config_name: cs_algorithms_zero_shot 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: 0 dataset_size: 544870 - config_name: dark_humor_detection_zero_shot 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: 0 dataset_size: 53112 - config_name: date_understanding_zero_shot 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: 0 dataset_size: 189816 - config_name: disambiguation_qa_zero_shot 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: 0 dataset_size: 244942 - config_name: discourse_marker_prediction_zero_shot 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: 0 dataset_size: 4181368 - config_name: disfl_qa_zero_shot 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: 0 dataset_size: 15929550 - config_name: dyck_languages_zero_shot 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: 0 dataset_size: 2455832 - config_name: elementary_math_qa_zero_shot 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: 0 dataset_size: 26885100 - config_name: emoji_movie_zero_shot 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: 0 dataset_size: 67334 - config_name: emojis_emotion_prediction_zero_shot 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: 0 dataset_size: 95966 - config_name: empirical_judgments_zero_shot 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: 0 dataset_size: 94998 - config_name: english_proverbs_zero_shot 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: 0 dataset_size: 45060 - config_name: english_russian_proverbs_zero_shot 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: 0 dataset_size: 119800 - config_name: entailed_polarity_hindi_zero_shot 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: 0 dataset_size: 114104 - config_name: entailed_polarity_zero_shot 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: 0 dataset_size: 50842 - config_name: epistemic_reasoning_zero_shot 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: 0 dataset_size: 1774316 - config_name: evaluating_information_essentiality_zero_shot 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: 0 dataset_size: 154976 - config_name: fact_checker_zero_shot 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: 0 dataset_size: 2674768 - config_name: fantasy_reasoning_zero_shot 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: 0 dataset_size: 151772 - config_name: few_shot_nlg_zero_shot 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: 0 dataset_size: 151874 - config_name: figure_of_speech_detection_zero_shot 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: 0 dataset_size: 43434 - config_name: formal_fallacies_syllogisms_negation_zero_shot 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: 0 dataset_size: 16629306 - config_name: gem_zero_shot 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: 0 dataset_size: 72130562 - config_name: gender_inclusive_sentences_german_zero_shot 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: 0 dataset_size: 253762 - config_name: general_knowledge_zero_shot 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: 0 dataset_size: 43656 - config_name: geometric_shapes_zero_shot 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: 0 dataset_size: 360188 - config_name: goal_step_wikihow_zero_shot 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: 0 dataset_size: 7135230 - config_name: gre_reading_comprehension_zero_shot 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: 0 dataset_size: 188546 - config_name: hhh_alignment_zero_shot 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: 0 dataset_size: 545796 - config_name: hindi_question_answering_zero_shot 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: 0 dataset_size: 30309908 - config_name: hindu_knowledge_zero_shot 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: 0 dataset_size: 88184 - config_name: hinglish_toxicity_zero_shot 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: 0 dataset_size: 121226 - config_name: human_organs_senses_zero_shot 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: 0 dataset_size: 15888 - config_name: hyperbaton_zero_shot 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: 0 dataset_size: 18767972 - config_name: identify_math_theorems_zero_shot 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: 0 dataset_size: 209682 - config_name: identify_odd_metaphor_zero_shot 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: 0 dataset_size: 55204 - config_name: implicatures_zero_shot 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: 0 dataset_size: 183366 - config_name: implicit_relations_zero_shot 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: 0 dataset_size: 159420 - config_name: intent_recognition_zero_shot 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: 0 dataset_size: 644742 - config_name: international_phonetic_alphabet_nli_zero_shot 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: 0 dataset_size: 158640 - config_name: international_phonetic_alphabet_transliterate_zero_shot 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: 0 dataset_size: 551876 - config_name: intersect_geometry_zero_shot 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: 0 dataset_size: 423349504 - config_name: irony_identification_zero_shot 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: 0 dataset_size: 56356 - config_name: kanji_ascii_zero_shot 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: 0 dataset_size: 733892 - config_name: kannada_zero_shot 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: 0 dataset_size: 281276 - config_name: key_value_maps_zero_shot 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: 0 dataset_size: 210272 - config_name: known_unknowns_zero_shot 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: 0 dataset_size: 15920 - config_name: language_games_zero_shot 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: 0 dataset_size: 1959238 - config_name: language_identification_zero_shot 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: 0 dataset_size: 14752446 - config_name: linguistic_mappings_zero_shot 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: 0 dataset_size: 2650372 - config_name: linguistics_puzzles_zero_shot 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: 0 dataset_size: 3492048 - config_name: list_functions_zero_shot 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: 2678136 num_examples: 10750 - name: train num_bytes: 2161065 num_examples: 8700 - name: validation num_bytes: 517071 num_examples: 2050 download_size: 0 dataset_size: 5356272 - config_name: logic_grid_puzzle_zero_shot 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: 0 dataset_size: 2912436 - config_name: logical_args_zero_shot 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: 0 dataset_size: 87164 - config_name: logical_deduction_zero_shot 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: 0 dataset_size: 2113432 - config_name: logical_fallacy_detection_zero_shot 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: 0 dataset_size: 1440572 - config_name: logical_sequence_zero_shot 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: 0 dataset_size: 45444 - config_name: mathematical_induction_zero_shot 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: 0 dataset_size: 38036 - config_name: matrixshapes_zero_shot 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: 0 dataset_size: 2261148 - config_name: metaphor_boolean_zero_shot 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: 0 dataset_size: 427696 - config_name: metaphor_understanding_zero_shot 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: 0 dataset_size: 401724 - config_name: minute_mysteries_qa_zero_shot 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: 0 dataset_size: 6490380 - config_name: misconceptions_russian_zero_shot 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: 0 dataset_size: 33982 - config_name: misconceptions_zero_shot 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: 0 dataset_size: 91632 - config_name: mnist_ascii_zero_shot 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: 0 dataset_size: 123479616 - config_name: modified_arithmetic_zero_shot 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: 0 dataset_size: 2441986 - config_name: moral_permissibility_zero_shot 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: 0 dataset_size: 324136 - config_name: movie_dialog_same_or_different_zero_shot 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: 0 dataset_size: 57291994 - config_name: movie_recommendation_zero_shot 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: 0 dataset_size: 347114 - config_name: mult_data_wrangling_zero_shot 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: 0 dataset_size: 1250844 - config_name: multiemo_zero_shot 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: 650173925 num_examples: 1437281 - name: train num_bytes: 520172185 num_examples: 1149873 - name: validation num_bytes: 130001740 num_examples: 287408 download_size: 0 dataset_size: 1300347850 - config_name: natural_instructions_zero_shot 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: 355938370 num_examples: 193250 - name: train num_bytes: 284920096 num_examples: 154615 - name: validation num_bytes: 71018274 num_examples: 38635 download_size: 0 dataset_size: 711876740 - config_name: navigate_zero_shot 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: 225813 num_examples: 1000 - name: train num_bytes: 180958 num_examples: 800 - name: validation num_bytes: 44855 num_examples: 200 download_size: 83744 dataset_size: 451626 - config_name: nonsense_words_grammar_zero_shot 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: 11102 num_examples: 50 - name: train num_bytes: 7582 num_examples: 34 - name: validation num_bytes: 3520 num_examples: 16 download_size: 24107 dataset_size: 22204 - config_name: novel_concepts_zero_shot 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: 16065 num_examples: 32 - name: train num_bytes: 8128 num_examples: 16 - name: validation num_bytes: 7937 num_examples: 16 download_size: 25919 dataset_size: 32130 - config_name: object_counting_zero_shot 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: 149555 num_examples: 1000 - name: train num_bytes: 119609 num_examples: 800 - name: validation num_bytes: 29946 num_examples: 200 download_size: 91852 dataset_size: 299110 - config_name: odd_one_out_zero_shot 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: 13843 num_examples: 86 - name: train num_bytes: 11217 num_examples: 69 - name: validation num_bytes: 2626 num_examples: 17 download_size: 25796 dataset_size: 27686 - config_name: operators_zero_shot 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: 32435 num_examples: 210 - name: train num_bytes: 25937 num_examples: 168 - name: validation num_bytes: 6498 num_examples: 42 download_size: 24728 dataset_size: 64870 - config_name: paragraph_segmentation_zero_shot 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: 56846507 num_examples: 9000 - name: train num_bytes: 45674320 num_examples: 7200 - name: validation num_bytes: 11172187 num_examples: 1800 download_size: 61123049 dataset_size: 113693014 - config_name: parsinlu_qa_zero_shot 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: 456189 num_examples: 1050 - name: train num_bytes: 366577 num_examples: 840 - name: validation num_bytes: 89612 num_examples: 210 download_size: 465963 dataset_size: 912378 - config_name: parsinlu_reading_comprehension_zero_shot 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: 573798 num_examples: 518 - name: train num_bytes: 455828 num_examples: 415 - name: validation num_bytes: 117970 num_examples: 103 download_size: 572992 dataset_size: 1147596 - config_name: penguins_in_a_table_zero_shot 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: 75985 num_examples: 149 - name: train num_bytes: 61321 num_examples: 120 - name: validation num_bytes: 14664 num_examples: 29 download_size: 32039 dataset_size: 151970 - config_name: periodic_elements_zero_shot 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: 285204 num_examples: 654 - name: train num_bytes: 229481 num_examples: 524 - name: validation num_bytes: 55723 num_examples: 130 download_size: 41084 dataset_size: 570408 - config_name: persian_idioms_zero_shot 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: 28592 num_examples: 66 - name: train num_bytes: 21684 num_examples: 50 - name: validation num_bytes: 6908 num_examples: 16 download_size: 34341 dataset_size: 57184 - config_name: phrase_relatedness_zero_shot 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: 30190 num_examples: 100 - name: train num_bytes: 23773 num_examples: 80 - name: validation num_bytes: 6417 num_examples: 20 download_size: 40334 dataset_size: 60380 - config_name: physical_intuition_zero_shot 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: 23734 num_examples: 81 - name: train num_bytes: 19307 num_examples: 65 - name: validation num_bytes: 4427 num_examples: 16 download_size: 28462 dataset_size: 47468 - config_name: physics_questions_zero_shot 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: 18372 num_examples: 54 - name: train num_bytes: 13402 num_examples: 38 - name: validation num_bytes: 4970 num_examples: 16 download_size: 35187 dataset_size: 36744 - config_name: physics_zero_shot 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: 120239 num_examples: 229 - name: train num_bytes: 96122 num_examples: 184 - name: validation num_bytes: 24117 num_examples: 45 download_size: 69885 dataset_size: 240478 - config_name: play_dialog_same_or_different_zero_shot 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: 3142468 num_examples: 3264 - name: train num_bytes: 2516052 num_examples: 2612 - name: validation num_bytes: 626416 num_examples: 652 download_size: 1710264 dataset_size: 6284936 - config_name: polish_sequence_labeling_zero_shot 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: 18081112 num_examples: 12812 - name: train num_bytes: 14470720 num_examples: 10250 - name: validation num_bytes: 3610392 num_examples: 2562 download_size: 5242934 dataset_size: 36162224 - config_name: presuppositions_as_nli_zero_shot 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: 502522 num_examples: 735 - name: train num_bytes: 400761 num_examples: 588 - name: validation num_bytes: 101761 num_examples: 147 download_size: 240065 dataset_size: 1005044 - config_name: qa_wikidata_zero_shot 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: 1419042 num_examples: 20321 - name: train num_bytes: 1134918 num_examples: 16257 - name: validation num_bytes: 284124 num_examples: 4064 download_size: 1181835 dataset_size: 2838084 - config_name: question_selection_zero_shot 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: 2487181 num_examples: 1582 - name: train num_bytes: 1990094 num_examples: 1266 - name: validation num_bytes: 497087 num_examples: 316 download_size: 1804283 dataset_size: 4974362 - config_name: real_or_fake_text_zero_shot 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: 53663318 num_examples: 15088 - name: train num_bytes: 42879846 num_examples: 12072 - name: validation num_bytes: 10783472 num_examples: 3016 download_size: 47399045 dataset_size: 107326636 - config_name: reasoning_about_colored_objects_zero_shot 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: 907474 num_examples: 2000 - name: train num_bytes: 729609 num_examples: 1600 - name: validation num_bytes: 177865 num_examples: 400 download_size: 273263 dataset_size: 1814948 - config_name: repeat_copy_logic_zero_shot 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: 6678 num_examples: 32 - name: train num_bytes: 3327 num_examples: 16 - name: validation num_bytes: 3351 num_examples: 16 download_size: 18315 dataset_size: 13356 - config_name: rephrase_zero_shot 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: 34222 num_examples: 78 - name: train num_bytes: 27360 num_examples: 62 - name: validation num_bytes: 6862 num_examples: 16 download_size: 41102 dataset_size: 68444 - config_name: riddle_sense_zero_shot 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: 15507 num_examples: 49 - name: train num_bytes: 10741 num_examples: 33 - name: validation num_bytes: 4766 num_examples: 16 download_size: 32496 dataset_size: 31014 - config_name: ruin_names_zero_shot 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: 144087 num_examples: 448 - name: train num_bytes: 115171 num_examples: 359 - name: validation num_bytes: 28916 num_examples: 89 download_size: 118193 dataset_size: 288174 - config_name: salient_translation_error_detection_zero_shot 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: 1141626 num_examples: 998 - name: train num_bytes: 912819 num_examples: 799 - name: validation num_bytes: 228807 num_examples: 199 download_size: 413634 dataset_size: 2283252 - config_name: scientific_press_release_zero_shot 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: 13690 num_examples: 50 - name: train num_bytes: 9254 num_examples: 34 - name: validation num_bytes: 4436 num_examples: 16 download_size: 27293 dataset_size: 27380 - config_name: semantic_parsing_in_context_sparc_zero_shot 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: 1524852 num_examples: 1155 - name: train num_bytes: 1248391 num_examples: 924 - name: validation num_bytes: 276461 num_examples: 231 download_size: 440326 dataset_size: 3049704 - config_name: semantic_parsing_spider_zero_shot 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: 1265744 num_examples: 1034 - name: train num_bytes: 973864 num_examples: 828 - name: validation num_bytes: 291880 num_examples: 206 download_size: 358276 dataset_size: 2531488 - config_name: sentence_ambiguity_zero_shot 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: 8168 num_examples: 60 - name: train num_bytes: 5976 num_examples: 44 - name: validation num_bytes: 2192 num_examples: 16 download_size: 18275 dataset_size: 16336 - config_name: similarities_abstraction_zero_shot 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: 23416 num_examples: 76 - name: train num_bytes: 18545 num_examples: 60 - name: validation num_bytes: 4871 num_examples: 16 download_size: 31521 dataset_size: 46832 - config_name: simp_turing_concept_zero_shot 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: 1017646 num_examples: 6390 - name: train num_bytes: 813220 num_examples: 5112 - name: validation num_bytes: 204426 num_examples: 1278 download_size: 402574 dataset_size: 2035292 - config_name: simple_arithmetic_json_multiple_choice_zero_shot 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: 924 num_examples: 8 - name: train num_bytes: 0 num_examples: 0 - name: validation num_bytes: 0 num_examples: 0 download_size: 7777 dataset_size: 924 - config_name: simple_arithmetic_json_subtasks_zero_shot 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: 1145 num_examples: 30 - name: train num_bytes: 571 num_examples: 15 - name: validation num_bytes: 574 num_examples: 15 download_size: 10460 dataset_size: 2290 - config_name: simple_arithmetic_json_zero_shot 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: 1145 num_examples: 30 - name: train num_bytes: 540 num_examples: 14 - name: validation num_bytes: 605 num_examples: 16 download_size: 10645 dataset_size: 2290 - config_name: simple_arithmetic_multiple_targets_json_zero_shot 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: 414 num_examples: 10 - name: train num_bytes: 0 num_examples: 0 - name: validation num_bytes: 0 num_examples: 0 download_size: 7352 dataset_size: 414 - config_name: simple_ethical_questions_zero_shot 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: 76518 num_examples: 115 - name: train num_bytes: 60275 num_examples: 92 - name: validation num_bytes: 16243 num_examples: 23 download_size: 81285 dataset_size: 153036 - config_name: simple_text_editing_zero_shot 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: 27865 num_examples: 47 - name: train num_bytes: 18469 num_examples: 31 - name: validation num_bytes: 9396 num_examples: 16 download_size: 27100 dataset_size: 55730 - config_name: snarks_zero_shot 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: 45717 num_examples: 181 - name: train num_bytes: 36989 num_examples: 145 - name: validation num_bytes: 8728 num_examples: 36 download_size: 45434 dataset_size: 91434 - config_name: social_iqa_zero_shot 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: 643162 num_examples: 1935 - name: train num_bytes: 515686 num_examples: 1548 - name: validation num_bytes: 127476 num_examples: 387 download_size: 684043 dataset_size: 1286324 - config_name: social_support_zero_shot 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: 366705 num_examples: 897 - name: train num_bytes: 294793 num_examples: 718 - name: validation num_bytes: 71912 num_examples: 179 download_size: 288867 dataset_size: 733410 - config_name: sports_understanding_zero_shot 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: 226654 num_examples: 986 - name: train num_bytes: 181328 num_examples: 789 - name: validation num_bytes: 45326 num_examples: 197 download_size: 82415 dataset_size: 453308 - config_name: strange_stories_zero_shot 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: 120500 num_examples: 174 - name: train num_bytes: 98055 num_examples: 140 - name: validation num_bytes: 22445 num_examples: 34 download_size: 106428 dataset_size: 241000 - config_name: strategyqa_zero_shot 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: 659967 num_examples: 2289 - name: train num_bytes: 527670 num_examples: 1832 - name: validation num_bytes: 132297 num_examples: 457 download_size: 814405 dataset_size: 1319934 - config_name: sufficient_information_zero_shot 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: 9425 num_examples: 39 - name: train num_bytes: 5594 num_examples: 23 - name: validation num_bytes: 3831 num_examples: 16 download_size: 17766 dataset_size: 18850 - config_name: suicide_risk_zero_shot 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: 37952 num_examples: 40 - name: train num_bytes: 23067 num_examples: 24 - name: validation num_bytes: 14885 num_examples: 16 download_size: 60518 dataset_size: 75904 - config_name: swahili_english_proverbs_zero_shot 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: 90246 num_examples: 153 - name: train num_bytes: 72467 num_examples: 123 - name: validation num_bytes: 17779 num_examples: 30 download_size: 95186 dataset_size: 180492 - config_name: swedish_to_german_proverbs_zero_shot 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: 35204 num_examples: 72 - name: train num_bytes: 27266 num_examples: 56 - name: validation num_bytes: 7938 num_examples: 16 download_size: 55102 dataset_size: 70408 - config_name: symbol_interpretation_zero_shot 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: 1148958 num_examples: 990 - name: train num_bytes: 927326 num_examples: 795 - name: validation num_bytes: 221632 num_examples: 195 download_size: 320412 dataset_size: 2297916 - config_name: temporal_sequences_zero_shot 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: 687086 num_examples: 1000 - name: train num_bytes: 549808 num_examples: 800 - name: validation num_bytes: 137278 num_examples: 200 download_size: 295316 dataset_size: 1374172 - config_name: tense_zero_shot 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: 43882 num_examples: 286 - name: train num_bytes: 35466 num_examples: 229 - name: validation num_bytes: 8416 num_examples: 57 download_size: 51466 dataset_size: 87764 - config_name: timedial_zero_shot 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: 2763178 num_examples: 2550 - name: train num_bytes: 2217190 num_examples: 2040 - name: validation num_bytes: 545988 num_examples: 510 download_size: 2444115 dataset_size: 5526356 - config_name: topical_chat_zero_shot 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: 30927758 num_examples: 22295 - name: train num_bytes: 24827254 num_examples: 17836 - name: validation num_bytes: 6100504 num_examples: 4459 download_size: 23505731 dataset_size: 61855516 - config_name: tracking_shuffled_objects_zero_shot 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: 2775972 num_examples: 3750 - name: train num_bytes: 2224037 num_examples: 3000 - name: validation num_bytes: 551935 num_examples: 750 download_size: 738413 dataset_size: 5551944 - config_name: understanding_fables_zero_shot 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: 227748 num_examples: 189 - name: train num_bytes: 181000 num_examples: 152 - name: validation num_bytes: 46748 num_examples: 37 download_size: 237036 dataset_size: 455496 - config_name: undo_permutation_zero_shot 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: 196118 num_examples: 300 - name: train num_bytes: 158562 num_examples: 240 - name: validation num_bytes: 37556 num_examples: 60 download_size: 137204 dataset_size: 392236 - config_name: unit_conversion_zero_shot 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: 4028628 num_examples: 23936 - name: train num_bytes: 3230357 num_examples: 19151 - name: validation num_bytes: 798271 num_examples: 4785 download_size: 3208622 dataset_size: 8057256 - config_name: unit_interpretation_zero_shot 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: 37363 num_examples: 100 - name: train num_bytes: 29939 num_examples: 80 - name: validation num_bytes: 7424 num_examples: 20 download_size: 34926 dataset_size: 74726 - config_name: unnatural_in_context_learning_zero_shot 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: 4599760 num_examples: 73420 - name: train num_bytes: 3679822 num_examples: 58736 - name: validation num_bytes: 919938 num_examples: 14684 download_size: 3840657 dataset_size: 9199520 - config_name: vitaminc_fact_verification_zero_shot 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: 32361818 num_examples: 54668 - name: train num_bytes: 25889850 num_examples: 43735 - name: validation num_bytes: 6471968 num_examples: 10933 download_size: 14264790 dataset_size: 64723636 - config_name: what_is_the_tao_zero_shot 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: 13268 num_examples: 36 - name: train num_bytes: 7435 num_examples: 20 - name: validation num_bytes: 5833 num_examples: 16 download_size: 27585 dataset_size: 26536 - config_name: which_wiki_edit_zero_shot 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: 6331683 num_examples: 571 - name: train num_bytes: 5233870 num_examples: 457 - name: validation num_bytes: 1097813 num_examples: 114 download_size: 3914574 dataset_size: 12663366 - config_name: winowhy_zero_shot 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: 1002434 num_examples: 2862 - name: train num_bytes: 800520 num_examples: 2290 - name: validation num_bytes: 201914 num_examples: 572 download_size: 449218 dataset_size: 2004868 - config_name: word_sorting_zero_shot 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: 491054 num_examples: 1900 - name: train num_bytes: 392738 num_examples: 1520 - name: validation num_bytes: 98316 num_examples: 380 download_size: 641536 dataset_size: 982108 - config_name: word_unscrambling_zero_shot 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: 882364 num_examples: 8917 - name: train num_bytes: 705755 num_examples: 7134 - name: validation num_bytes: 176609 num_examples: 1783 download_size: 563799 dataset_size: 1764728 configs: - config_name: abstract_narrative_understanding_zero_shot data_files: - split: default path: abstract_narrative_understanding_zero_shot/default-* - split: train path: abstract_narrative_understanding_zero_shot/train-* - split: validation path: abstract_narrative_understanding_zero_shot/validation-* - config_name: anachronisms_zero_shot data_files: - split: default path: anachronisms_zero_shot/default-* - split: train path: anachronisms_zero_shot/train-* - split: validation path: anachronisms_zero_shot/validation-* - config_name: analogical_similarity_zero_shot data_files: - split: default path: analogical_similarity_zero_shot/default-* - split: train path: analogical_similarity_zero_shot/train-* - split: validation path: analogical_similarity_zero_shot/validation-* - config_name: analytic_entailment_zero_shot data_files: - split: default path: analytic_entailment_zero_shot/default-* - split: train path: analytic_entailment_zero_shot/train-* - split: validation path: analytic_entailment_zero_shot/validation-* - config_name: arithmetic_zero_shot data_files: - split: default path: arithmetic_zero_shot/default-* - split: train path: arithmetic_zero_shot/train-* - split: validation path: arithmetic_zero_shot/validation-* - config_name: ascii_word_recognition_zero_shot data_files: - split: default path: ascii_word_recognition_zero_shot/default-* - split: train path: ascii_word_recognition_zero_shot/train-* - split: validation path: ascii_word_recognition_zero_shot/validation-* - config_name: authorship_verification_zero_shot data_files: - split: default path: authorship_verification_zero_shot/default-* - split: train path: authorship_verification_zero_shot/train-* - split: validation path: authorship_verification_zero_shot/validation-* - config_name: auto_categorization_zero_shot data_files: - split: default path: auto_categorization_zero_shot/default-* - split: train path: auto_categorization_zero_shot/train-* - split: validation path: auto_categorization_zero_shot/validation-* - config_name: auto_debugging_zero_shot data_files: - split: default path: auto_debugging_zero_shot/default-* - split: train path: auto_debugging_zero_shot/train-* - split: validation path: auto_debugging_zero_shot/validation-* - config_name: bbq_lite_json_zero_shot data_files: - split: default path: bbq_lite_json_zero_shot/default-* - split: train path: bbq_lite_json_zero_shot/train-* - split: validation path: bbq_lite_json_zero_shot/validation-* - config_name: bridging_anaphora_resolution_barqa_zero_shot data_files: - split: default path: bridging_anaphora_resolution_barqa_zero_shot/default-* - split: train path: bridging_anaphora_resolution_barqa_zero_shot/train-* - split: validation path: bridging_anaphora_resolution_barqa_zero_shot/validation-* - config_name: causal_judgment_zero_shot data_files: - split: default path: causal_judgment_zero_shot/default-* - split: train path: causal_judgment_zero_shot/train-* - split: validation path: causal_judgment_zero_shot/validation-* - config_name: cause_and_effect_zero_shot data_files: - split: default path: cause_and_effect_zero_shot/default-* - split: train path: cause_and_effect_zero_shot/train-* - split: validation path: cause_and_effect_zero_shot/validation-* - config_name: checkmate_in_one_zero_shot data_files: - split: default path: checkmate_in_one_zero_shot/default-* - split: train path: checkmate_in_one_zero_shot/train-* - split: validation path: checkmate_in_one_zero_shot/validation-* - config_name: chess_state_tracking_zero_shot data_files: - split: default path: chess_state_tracking_zero_shot/default-* - split: train path: chess_state_tracking_zero_shot/train-* - split: validation path: chess_state_tracking_zero_shot/validation-* - config_name: chinese_remainder_theorem_zero_shot data_files: - split: default path: chinese_remainder_theorem_zero_shot/default-* - split: train path: chinese_remainder_theorem_zero_shot/train-* - split: validation path: chinese_remainder_theorem_zero_shot/validation-* - config_name: cifar10_classification_zero_shot data_files: - split: default path: cifar10_classification_zero_shot/default-* - split: train path: cifar10_classification_zero_shot/train-* - split: validation path: cifar10_classification_zero_shot/validation-* - config_name: code_line_description_zero_shot data_files: - split: default path: code_line_description_zero_shot/default-* - split: train path: code_line_description_zero_shot/train-* - split: validation path: code_line_description_zero_shot/validation-* - config_name: codenames_zero_shot data_files: - split: default path: codenames_zero_shot/default-* - split: train path: codenames_zero_shot/train-* - split: validation path: codenames_zero_shot/validation-* - config_name: color_zero_shot data_files: - split: default path: color_zero_shot/default-* - split: train path: color_zero_shot/train-* - split: validation path: color_zero_shot/validation-* - config_name: common_morpheme_zero_shot data_files: - split: default path: common_morpheme_zero_shot/default-* - split: train path: common_morpheme_zero_shot/train-* - split: validation path: common_morpheme_zero_shot/validation-* - config_name: conceptual_combinations_zero_shot data_files: - split: default path: conceptual_combinations_zero_shot/default-* - split: train path: conceptual_combinations_zero_shot/train-* - split: validation path: conceptual_combinations_zero_shot/validation-* - config_name: conlang_translation_zero_shot data_files: - split: default path: conlang_translation_zero_shot/default-* - split: train path: conlang_translation_zero_shot/train-* - split: validation path: conlang_translation_zero_shot/validation-* - config_name: contextual_parametric_knowledge_conflicts_zero_shot data_files: - split: default path: contextual_parametric_knowledge_conflicts_zero_shot/default-* - split: train path: contextual_parametric_knowledge_conflicts_zero_shot/train-* - split: validation path: contextual_parametric_knowledge_conflicts_zero_shot/validation-* - config_name: crash_blossom_zero_shot data_files: - split: default path: crash_blossom_zero_shot/default-* - split: train path: crash_blossom_zero_shot/train-* - split: validation path: crash_blossom_zero_shot/validation-* - config_name: crass_ai_zero_shot data_files: - split: default path: crass_ai_zero_shot/default-* - split: train path: crass_ai_zero_shot/train-* - split: validation path: crass_ai_zero_shot/validation-* - config_name: cryobiology_spanish_zero_shot data_files: - split: default path: cryobiology_spanish_zero_shot/default-* - split: train path: cryobiology_spanish_zero_shot/train-* - split: validation path: cryobiology_spanish_zero_shot/validation-* - config_name: cryptonite_zero_shot data_files: - split: default path: cryptonite_zero_shot/default-* - split: train path: cryptonite_zero_shot/train-* - split: validation path: cryptonite_zero_shot/validation-* - config_name: cs_algorithms_zero_shot data_files: - split: default path: cs_algorithms_zero_shot/default-* - split: train path: cs_algorithms_zero_shot/train-* - split: validation path: cs_algorithms_zero_shot/validation-* - config_name: dark_humor_detection_zero_shot data_files: - split: default path: dark_humor_detection_zero_shot/default-* - split: train path: dark_humor_detection_zero_shot/train-* - split: validation path: dark_humor_detection_zero_shot/validation-* - config_name: date_understanding_zero_shot data_files: - split: default path: date_understanding_zero_shot/default-* - split: train path: date_understanding_zero_shot/train-* - split: validation path: date_understanding_zero_shot/validation-* - config_name: disambiguation_qa_zero_shot data_files: - split: default path: disambiguation_qa_zero_shot/default-* - split: train path: disambiguation_qa_zero_shot/train-* - split: validation path: disambiguation_qa_zero_shot/validation-* - config_name: discourse_marker_prediction_zero_shot data_files: - split: default path: discourse_marker_prediction_zero_shot/default-* - split: train path: discourse_marker_prediction_zero_shot/train-* - split: validation path: discourse_marker_prediction_zero_shot/validation-* - config_name: disfl_qa_zero_shot data_files: - split: default path: disfl_qa_zero_shot/default-* - split: train path: disfl_qa_zero_shot/train-* - split: validation path: disfl_qa_zero_shot/validation-* - config_name: dyck_languages_zero_shot data_files: - split: default path: dyck_languages_zero_shot/default-* - split: train path: dyck_languages_zero_shot/train-* - split: validation path: dyck_languages_zero_shot/validation-* - config_name: elementary_math_qa_zero_shot data_files: - split: default path: elementary_math_qa_zero_shot/default-* - split: train path: elementary_math_qa_zero_shot/train-* - split: validation path: elementary_math_qa_zero_shot/validation-* - config_name: emoji_movie_zero_shot data_files: - split: default path: emoji_movie_zero_shot/default-* - split: train path: emoji_movie_zero_shot/train-* - split: validation path: emoji_movie_zero_shot/validation-* - config_name: emojis_emotion_prediction_zero_shot data_files: - split: default path: emojis_emotion_prediction_zero_shot/default-* - split: train path: emojis_emotion_prediction_zero_shot/train-* - split: validation path: emojis_emotion_prediction_zero_shot/validation-* - config_name: empirical_judgments_zero_shot data_files: - split: default path: empirical_judgments_zero_shot/default-* - split: train path: empirical_judgments_zero_shot/train-* - split: validation path: empirical_judgments_zero_shot/validation-* - config_name: english_proverbs_zero_shot data_files: - split: default path: english_proverbs_zero_shot/default-* - split: train path: english_proverbs_zero_shot/train-* - split: validation path: english_proverbs_zero_shot/validation-* - config_name: english_russian_proverbs_zero_shot data_files: - split: default path: english_russian_proverbs_zero_shot/default-* - split: train path: english_russian_proverbs_zero_shot/train-* - split: validation path: english_russian_proverbs_zero_shot/validation-* - config_name: entailed_polarity_hindi_zero_shot data_files: - split: default path: entailed_polarity_hindi_zero_shot/default-* - split: train path: entailed_polarity_hindi_zero_shot/train-* - split: validation path: entailed_polarity_hindi_zero_shot/validation-* - config_name: entailed_polarity_zero_shot data_files: - split: default path: entailed_polarity_zero_shot/default-* - split: train path: entailed_polarity_zero_shot/train-* - split: validation path: entailed_polarity_zero_shot/validation-* - config_name: epistemic_reasoning_zero_shot data_files: - split: default path: epistemic_reasoning_zero_shot/default-* - split: train path: epistemic_reasoning_zero_shot/train-* - split: validation path: epistemic_reasoning_zero_shot/validation-* - config_name: evaluating_information_essentiality_zero_shot data_files: - split: default path: evaluating_information_essentiality_zero_shot/default-* - split: train path: evaluating_information_essentiality_zero_shot/train-* - split: validation path: evaluating_information_essentiality_zero_shot/validation-* - config_name: fact_checker_zero_shot data_files: - split: default path: fact_checker_zero_shot/default-* - split: train path: fact_checker_zero_shot/train-* - split: validation path: fact_checker_zero_shot/validation-* - config_name: fantasy_reasoning_zero_shot data_files: - split: default path: fantasy_reasoning_zero_shot/default-* - split: train path: fantasy_reasoning_zero_shot/train-* - split: validation path: fantasy_reasoning_zero_shot/validation-* - config_name: few_shot_nlg_zero_shot data_files: - split: default path: few_shot_nlg_zero_shot/default-* - split: train path: few_shot_nlg_zero_shot/train-* - split: validation path: few_shot_nlg_zero_shot/validation-* - config_name: figure_of_speech_detection_zero_shot data_files: - split: default path: figure_of_speech_detection_zero_shot/default-* - split: train path: figure_of_speech_detection_zero_shot/train-* - split: validation path: figure_of_speech_detection_zero_shot/validation-* - config_name: formal_fallacies_syllogisms_negation_zero_shot data_files: - split: default path: formal_fallacies_syllogisms_negation_zero_shot/default-* - split: train path: formal_fallacies_syllogisms_negation_zero_shot/train-* - split: validation path: formal_fallacies_syllogisms_negation_zero_shot/validation-* - config_name: gem_zero_shot data_files: - split: default path: gem_zero_shot/default-* - split: train path: gem_zero_shot/train-* - split: validation path: gem_zero_shot/validation-* - config_name: gender_inclusive_sentences_german_zero_shot data_files: - split: default path: gender_inclusive_sentences_german_zero_shot/default-* - split: train path: gender_inclusive_sentences_german_zero_shot/train-* - split: validation path: gender_inclusive_sentences_german_zero_shot/validation-* - config_name: general_knowledge_zero_shot data_files: - split: default path: general_knowledge_zero_shot/default-* - split: train path: general_knowledge_zero_shot/train-* - split: validation path: general_knowledge_zero_shot/validation-* - config_name: geometric_shapes_zero_shot data_files: - split: default path: geometric_shapes_zero_shot/default-* - split: train path: geometric_shapes_zero_shot/train-* - split: validation path: geometric_shapes_zero_shot/validation-* - config_name: goal_step_wikihow_zero_shot data_files: - split: default path: goal_step_wikihow_zero_shot/default-* - split: train path: goal_step_wikihow_zero_shot/train-* - split: validation path: goal_step_wikihow_zero_shot/validation-* - config_name: gre_reading_comprehension_zero_shot data_files: - split: default path: gre_reading_comprehension_zero_shot/default-* - split: train path: gre_reading_comprehension_zero_shot/train-* - split: validation path: gre_reading_comprehension_zero_shot/validation-* - config_name: hhh_alignment_zero_shot data_files: - split: default path: hhh_alignment_zero_shot/default-* - split: train path: hhh_alignment_zero_shot/train-* - split: validation path: hhh_alignment_zero_shot/validation-* - config_name: hindi_question_answering_zero_shot data_files: - split: default path: hindi_question_answering_zero_shot/default-* - split: train path: hindi_question_answering_zero_shot/train-* - split: validation path: hindi_question_answering_zero_shot/validation-* - config_name: hindu_knowledge_zero_shot data_files: - split: default path: hindu_knowledge_zero_shot/default-* - split: train path: hindu_knowledge_zero_shot/train-* - split: validation path: hindu_knowledge_zero_shot/validation-* - config_name: hinglish_toxicity_zero_shot data_files: - split: default path: hinglish_toxicity_zero_shot/default-* - split: train path: hinglish_toxicity_zero_shot/train-* - split: validation path: hinglish_toxicity_zero_shot/validation-* - config_name: human_organs_senses_zero_shot data_files: - split: default path: human_organs_senses_zero_shot/default-* - split: train path: human_organs_senses_zero_shot/train-* - split: validation path: human_organs_senses_zero_shot/validation-* - config_name: hyperbaton_zero_shot data_files: - split: default path: hyperbaton_zero_shot/default-* - split: train path: hyperbaton_zero_shot/train-* - split: validation path: hyperbaton_zero_shot/validation-* - config_name: identify_math_theorems_zero_shot data_files: - split: default path: identify_math_theorems_zero_shot/default-* - split: train path: identify_math_theorems_zero_shot/train-* - split: validation path: identify_math_theorems_zero_shot/validation-* - config_name: identify_odd_metaphor_zero_shot data_files: - split: default path: identify_odd_metaphor_zero_shot/default-* - split: train path: identify_odd_metaphor_zero_shot/train-* - split: validation path: identify_odd_metaphor_zero_shot/validation-* - config_name: implicatures_zero_shot data_files: - split: default path: implicatures_zero_shot/default-* - split: train path: implicatures_zero_shot/train-* - split: validation path: implicatures_zero_shot/validation-* - config_name: implicit_relations_zero_shot data_files: - split: default path: implicit_relations_zero_shot/default-* - split: train path: implicit_relations_zero_shot/train-* - split: validation path: implicit_relations_zero_shot/validation-* - config_name: intent_recognition_zero_shot data_files: - split: default path: intent_recognition_zero_shot/default-* - split: train path: intent_recognition_zero_shot/train-* - split: validation path: intent_recognition_zero_shot/validation-* - config_name: international_phonetic_alphabet_nli_zero_shot data_files: - split: default path: international_phonetic_alphabet_nli_zero_shot/default-* - split: train path: international_phonetic_alphabet_nli_zero_shot/train-* - split: validation path: international_phonetic_alphabet_nli_zero_shot/validation-* - config_name: international_phonetic_alphabet_transliterate_zero_shot data_files: - split: default path: international_phonetic_alphabet_transliterate_zero_shot/default-* - split: train path: international_phonetic_alphabet_transliterate_zero_shot/train-* - split: validation path: international_phonetic_alphabet_transliterate_zero_shot/validation-* - config_name: intersect_geometry_zero_shot data_files: - split: default path: intersect_geometry_zero_shot/default-* - split: train path: intersect_geometry_zero_shot/train-* - split: validation path: intersect_geometry_zero_shot/validation-* - config_name: irony_identification_zero_shot data_files: - split: default path: irony_identification_zero_shot/default-* - split: train path: irony_identification_zero_shot/train-* - split: validation path: irony_identification_zero_shot/validation-* - config_name: kanji_ascii_zero_shot data_files: - split: default path: kanji_ascii_zero_shot/default-* - split: train path: kanji_ascii_zero_shot/train-* - split: validation path: kanji_ascii_zero_shot/validation-* - config_name: kannada_zero_shot data_files: - split: default path: kannada_zero_shot/default-* - split: train path: kannada_zero_shot/train-* - split: validation path: kannada_zero_shot/validation-* - config_name: key_value_maps_zero_shot data_files: - split: default path: key_value_maps_zero_shot/default-* - split: train path: key_value_maps_zero_shot/train-* - split: validation path: key_value_maps_zero_shot/validation-* - config_name: known_unknowns_zero_shot data_files: - split: default path: known_unknowns_zero_shot/default-* - split: train path: known_unknowns_zero_shot/train-* - split: validation path: known_unknowns_zero_shot/validation-* - config_name: language_games_zero_shot data_files: - split: default path: language_games_zero_shot/default-* - split: train path: language_games_zero_shot/train-* - split: validation path: language_games_zero_shot/validation-* - config_name: language_identification_zero_shot data_files: - split: default path: language_identification_zero_shot/default-* - split: train path: language_identification_zero_shot/train-* - split: validation path: language_identification_zero_shot/validation-* - config_name: linguistic_mappings_zero_shot data_files: - split: default path: linguistic_mappings_zero_shot/default-* - split: train path: linguistic_mappings_zero_shot/train-* - split: validation path: linguistic_mappings_zero_shot/validation-* - config_name: linguistics_puzzles_zero_shot data_files: - split: default path: linguistics_puzzles_zero_shot/default-* - split: train path: linguistics_puzzles_zero_shot/train-* - split: validation path: linguistics_puzzles_zero_shot/validation-* - config_name: list_functions_zero_shot data_files: - split: default path: list_functions_zero_shot/default-* - split: train path: list_functions_zero_shot/train-* - split: validation path: list_functions_zero_shot/validation-* - config_name: logic_grid_puzzle_zero_shot data_files: - split: default path: logic_grid_puzzle_zero_shot/default-* - split: train path: logic_grid_puzzle_zero_shot/train-* - split: validation path: logic_grid_puzzle_zero_shot/validation-* - config_name: logical_args_zero_shot data_files: - split: default path: logical_args_zero_shot/default-* - split: train path: logical_args_zero_shot/train-* - split: validation path: logical_args_zero_shot/validation-* - config_name: logical_deduction_zero_shot data_files: - split: default path: logical_deduction_zero_shot/default-* - split: train path: logical_deduction_zero_shot/train-* - split: validation path: logical_deduction_zero_shot/validation-* - config_name: logical_fallacy_detection_zero_shot data_files: - split: default path: logical_fallacy_detection_zero_shot/default-* - split: train path: logical_fallacy_detection_zero_shot/train-* - split: validation path: logical_fallacy_detection_zero_shot/validation-* - config_name: logical_sequence_zero_shot data_files: - split: default path: logical_sequence_zero_shot/default-* - split: train path: logical_sequence_zero_shot/train-* - split: validation path: logical_sequence_zero_shot/validation-* - config_name: mathematical_induction_zero_shot data_files: - split: default path: mathematical_induction_zero_shot/default-* - split: train path: mathematical_induction_zero_shot/train-* - split: validation path: mathematical_induction_zero_shot/validation-* - config_name: matrixshapes_zero_shot data_files: - split: default path: matrixshapes_zero_shot/default-* - split: train path: matrixshapes_zero_shot/train-* - split: validation path: matrixshapes_zero_shot/validation-* - config_name: metaphor_boolean_zero_shot data_files: - split: default path: metaphor_boolean_zero_shot/default-* - split: train path: metaphor_boolean_zero_shot/train-* - split: validation path: metaphor_boolean_zero_shot/validation-* - config_name: metaphor_understanding_zero_shot data_files: - split: default path: metaphor_understanding_zero_shot/default-* - split: train path: metaphor_understanding_zero_shot/train-* - split: validation path: metaphor_understanding_zero_shot/validation-* - config_name: minute_mysteries_qa_zero_shot data_files: - split: default path: minute_mysteries_qa_zero_shot/default-* - split: train path: minute_mysteries_qa_zero_shot/train-* - split: validation path: minute_mysteries_qa_zero_shot/validation-* - config_name: misconceptions_russian_zero_shot data_files: - split: default path: misconceptions_russian_zero_shot/default-* - split: train path: misconceptions_russian_zero_shot/train-* - split: validation path: misconceptions_russian_zero_shot/validation-* - config_name: misconceptions_zero_shot data_files: - split: default path: misconceptions_zero_shot/default-* - split: train path: misconceptions_zero_shot/train-* - split: validation path: misconceptions_zero_shot/validation-* - config_name: mnist_ascii_zero_shot data_files: - split: default path: mnist_ascii_zero_shot/default-* - split: train path: mnist_ascii_zero_shot/train-* - split: validation path: mnist_ascii_zero_shot/validation-* - config_name: modified_arithmetic_zero_shot data_files: - split: default path: modified_arithmetic_zero_shot/default-* - split: train path: modified_arithmetic_zero_shot/train-* - split: validation path: modified_arithmetic_zero_shot/validation-* - config_name: moral_permissibility_zero_shot data_files: - split: default path: moral_permissibility_zero_shot/default-* - split: train path: moral_permissibility_zero_shot/train-* - split: validation path: moral_permissibility_zero_shot/validation-* - config_name: movie_dialog_same_or_different_zero_shot data_files: - split: default path: movie_dialog_same_or_different_zero_shot/default-* - split: train path: movie_dialog_same_or_different_zero_shot/train-* - split: validation path: movie_dialog_same_or_different_zero_shot/validation-* - config_name: movie_recommendation_zero_shot data_files: - split: default path: movie_recommendation_zero_shot/default-* - split: train path: movie_recommendation_zero_shot/train-* - split: validation path: movie_recommendation_zero_shot/validation-* - config_name: mult_data_wrangling_zero_shot data_files: - split: default path: mult_data_wrangling_zero_shot/default-* - split: train path: mult_data_wrangling_zero_shot/train-* - split: validation path: mult_data_wrangling_zero_shot/validation-* - config_name: multiemo_zero_shot data_files: - split: default path: multiemo_zero_shot/default-* - split: train path: multiemo_zero_shot/train-* - split: validation path: multiemo_zero_shot/validation-* - config_name: natural_instructions_zero_shot data_files: - split: default path: natural_instructions_zero_shot/default-* - split: train path: natural_instructions_zero_shot/train-* - split: validation path: natural_instructions_zero_shot/validation-* - config_name: navigate_zero_shot data_files: - split: default path: navigate_zero_shot/default-* - split: train path: navigate_zero_shot/train-* - split: validation path: navigate_zero_shot/validation-* - config_name: nonsense_words_grammar_zero_shot data_files: - split: default path: nonsense_words_grammar_zero_shot/default-* - split: train path: nonsense_words_grammar_zero_shot/train-* - split: validation path: nonsense_words_grammar_zero_shot/validation-* - config_name: novel_concepts_zero_shot data_files: - split: default path: novel_concepts_zero_shot/default-* - split: train path: novel_concepts_zero_shot/train-* - split: validation path: novel_concepts_zero_shot/validation-* - config_name: object_counting_zero_shot data_files: - split: default path: object_counting_zero_shot/default-* - split: train path: object_counting_zero_shot/train-* - split: validation path: object_counting_zero_shot/validation-* - config_name: odd_one_out_zero_shot data_files: - split: default path: odd_one_out_zero_shot/default-* - split: train path: odd_one_out_zero_shot/train-* - split: validation path: odd_one_out_zero_shot/validation-* - config_name: operators_zero_shot data_files: - split: default path: operators_zero_shot/default-* - split: train path: operators_zero_shot/train-* - split: validation path: operators_zero_shot/validation-* - config_name: paragraph_segmentation_zero_shot data_files: - split: default path: paragraph_segmentation_zero_shot/default-* - split: train path: paragraph_segmentation_zero_shot/train-* - split: validation path: paragraph_segmentation_zero_shot/validation-* - config_name: parsinlu_qa_zero_shot data_files: - split: default path: parsinlu_qa_zero_shot/default-* - split: train path: parsinlu_qa_zero_shot/train-* - split: validation path: parsinlu_qa_zero_shot/validation-* - config_name: parsinlu_reading_comprehension_zero_shot data_files: - split: default path: parsinlu_reading_comprehension_zero_shot/default-* - split: train path: parsinlu_reading_comprehension_zero_shot/train-* - split: validation path: parsinlu_reading_comprehension_zero_shot/validation-* - config_name: penguins_in_a_table_zero_shot data_files: - split: default path: penguins_in_a_table_zero_shot/default-* - split: train path: penguins_in_a_table_zero_shot/train-* - split: validation path: penguins_in_a_table_zero_shot/validation-* - config_name: periodic_elements_zero_shot data_files: - split: default path: periodic_elements_zero_shot/default-* - split: train path: periodic_elements_zero_shot/train-* - split: validation path: periodic_elements_zero_shot/validation-* - config_name: persian_idioms_zero_shot data_files: - split: default path: persian_idioms_zero_shot/default-* - split: train path: persian_idioms_zero_shot/train-* - split: validation path: persian_idioms_zero_shot/validation-* - config_name: phrase_relatedness_zero_shot data_files: - split: default path: phrase_relatedness_zero_shot/default-* - split: train path: phrase_relatedness_zero_shot/train-* - split: validation path: phrase_relatedness_zero_shot/validation-* - config_name: physical_intuition_zero_shot data_files: - split: default path: physical_intuition_zero_shot/default-* - split: train path: physical_intuition_zero_shot/train-* - split: validation path: physical_intuition_zero_shot/validation-* - config_name: physics_questions_zero_shot data_files: - split: default path: physics_questions_zero_shot/default-* - split: train path: physics_questions_zero_shot/train-* - split: validation path: physics_questions_zero_shot/validation-* - config_name: physics_zero_shot data_files: - split: default path: physics_zero_shot/default-* - split: train path: physics_zero_shot/train-* - split: validation path: physics_zero_shot/validation-* - config_name: play_dialog_same_or_different_zero_shot data_files: - split: default path: play_dialog_same_or_different_zero_shot/default-* - split: train path: play_dialog_same_or_different_zero_shot/train-* - split: validation path: play_dialog_same_or_different_zero_shot/validation-* - config_name: polish_sequence_labeling_zero_shot data_files: - split: default path: polish_sequence_labeling_zero_shot/default-* - split: train path: polish_sequence_labeling_zero_shot/train-* - split: validation path: polish_sequence_labeling_zero_shot/validation-* - config_name: presuppositions_as_nli_zero_shot data_files: - split: default path: presuppositions_as_nli_zero_shot/default-* - split: train path: presuppositions_as_nli_zero_shot/train-* - split: validation path: presuppositions_as_nli_zero_shot/validation-* - config_name: qa_wikidata_zero_shot data_files: - split: default path: qa_wikidata_zero_shot/default-* - split: train path: qa_wikidata_zero_shot/train-* - split: validation path: qa_wikidata_zero_shot/validation-* - config_name: question_selection_zero_shot data_files: - split: default path: question_selection_zero_shot/default-* - split: train path: question_selection_zero_shot/train-* - split: validation path: question_selection_zero_shot/validation-* - config_name: real_or_fake_text_zero_shot data_files: - split: default path: real_or_fake_text_zero_shot/default-* - split: train path: real_or_fake_text_zero_shot/train-* - split: validation path: real_or_fake_text_zero_shot/validation-* - config_name: reasoning_about_colored_objects_zero_shot data_files: - split: default path: reasoning_about_colored_objects_zero_shot/default-* - split: train path: reasoning_about_colored_objects_zero_shot/train-* - split: validation path: reasoning_about_colored_objects_zero_shot/validation-* - config_name: repeat_copy_logic_zero_shot data_files: - split: default path: repeat_copy_logic_zero_shot/default-* - split: train path: repeat_copy_logic_zero_shot/train-* - split: validation path: repeat_copy_logic_zero_shot/validation-* - config_name: rephrase_zero_shot data_files: - split: default path: rephrase_zero_shot/default-* - split: train path: rephrase_zero_shot/train-* - split: validation path: rephrase_zero_shot/validation-* - config_name: riddle_sense_zero_shot data_files: - split: default path: riddle_sense_zero_shot/default-* - split: train path: riddle_sense_zero_shot/train-* - split: validation path: riddle_sense_zero_shot/validation-* - config_name: ruin_names_zero_shot data_files: - split: default path: ruin_names_zero_shot/default-* - split: train path: ruin_names_zero_shot/train-* - split: validation path: ruin_names_zero_shot/validation-* - config_name: salient_translation_error_detection_zero_shot data_files: - split: default path: salient_translation_error_detection_zero_shot/default-* - split: train path: salient_translation_error_detection_zero_shot/train-* - split: validation path: salient_translation_error_detection_zero_shot/validation-* - config_name: scientific_press_release_zero_shot data_files: - split: default path: scientific_press_release_zero_shot/default-* - split: train path: scientific_press_release_zero_shot/train-* - split: validation path: scientific_press_release_zero_shot/validation-* - config_name: semantic_parsing_in_context_sparc_zero_shot data_files: - split: default path: semantic_parsing_in_context_sparc_zero_shot/default-* - split: train path: semantic_parsing_in_context_sparc_zero_shot/train-* - split: validation path: semantic_parsing_in_context_sparc_zero_shot/validation-* - config_name: semantic_parsing_spider_zero_shot data_files: - split: default path: semantic_parsing_spider_zero_shot/default-* - split: train path: semantic_parsing_spider_zero_shot/train-* - split: validation path: semantic_parsing_spider_zero_shot/validation-* - config_name: sentence_ambiguity_zero_shot data_files: - split: default path: sentence_ambiguity_zero_shot/default-* - split: train path: sentence_ambiguity_zero_shot/train-* - split: validation path: sentence_ambiguity_zero_shot/validation-* - config_name: similarities_abstraction_zero_shot data_files: - split: default path: similarities_abstraction_zero_shot/default-* - split: train path: similarities_abstraction_zero_shot/train-* - split: validation path: similarities_abstraction_zero_shot/validation-* - config_name: simp_turing_concept_zero_shot data_files: - split: default path: simp_turing_concept_zero_shot/default-* - split: train path: simp_turing_concept_zero_shot/train-* - split: validation path: simp_turing_concept_zero_shot/validation-* - config_name: simple_arithmetic_json_multiple_choice_zero_shot data_files: - split: default path: simple_arithmetic_json_multiple_choice_zero_shot/default-* - split: train path: simple_arithmetic_json_multiple_choice_zero_shot/train-* - split: validation path: simple_arithmetic_json_multiple_choice_zero_shot/validation-* - config_name: simple_arithmetic_json_subtasks_zero_shot data_files: - split: default path: simple_arithmetic_json_subtasks_zero_shot/default-* - split: train path: simple_arithmetic_json_subtasks_zero_shot/train-* - split: validation path: simple_arithmetic_json_subtasks_zero_shot/validation-* - config_name: simple_arithmetic_json_zero_shot data_files: - split: default path: simple_arithmetic_json_zero_shot/default-* - split: train path: simple_arithmetic_json_zero_shot/train-* - split: validation path: simple_arithmetic_json_zero_shot/validation-* - config_name: simple_arithmetic_multiple_targets_json_zero_shot data_files: - split: default path: simple_arithmetic_multiple_targets_json_zero_shot/default-* - split: train path: simple_arithmetic_multiple_targets_json_zero_shot/train-* - split: validation path: simple_arithmetic_multiple_targets_json_zero_shot/validation-* - config_name: simple_ethical_questions_zero_shot data_files: - split: default path: simple_ethical_questions_zero_shot/default-* - split: train path: simple_ethical_questions_zero_shot/train-* - split: validation path: simple_ethical_questions_zero_shot/validation-* - config_name: simple_text_editing_zero_shot data_files: - split: default path: simple_text_editing_zero_shot/default-* - split: train path: simple_text_editing_zero_shot/train-* - split: validation path: simple_text_editing_zero_shot/validation-* - config_name: snarks_zero_shot data_files: - split: default path: snarks_zero_shot/default-* - split: train path: snarks_zero_shot/train-* - split: validation path: snarks_zero_shot/validation-* - config_name: social_iqa_zero_shot data_files: - split: default path: social_iqa_zero_shot/default-* - split: train path: social_iqa_zero_shot/train-* - split: validation path: social_iqa_zero_shot/validation-* - config_name: social_support_zero_shot data_files: - split: default path: social_support_zero_shot/default-* - split: train path: social_support_zero_shot/train-* - split: validation path: social_support_zero_shot/validation-* - config_name: sports_understanding_zero_shot data_files: - split: default path: sports_understanding_zero_shot/default-* - split: train path: sports_understanding_zero_shot/train-* - split: validation path: sports_understanding_zero_shot/validation-* - config_name: strange_stories_zero_shot data_files: - split: default path: strange_stories_zero_shot/default-* - split: train path: strange_stories_zero_shot/train-* - split: validation path: strange_stories_zero_shot/validation-* - config_name: strategyqa_zero_shot data_files: - split: default path: strategyqa_zero_shot/default-* - split: train path: strategyqa_zero_shot/train-* - split: validation path: strategyqa_zero_shot/validation-* - config_name: sufficient_information_zero_shot data_files: - split: default path: sufficient_information_zero_shot/default-* - split: train path: sufficient_information_zero_shot/train-* - split: validation path: sufficient_information_zero_shot/validation-* - config_name: suicide_risk_zero_shot data_files: - split: default path: suicide_risk_zero_shot/default-* - split: train path: suicide_risk_zero_shot/train-* - split: validation path: suicide_risk_zero_shot/validation-* - config_name: swahili_english_proverbs_zero_shot data_files: - split: default path: swahili_english_proverbs_zero_shot/default-* - split: train path: swahili_english_proverbs_zero_shot/train-* - split: validation path: swahili_english_proverbs_zero_shot/validation-* - config_name: swedish_to_german_proverbs_zero_shot data_files: - split: default path: swedish_to_german_proverbs_zero_shot/default-* - split: train path: swedish_to_german_proverbs_zero_shot/train-* - split: validation path: swedish_to_german_proverbs_zero_shot/validation-* - config_name: symbol_interpretation_zero_shot data_files: - split: default path: symbol_interpretation_zero_shot/default-* - split: train path: symbol_interpretation_zero_shot/train-* - split: validation path: symbol_interpretation_zero_shot/validation-* - config_name: temporal_sequences_zero_shot data_files: - split: default path: temporal_sequences_zero_shot/default-* - split: train path: temporal_sequences_zero_shot/train-* - split: validation path: temporal_sequences_zero_shot/validation-* - config_name: tense_zero_shot data_files: - split: default path: tense_zero_shot/default-* - split: train path: tense_zero_shot/train-* - split: validation path: tense_zero_shot/validation-* - config_name: timedial_zero_shot data_files: - split: default path: timedial_zero_shot/default-* - split: train path: timedial_zero_shot/train-* - split: validation path: timedial_zero_shot/validation-* - config_name: topical_chat_zero_shot data_files: - split: default path: topical_chat_zero_shot/default-* - split: train path: topical_chat_zero_shot/train-* - split: validation path: topical_chat_zero_shot/validation-* - config_name: tracking_shuffled_objects_zero_shot data_files: - split: default path: tracking_shuffled_objects_zero_shot/default-* - split: train path: tracking_shuffled_objects_zero_shot/train-* - split: validation path: tracking_shuffled_objects_zero_shot/validation-* - config_name: understanding_fables_zero_shot data_files: - split: default path: understanding_fables_zero_shot/default-* - split: train path: understanding_fables_zero_shot/train-* - split: validation path: understanding_fables_zero_shot/validation-* - config_name: undo_permutation_zero_shot data_files: - split: default path: undo_permutation_zero_shot/default-* - split: train path: undo_permutation_zero_shot/train-* - split: validation path: undo_permutation_zero_shot/validation-* - config_name: unit_conversion_zero_shot data_files: - split: default path: unit_conversion_zero_shot/default-* - split: train path: unit_conversion_zero_shot/train-* - split: validation path: unit_conversion_zero_shot/validation-* - config_name: unit_interpretation_zero_shot data_files: - split: default path: unit_interpretation_zero_shot/default-* - split: train path: unit_interpretation_zero_shot/train-* - split: validation path: unit_interpretation_zero_shot/validation-* - config_name: unnatural_in_context_learning_zero_shot data_files: - split: default path: unnatural_in_context_learning_zero_shot/default-* - split: train path: unnatural_in_context_learning_zero_shot/train-* - split: validation path: unnatural_in_context_learning_zero_shot/validation-* - config_name: vitaminc_fact_verification_zero_shot data_files: - split: default path: vitaminc_fact_verification_zero_shot/default-* - split: train path: vitaminc_fact_verification_zero_shot/train-* - split: validation path: vitaminc_fact_verification_zero_shot/validation-* - config_name: what_is_the_tao_zero_shot data_files: - split: default path: what_is_the_tao_zero_shot/default-* - split: train path: what_is_the_tao_zero_shot/train-* - split: validation path: what_is_the_tao_zero_shot/validation-* - config_name: which_wiki_edit_zero_shot data_files: - split: default path: which_wiki_edit_zero_shot/default-* - split: train path: which_wiki_edit_zero_shot/train-* - split: validation path: which_wiki_edit_zero_shot/validation-* - config_name: winowhy_zero_shot data_files: - split: default path: winowhy_zero_shot/default-* - split: train path: winowhy_zero_shot/train-* - split: validation path: winowhy_zero_shot/validation-* - config_name: word_sorting_zero_shot data_files: - split: default path: word_sorting_zero_shot/default-* - split: train path: word_sorting_zero_shot/train-* - split: validation path: word_sorting_zero_shot/validation-* - config_name: word_unscrambling_zero_shot data_files: - split: default path: word_unscrambling_zero_shot/default-* - split: train path: word_unscrambling_zero_shot/train-* - split: validation path: word_unscrambling_zero_shot/validation-* --- # Dataset Card for "bigbench" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

open-llm-leaderboard/contents

open-llm-leaderboard

"2025-03-20T12:17:27Z"

18,423

15

[ "size_categories:1K<n<10K", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]

null

"2024-06-26T08:33:17Z"

--- dataset_info: features: - name: eval_name dtype: string - name: Precision dtype: string - name: Type dtype: string - name: T dtype: string - name: Weight type dtype: string - name: Architecture dtype: string - name: Model dtype: string - name: fullname dtype: string - name: Model sha dtype: string - name: Average ⬆️ dtype: float64 - name: Hub License dtype: string - name: Hub ❤️ dtype: int64 - name: '#Params (B)' dtype: float64 - name: Available on the hub dtype: bool - name: MoE dtype: bool - name: Flagged dtype: bool - name: Chat Template dtype: bool - name: CO₂ cost (kg) dtype: float64 - name: IFEval Raw dtype: float64 - name: IFEval dtype: float64 - name: BBH Raw dtype: float64 - name: BBH dtype: float64 - name: MATH Lvl 5 Raw dtype: float64 - name: MATH Lvl 5 dtype: float64 - name: GPQA Raw dtype: float64 - name: GPQA dtype: float64 - name: MUSR Raw dtype: float64 - name: MUSR dtype: float64 - name: MMLU-PRO Raw dtype: float64 - name: MMLU-PRO dtype: float64 - name: Merged dtype: bool - name: Official Providers dtype: bool - name: Upload To Hub Date dtype: string - name: Submission Date dtype: string - name: Generation dtype: int64 - name: Base Model dtype: string splits: - name: train num_bytes: 4004719 num_examples: 4576 download_size: 1109997 dataset_size: 4004719 configs: - config_name: default data_files: - split: train path: data/train-* ---

textmachinelab/quail

textmachinelab

"2024-01-04T16:18:32Z"

18,305

7

[ "task_categories:multiple-choice", "task_ids:multiple-choice-qa", "annotations_creators:crowdsourced", "language_creators:found", "multilinguality:monolingual", "source_datasets:original", "language:en", "license:cc-by-nc-sa-4.0", "size_categories:10K<n<100K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]

[ "multiple-choice" ]

"2022-03-02T23:29:22Z"

--- annotations_creators: - crowdsourced language_creators: - found language: - en license: - cc-by-nc-sa-4.0 multilinguality: - monolingual size_categories: - 10K<n<100K source_datasets: - original task_categories: - multiple-choice task_ids: - multiple-choice-qa paperswithcode_id: quail pretty_name: Question Answering for Artificial Intelligence (QuAIL) dataset_info: config_name: quail features: - name: id dtype: string - name: context_id dtype: string - name: question_id dtype: string - name: domain dtype: string - name: metadata struct: - name: author dtype: string - name: title dtype: string - name: url dtype: string - name: context dtype: string - name: question dtype: string - name: question_type dtype: string - name: answers sequence: string - name: correct_answer_id dtype: int32 splits: - name: train num_bytes: 23432601 num_examples: 10246 - name: validation num_bytes: 4989531 num_examples: 2164 - name: challenge num_bytes: 1199792 num_examples: 556 download_size: 2286403 dataset_size: 29621924 configs: - config_name: quail data_files: - split: train path: quail/train-* - split: validation path: quail/validation-* - split: challenge path: quail/challenge-* default: true --- # Dataset Card for "quail" ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Homepage:** [https://text-machine-lab.github.io/blog/2020/quail/](https://text-machine-lab.github.io/blog/2020/quail/) - **Repository:** https://github.com/text-machine-lab/quail - **Paper:** [Getting Closer to AI Complete Question Answering: A Set of Prerequisite Real Tasks](https://doi.org/10.1609/aaai.v34i05.6398 ) - **Point of Contact:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - **Size of downloaded dataset files:** 6.41 MB - **Size of the generated dataset:** 29.62 MB - **Total amount of disk used:** 36.03 MB ### Dataset Summary QuAIL is a reading comprehension dataset. QuAIL contains 15K multi-choice questions in texts 300-350 tokens long 4 domains (news, user stories, fiction, blogs).QuAIL is balanced and annotated for question types. ### Supported Tasks and Leaderboards [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Languages [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Dataset Structure ### Data Instances #### quail - **Size of downloaded dataset files:** 6.41 MB - **Size of the generated dataset:** 29.62 MB - **Total amount of disk used:** 36.03 MB An example of 'train' looks as follows. ``` This example was too long and was cropped: { "answers": ["the cousin is not friendly", "the cousin could have been pretier", "not enough information", "the cousin was too nice"], "context": "\"That fall came and I went back to Michigan and the school year went by and summer came and I never really thought about it. I'm...", "context_id": "f001", "correct_answer_id": 0, "domain": "fiction", "id": "f001_19", "metadata": { "author": "Joseph Devon", "title": "Black Eyed Susan", "url": "http://manybooks.net/pages/devonjother08black_eyed_susan/0.html" }, "question": "After the events in the text what does the author think about the cousin?", "question_id": "19", "question_type": "Subsequent_state" } ``` ### Data Fields The data fields are the same among all splits. #### quail - `id`: a `string` feature. - `context_id`: a `string` feature. - `question_id`: a `string` feature. - `domain`: a `string` feature. - `author`: a `string` feature. - `title`: a `string` feature. - `url`: a `string` feature. - `context`: a `string` feature. - `question`: a `string` feature. - `question_type`: a `string` feature. - `answers`: a `list` of `string` features. - `correct_answer_id`: a `int32` feature. ### Data Splits |name |train|challenge|validation| |-----|----:|--------:|---------:| |quail|10246| 556| 2164| ## Dataset Creation ### Curation Rationale [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Source Data #### Initial Data Collection and Normalization [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the source language producers? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Annotations #### Annotation process [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the annotators? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Personal and Sensitive Information [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Discussion of Biases [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Other Known Limitations [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Additional Information ### Dataset Curators [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Licensing Information [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Citation Information ``` @inproceedings{DBLP:conf/aaai/RogersKDR20, author = {Anna Rogers and Olga Kovaleva and Matthew Downey and Anna Rumshisky}, title = {Getting Closer to {AI} Complete Question Answering: {A} Set of Prerequisite Real Tasks}, booktitle = {The Thirty-Fourth {AAAI} Conference on Artificial Intelligence, {AAAI} 2020, The Thirty-Second Innovative Applications of Artificial Intelligence Conference, {IAAI} 2020, The Tenth {AAAI} Symposium on Educational Advances in Artificial Intelligence, {EAAI} 2020, New York, NY, USA, February 7-12, 2020}, pages = {8722--8731}, publisher = {{AAAI} Press}, year = {2020}, url = {https://aaai.org/ojs/index.php/AAAI/article/view/6398}, timestamp = {Thu, 04 Jun 2020 13:18:48 +0200}, biburl = {https://dblp.org/rec/conf/aaai/RogersKDR20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} } ``` ### Contributions Thanks to [@sai-prasanna](https://github.com/sai-prasanna), [@ngdodd](https://github.com/ngdodd) for adding this dataset.

avery00/MomentSeeker

avery00

"2025-03-26T03:18:37Z"

18,222

1

[ "task_categories:question-answering", "language:en", "license:cc-by-nc-sa-4.0", "size_categories:1K<n<10K", "format:imagefolder", "modality:image", "modality:video", "library:datasets", "library:mlcroissant", "arxiv:2502.12558", "region:us" ]

[ "question-answering" ]

"2025-03-07T08:35:58Z"

--- license: cc-by-nc-sa-4.0 extra_gated_prompt: >- You acknowledge and understand that: This dataset is provided solely for academic research purposes. It is not intended for commercial use or any other non-research activities. All copyrights, trademarks, and other intellectual property rights related to the videos in the dataset remain the exclusive property of their respective owners. You assume full responsibility for any additional use or dissemination of this dataset and for any consequences that may arise from such actions. You are also aware that the copyright holders of the original videos retain the right to request the removal of their videos from the dataset. Furthermore, it is your responsibility to respect these conditions and to use the dataset ethically and in compliance with all applicable laws and regulations. Any violation of these terms may result in the immediate termination of your access to the dataset. extra_gated_fields: Institution: text Name: text Country: country I want to use this dataset for: type: select options: - Research I agree to use this dataset solely for research purposes: checkbox I will not use this dataset in any way that infringes upon the rights of the copyright holders of the original videos, and strictly prohibit its use for any commercial purposes: checkbox task_categories: - question-answering language: - en --- <h1 align="center">MomentSeeker: A Comprehensive Benchmark and A Strong Baseline For Moment Retrieval Within Long Videos</h1> <p align="center"> <a href="https://arxiv.org/abs/2502.12558"> <img alt="Build" src="http://img.shields.io/badge/cs.CV-arXiv%3A2406.04264-B31B1B.svg"> </a> <a href="https://github.com/yhy-2000/MomentSeeker"> <img alt="Build" src="https://img.shields.io/badge/Github-MomentSeeker: A Comprehensive Benchmark and A Strong Baseline For Moment Retrieval Within Long Videos-blue"> </a> </p> This repo contains the annotation data for the paper "[MomentSeeker: A Comprehensive Benchmark and A Strong Baseline For Moment Retrieval Within Long Videos](https://arxiv.org/abs/2502.12558)". ## 🔔 News: - 🥳 2025/03/07: We have released the MomentSeeker [Benchmark](https://huggingface.co/datasets/avery00/MomentSeeker) and [Paper](https://arxiv.org/abs/2502.12558)! 🔥 ## License Our dataset is under the CC-BY-NC-SA-4.0 license. ⚠️ If you need to access and use our dataset, you must understand and agree: **This dataset is for research purposes only and cannot be used for any commercial or other purposes. The user assumes all effects arising from any other use and dissemination.** We do not own the copyright of any raw video files. Currently, we provide video access to researchers under the condition of acknowledging the above license. For the video data used, we respect and acknowledge any copyrights of the video authors. Therefore, for the movies, TV series, documentaries, and cartoons used in the dataset, we have reduced the resolution, clipped the length, adjusted dimensions, etc. of the original videos to minimize the impact on the rights of the original works. If the original authors of the related works still believe that the videos should be removed, please contact [email protected] or directly raise an issue. ## Introduction We present MomentSeeker, a comprehensive benchmark to evaluate retrieval models' performance in handling general long-video moment retrieval (LVMR) tasks. MomentSeeker offers three key advantages. First, it incorporates long videos of over 500 seconds on average, making it the first benchmark specialized for long-video moment retrieval. Second, it covers a wide range of task categories (including Moment Search, Caption Alignment, Image-conditioned Moment Search, and Video-conditioned Moment Search) and diverse application scenarios (e.g., sports, movies, cartoons, and ego), making it a comprehensive tool for assessing retrieval models' general LVMR performance. Additionally, the evaluation tasks are carefully curated through human annotation, ensuring the reliability of assessment. We further fine-tune an MLLM-based LVMR retriever on synthetic data, which demonstrates strong performance on our benchmark. The checkpoint will release soon. ![Illustrative overview of our MomentSeeker dataset.](https://cdn-uploads.huggingface.co/production/uploads/66d916a7b86f0d569aa19b60/ff-9bFKlN466wElhiA4Wi.png) ## 🏆 Mini Leaderboard | Rank | Method | Backbone | # Params | CA | MS | IMS | VMS | Overall | |------|------------------------------------------|-----------------|---------|--------|--------|--------|--------|--------| | 1 | **V-Embedder** | InternVideo2-Chat| 8B | <u>42.2</u> | **20.4** | **15.0** | **15.8** | **23.3** | | 2 | CoVR | BLIP-Large | 588M | 25.8 | 17.4 | <u>12.3</u> | <u>12.3</u> | <u>17.1</u> | | 3 | InternVideo2 | ViT | 1B | **44.6** | <u>18.2</u> | 4.8 | 0.0 | 16.9 | | 4 | MM-Ret | CLIP-Base | 149M | 23.2 | 15.4 | 10.5 | 10.5 | 14.9 | | 5 | LanguageBind | CLIP-Large | 428M | 39.6 | 16.4 | 3.2 | 0.0 | 14.8 | | 6 | E5V | LLaVA-1.6 | 8.4B | 25.8 | 16.8 | 6.2 | 5.2 | 13.5 | | 7 | UniIR | CLIP-Large | 428M | 25.0 | 15.2 | 6.4 | 0.0 | 10.9 | | 8 | MLLM2VEC | LLaVA-1.6 | 8.4B | 6.4 | 6.2 | 3.0 | 3.0 | 4.7 | | 9 | MagicLens | CLIP-Large | 428M | 9.0 | 2.4 | 3.2 | 2.8 | 4.4 | ## License Our dataset is under the CC-BY-NC-SA-4.0 license. ⚠️ If you need to access and use our dataset, you must understand and agree: **This dataset is for research purposes only and cannot be used for any commercial or other purposes. The user assumes all effects arising from any other use and dissemination.** We do not own the copyright of any raw video files. Currently, we provide video access to researchers under the condition of acknowledging the above license. For the video data used, we respect and acknowledge any copyrights of the video authors. Therefore, for the movies, TV series, documentaries, and cartoons used in the dataset, we have reduced the resolution, clipped the length, adjusted dimensions, etc. of the original videos to minimize the impact on the rights of the original works. If the original authors of the related works still believe that the videos should be removed, please contact [email protected] or directly raise an issue. ## Evaluation > Before you access our dataset, we kindly ask you to thoroughly read and understand the license outlined above. If you cannot agree to these terms, we request that you refrain from downloading our video data. The JSON file provides candidate videos for each question. The candidates can be ranked, and metrics such as Recall@1 and MAP@5 can be computed accordingly. ## Hosting and Maintenance The annotation files will be permanently retained. If some videos are requested to be removed, we will replace them with a set of video frames sparsely sampled from the video and adjusted in resolution. Since **all the questions in MomentSeeker are only related to visual content** and do not involve audio, this will not significantly affect the validity of MomentSeeker (most existing MLLMs also understand videos by frame extraction). If even retaining the frame set is not allowed, we will still keep the relevant annotation files, and replace them with the meta-information of the video, or actively seek more reliable and risk-free video sources. ## Citation If you find this repository useful, please consider giving a star 🌟 and citation ``` @misc{yuan2025momentseekercomprehensivebenchmarkstrong, title={MomentSeeker: A Comprehensive Benchmark and A Strong Baseline For Moment Retrieval Within Long Videos}, author={Huaying Yuan and Jian Ni and Yueze Wang and Junjie Zhou and Zhengyang Liang and Zheng Liu and Zhao Cao and Zhicheng Dou and Ji-Rong Wen}, year={2025}, eprint={2502.12558}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2502.12558}, } ```

jkot/parliament_hearings_processed

jkot

"2023-04-25T08:53:38Z"

18,135

1

[ "size_categories:100K<n<1M", "format:parquet", "modality:audio", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]

null

"2023-04-21T10:06:00Z"

--- dataset_info: features: - name: id dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: transcription dtype: string splits: - name: train num_bytes: 51234859011.0 num_examples: 191455 - name: test num_bytes: 762989296.0 num_examples: 2726 download_size: 51507735963 dataset_size: 51997848307.0 --- # Preprocessed parliament hearings ASR dataset to truecased form. ## Original dataset: https://lindat.mff.cuni.cz/repository/xmlui/handle/11234/1-3126 --- dataset_info: features: - name: id dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: transcription sequence: string splits: - name: train num_bytes: 53645064353.18 num_examples: 191455 - name: test num_bytes: 740331298.0 num_examples: 2726 download_size: 51507379112 dataset_size: 54385395651.18 ---

AppThreat/vdb

AppThreat

"2025-04-11T20:48:34Z"

18,132

1

[ "language:en", "license:mit", "region:us", "vulnerabilities", "vdb", "sca", "osv", "nvd", "ghsa", "vers", "purl" ]

null

"2025-02-17T23:35:01Z"

--- viewer: false license: mit language: - en tags: - vulnerabilities - vdb - sca - osv - nvd - ghsa - vers - purl --- This dataset comprises application and OS vulnerabilities aggregated from multiple sources, including OSV, GitHub, NVD, and Linux vendor feeds, in the form of SQLite data files (.vdb6). ## Vulnerability Data sources - Linux [vuln-list](https://github.com/appthreat/vuln-list) - OSV (1) - NVD - GitHub ## Linux distros - AlmaLinux - Debian - Alpine - Amazon Linux - Arch Linux - RHEL/CentOS - Rocky Linux - Ubuntu - OpenSUSE - Photon - Chainguard - Wolfi OS ## Database files The vulnerability database comprises two SQLite database files. - data.index.vdb6 - A smaller index database optimized for quick purl or cpe string searches and vers-based range comparisons. ![Index schema](./docs/vdb-index-schema.png) - data.vdb6 - Full CVE source database containing normalized data in CVE 5.1 specification formation and purl prefix. ![Data schema](./docs/vdb-schema.png) ## Folders - app - Application only vulnerabilities from 2018 - app-10y - Application only vulnerabilities from 2014 - app-os - Application and OS vulnerabilities from 2018 - app-os-10y - Application and OS vulnerabilities from 2014 Download data.vdb6 and data.index.vdb6 files from a single folder of your choice. ## Searching for CVEs Use the smaller index database for all search operations. ### Searching by purl Given a purl string (`purl_str`), perform the following steps to convert this into a suitable purl prefix (`purl_prefix`) string: In most cases, a purl prefix is a substring at index 0 after a split by "@". Eg: `purl_prefix = purl_str.split("@")[0]`. A more robust approach: - Parse and validate the string using a suitable [library](https://github.com/package-url/). Retain the parsed purl object (`purl_obj`) - Construct a purl prefix string with the following logic: - Set the value for `purl_prefix` to `"pkg:" + purl_obj["type"]` - If there is a namespace, append it to purl_prefix after the slash character. Eg: `purl_prefix = purl_prefix + "/" + purl_obj['namespace']` - Optional for Linux distros: If there is a qualifier string with the name `distro_name`, append it to the purl_prefix after the slash character. Eg: `purl_prefix = purl_prefix + "/" + purl_obj['qualifiers']['distro_name']` - Append the name after the slash character. Eg: `purl_prefix = purl_prefix + "/" + purl_obj['name']` Use the below SQL query to search by purl_prefix: ``` SELECT DISTINCT cve_id, type, namespace, name, vers, purl_prefix FROM cve_index where purl_prefix = ?; ``` ### Searching by cpe Parse the cpe string to extract the vendor, product, and version. The regex for python is shown below: ```python import re CPE_FULL_REGEX = re.compile( "cpe:?:[^:]+:(?P<cve_type>[^:]+):(?P<vendor>[^:]+):(?P<package>[^:]+):(?P<version>[^:]+):(?P<update>[^:]+):(?P<edition>[^:]+):(?P<lang>[^:]+):(?P<sw_edition>[^:]+):(?P<target_sw>[^:]+):(?P<target_hw>[^:]+):(?P<other>[^:]+)" ) ``` In the `cve_index` table, vendor maps to namespace and package maps to name. The SQL query is below: ```sql SELECT DISTINCT cve_id, type, namespace, name, vers, purl_prefix FROM cve_index where namespace = ? AND name = ?; ``` ### Comparing version ranges using vers Refer to the vers [documentation](https://github.com/package-url/purl-spec/blob/version-range-spec/VERSION-RANGE-SPEC.rst) for information regarding vers and a logic to parse and check if a version is within a range. To simplify the logic, a value from the vers column in `cve_index` would contain only a maximum of two constraints (one greater than and one lesser than). ## Combining data Search the `cve_index` table in the index database first to retrieve any matching cve_id and purl_prefix values. Use these two column values to retrieve the full CVE source information from the `cve_data` table. An example query is shown below: ```sql SELECT DISTINCT cve_id, type, namespace, name, source_data_hash, json(source_data), json(override_data), purl_prefix FROM cve_data WHERE cve_id = ? AND purl_prefix = ? GROUP BY purl_prefix ORDER BY cve_id DESC; ``` Use the `source_data_hash` values to filter out any duplicate results for the same CVE. Duplicate results are possible when multiple vers match the same CVE and purl prefixes. ## Citation Use the below citation in your research. ```text @misc{vdb, author = {Team AppThreat}, month = Feb, title = {{AppThreat vulnerability-db}}, howpublished = {{https://huggingface.co/datasets/AppThreat/vdb}}, year = {2025} } ```

ptb-text-only/ptb_text_only

ptb-text-only

"2024-01-18T11:13:39Z"

18,045

16

[ "task_categories:text-generation", "task_categories:fill-mask", "task_ids:language-modeling", "task_ids:masked-language-modeling", "annotations_creators:expert-generated", "language_creators:found", "multilinguality:monolingual", "source_datasets:original", "language:en", "license:other", "size_categories:10K<n<100K", "region:us" ]

[ "text-generation", "fill-mask" ]

"2022-03-02T23:29:22Z"

--- annotations_creators: - expert-generated language_creators: - found language: - en license: - other license_details: LDC User Agreement for Non-Members multilinguality: - monolingual size_categories: - 10K<n<100K source_datasets: - original task_categories: - text-generation - fill-mask task_ids: - language-modeling - masked-language-modeling paperswithcode_id: null pretty_name: Penn Treebank dataset_info: features: - name: sentence dtype: string config_name: penn_treebank splits: - name: train num_bytes: 5143706 num_examples: 42068 - name: test num_bytes: 453710 num_examples: 3761 - name: validation num_bytes: 403156 num_examples: 3370 download_size: 5951345 dataset_size: 6000572 --- # Dataset Card for Penn Treebank ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Homepage:** https://catalog.ldc.upenn.edu/LDC99T42 - **Repository:** 'https://raw.githubusercontent.com/wojzaremba/lstm/master/data/ptb.train.txt', 'https://raw.githubusercontent.com/wojzaremba/lstm/master/data/ptb.valid.txt', 'https://raw.githubusercontent.com/wojzaremba/lstm/master/data/ptb.test.txt' - **Paper:** https://www.aclweb.org/anthology/J93-2004.pdf - **Leaderboard:** [Needs More Information] - **Point of Contact:** [Needs More Information] ### Dataset Summary This is the Penn Treebank Project: Release 2 CDROM, featuring a million words of 1989 Wall Street Journal material. The rare words in this version are already replaced with <unk> token. The numbers are replaced with <N> token. ### Supported Tasks and Leaderboards Language Modelling ### Languages The text in the dataset is in American English ## Dataset Structure ### Data Instances [Needs More Information] ### Data Fields [Needs More Information] ### Data Splits [Needs More Information] ## Dataset Creation ### Curation Rationale [Needs More Information] ### Source Data #### Initial Data Collection and Normalization [Needs More Information] #### Who are the source language producers? [Needs More Information] ### Annotations #### Annotation process [Needs More Information] #### Who are the annotators? [Needs More Information] ### Personal and Sensitive Information [Needs More Information] ## Considerations for Using the Data ### Social Impact of Dataset [Needs More Information] ### Discussion of Biases [Needs More Information] ### Other Known Limitations [Needs More Information] ## Additional Information ### Dataset Curators [Needs More Information] ### Licensing Information Dataset provided for research purposes only. Please check dataset license for additional information. ### Citation Information @article{marcus-etal-1993-building, title = "Building a Large Annotated Corpus of {E}nglish: The {P}enn {T}reebank", author = "Marcus, Mitchell P. and Santorini, Beatrice and Marcinkiewicz, Mary Ann", journal = "Computational Linguistics", volume = "19", number = "2", year = "1993", url = "https://www.aclweb.org/anthology/J93-2004", pages = "313--330", } ### Contributions Thanks to [@harshalmittal4](https://github.com/harshalmittal4) for adding this dataset.

allenai/sciq

allenai

"2024-01-04T16:23:51Z"

18,019

104

[ "task_categories:question-answering", "task_ids:closed-domain-qa", "annotations_creators:no-annotation", "language_creators:crowdsourced", "multilinguality:monolingual", "source_datasets:original", "language:en", "license:cc-by-nc-3.0", "size_categories:10K<n<100K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]

[ "question-answering" ]

"2022-03-02T23:29:22Z"

--- annotations_creators: - no-annotation language_creators: - crowdsourced language: - en license: - cc-by-nc-3.0 multilinguality: - monolingual size_categories: - 10K<n<100K source_datasets: - original task_categories: - question-answering task_ids: - closed-domain-qa paperswithcode_id: sciq pretty_name: SciQ dataset_info: features: - name: question dtype: string - name: distractor3 dtype: string - name: distractor1 dtype: string - name: distractor2 dtype: string - name: correct_answer dtype: string - name: support dtype: string splits: - name: train num_bytes: 6546183 num_examples: 11679 - name: validation num_bytes: 554120 num_examples: 1000 - name: test num_bytes: 563927 num_examples: 1000 download_size: 4674410 dataset_size: 7664230 configs: - config_name: default data_files: - split: train path: data/train-* - split: validation path: data/validation-* - split: test path: data/test-* --- # Dataset Card for "sciq" ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Homepage:** [https://allenai.org/data/sciq](https://allenai.org/data/sciq) - **Repository:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - **Paper:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - **Point of Contact:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - **Size of downloaded dataset files:** 2.82 MB - **Size of the generated dataset:** 7.68 MB - **Total amount of disk used:** 10.50 MB ### Dataset Summary The SciQ dataset contains 13,679 crowdsourced science exam questions about Physics, Chemistry and Biology, among others. The questions are in multiple-choice format with 4 answer options each. For the majority of the questions, an additional paragraph with supporting evidence for the correct answer is provided. ### Supported Tasks and Leaderboards [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Languages [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Dataset Structure ### Data Instances #### default - **Size of downloaded dataset files:** 2.82 MB - **Size of the generated dataset:** 7.68 MB - **Total amount of disk used:** 10.50 MB An example of 'train' looks as follows. ``` This example was too long and was cropped: { "correct_answer": "coriolis effect", "distractor1": "muon effect", "distractor2": "centrifugal effect", "distractor3": "tropical effect", "question": "What phenomenon makes global winds blow northeast to southwest or the reverse in the northern hemisphere and northwest to southeast or the reverse in the southern hemisphere?", "support": "\"Without Coriolis Effect the global winds would blow north to south or south to north. But Coriolis makes them blow northeast to..." } ``` ### Data Fields The data fields are the same among all splits. #### default - `question`: a `string` feature. - `distractor3`: a `string` feature. - `distractor1`: a `string` feature. - `distractor2`: a `string` feature. - `correct_answer`: a `string` feature. - `support`: a `string` feature. ### Data Splits | name |train|validation|test| |-------|----:|---------:|---:| |default|11679| 1000|1000| ## Dataset Creation ### Curation Rationale [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Source Data #### Initial Data Collection and Normalization [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the source language producers? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Annotations #### Annotation process [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the annotators? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Personal and Sensitive Information [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Discussion of Biases [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Other Known Limitations [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Additional Information ### Dataset Curators [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Licensing Information The dataset is licensed under the [Creative Commons Attribution-NonCommercial 3.0 Unported License](http://creativecommons.org/licenses/by-nc/3.0/). ### Citation Information ``` @inproceedings{SciQ, title={Crowdsourcing Multiple Choice Science Questions}, author={Johannes Welbl, Nelson F. Liu, Matt Gardner}, year={2017}, journal={arXiv:1707.06209v1} } ``` ### Contributions Thanks to [@patrickvonplaten](https://github.com/patrickvonplaten), [@lewtun](https://github.com/lewtun), [@thomwolf](https://github.com/thomwolf) for adding this dataset.

mlfoundations/MINT-1T-PDF-CC-2024-18

mlfoundations

"2024-09-19T21:02:55Z"

17,909

19

[ "task_categories:image-to-text", "task_categories:text-generation", "language:en", "license:cc-by-4.0", "size_categories:100B<n<1T", "arxiv:2406.11271", "region:us", "multimodal" ]

[ "image-to-text", "text-generation" ]

"2024-07-15T03:19:33Z"

--- license: cc-by-4.0 task_categories: - image-to-text - text-generation language: - en tags: - multimodal pretty_name: MINT-1T size_categories: - 100B<n<1T configs: - config_name: default data_files: - split: train path: CC-MAIN-*/* --- <h1 align="center"> 🍃 MINT-1T:<br>Scaling Open-Source Multimodal Data by 10x:<br> A Multimodal Dataset with One Trillion Tokens </h1> 🍃 MINT-1T is an open-source **M**ultimodal **INT**erleaved dataset with 1 trillion text tokens and 3.4 billion images, a 10x scale-up from existing open-source datasets. Additionally, we include previously untapped sources such as PDFs and ArXiv papers. 🍃 MINT-1T is designed to facilitate research in multimodal pretraining. 🍃 MINT-1T is created by a team from the University of Washington in collaboration with Salesforce Research, other academic institutions including Stanford University, University of Texas at Austin, and University of California Berkeley. You are currently viewing a subset of the PDF portion of 🍃 MINT-1T associated with CommonCrawl dump `CC-2024-18`. For other PDF, HTML, and ArXiv subsets, refer to the [🍃 MINT-1T collection](https://huggingface.co/collections/mlfoundations/mint-1t-6690216ca4d0df7e518dde1c). ![Examples](interleaved-example-twitter.png) ## Updates ### 9/19/24 We have removed roughly 10% of the PDF samples as there was a mismatch between the frames in the TIFF images and the document metadata. ### 8/8/24 We have become aware that the image hashes in the PDF subset of MINT-1T do not match the images in the documents. We want to emphasize that the images for each document are correct, and only the image hashes in the documents' metadata are mislabeled. ## Dataset Details ### Dataset Sources - **Repository**: https://github.com/mlfoundations/MINT-1T - **Paper:** https://arxiv.org/abs/2406.11271 - **Blog:** https://blog.salesforceairesearch.com/mint-1t/ ## Uses ### Direct Use  🍃 MINT-1T is designed to facilitate research in multimodal pretraining. The dataset can be used for training multimodal models that can reson about interleaved text and images sequences such as [Idefics2](https://huggingface.co/HuggingFaceM4/idefics2-8b), [XGen-MM](https://huggingface.co/Salesforce/xgen-mm-phi3-mini-instruct-r-v1), and [Chameleon](https://huggingface.co/facebook/chameleon-30b). ### Out-of-Scope Use  🍃 MINT-1T was built to make research into large multimodal models more accessible. Using the dataset to train models that ingest or generate personally identifying information (such as images of people’s faces and other sensitive content) as well as military applications are all inappropriate use cases of 🍃 MINT-1T. ## Dataset Creation ### Curation Rationale 🍃 MINT-1T was created to address a significant gap in the open-source domain by providing a large-scale multimodal interleaved dataset for pre-training large multimodal models. This dataset aims to be a valuable resource for the research community, facilitating open science in multimodal pretraining. ### Source Data The dataset is a comprehensive collection of multimodal documents from various sources: - HTML documents: Filtered from CommonCrawl WARC dumps spanning from 2017 to 2024 - PDF documents: Extracted from CommonCrawl WAT dumps covering 2023 to 2024 - ArXiv documents: A subset of papers from the ArXiv repository In total, 🍃 MINT-1T contains 1056.8 million documents, broken down as follows: - 1029.4 million HTML documents - 24.0 million PDF documents - 0.6 million ArXiv documents #### Data Collection and Processing The data collection and processing involved several steps: 1. Document Extraction: - HTML documents were parsed from CommonCrawl WARC files - PDF documents were extracted from CommonCrawl WAT files - ArXiv papers were directly sourced from ArXiv S3 buckets 2. Filtering Process: - Applied text quality filters to ensure content relevance and readability - Removed duplicate content at both paragraph and document levels - Filtered out undesirable content based on predefined criteria - Verified image availability and quality for HTML documents - Limited PDF size to 50MB and 50 pages to manage dataset size and quality 3. Image Processing: - Used NSFW image detection to remove pornographic or otherwise undesirable images - Removed images smaller than 150 pixels or larger than 20,000 pixels - Adjusted aspect ratio thresholds for HTML (2:1) and PDF (3:1) to preserve scientific figures 4. Text Processing: - Used fasttext for language identification, focusing on English content - Masked personally identifiable information such as email addresses and IP addresses - Applied paragraph and document-level deduplication using Bloom filters 5. PDF Specific Processing: - Used PyMuPDF for parsing PDFs and extracting reading order - Clustered text blocks based on columns and ordered from top left to bottom right 6. ArXiv Specific Processing: - Used TexSoup to parse LaTeX source code and interleave images with text - Cleaned up LaTeX code by removing imports, bibliography, tables, and citation tags Various open-source tools were utilized in this process, including fasttext, [PyMuPDF](https://github.com/pymupdf/PyMuPDF), and [DCLM](https://www.datacomp.ai/dclm/) and [bff](https://github.com/revbucket/bff) for deduplication and content filtering. #### Personal and Sensitive Information Despite sourcing from public web data, significant efforts were made to minimize the inclusion of personal and sensitive information: - Email addresses and IP addresses were masked to protect privacy - An NSFW image classifierto remove inappropriate visual content - URLs containing substrings associated with undesirable or sensitive content were filtered out However, users should be aware that as the data originates from the public web, it may still contain some sensitive or personal information. The dataset creators acknowledge this limitation and advise users to exercise caution and potentially apply additional filtering based on their specific use cases. ## Bias, Risks, and Limitations Several potential biases, risks, and limitations have been identified: 1. Data Bias: As the dataset is sourced from web crawls, it may inherit biases present in online content. 2. Content Risks: Despite extensive filtering, there's a possibility that some offensive, insensitive, or inappropriate content may remain in the dataset. 3. Image Availability: The dataset relies on external image URLs, which may become unavailable over time due to link rot, potentially affecting the dataset's long-term usability. 4. PDF Parsing Limitations: The current method for extracting reading order from PDFs may not always accurately capture the intended flow, especially for documents with complex layouts. 5. Potential Legal and Ethical Concerns: While efforts were made to respect robots.txt files and remove sensitive information, there may still be content that individuals did not explicitly consent to include. ### Recommendations Given these considerations, the following recommendations are provided: 1. Additional Filtering: Users are strongly encouraged to apply additional filtering based on their specific use case and ethical considerations. 2. Inappropriate Use Cases: The dataset is not recommended for applications involving the processing or generation of personally identifying information, nor for military applications. 3. Legal Compliance: Users should independently verify compliance with applicable laws before employing MINT-1T for commercial purposes. 4. Bias Awareness: Researchers and developers should be cognizant of potential biases in the dataset and consider their impact on model training and outputs. ## License We release 🍃 MINT-1T under a CC-BY-4.0 license, designating it primarily as a research artifact. While the dataset is freely available, users are responsible for ensuring its legal use in commercial settings. Users must independently verify compliance with applicable laws before employing MINT-1T for commercial purposes. ## Citation ``` @article{awadalla2024mint1t, title={MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokens}, author={Anas Awadalla and Le Xue and Oscar Lo and Manli Shu and Hannah Lee and Etash Kumar Guha and Matt Jordan and Sheng Shen and Mohamed Awadalla and Silvio Savarese and Caiming Xiong and Ran Xu and Yejin Choi and Ludwig Schmidt}, year={2024} } ```

gigant/tib_slides

gigant

"2025-01-28T14:40:52Z"

17,901

0

[ "size_categories:100K<n<1M", "format:parquet", "modality:image", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]

null

"2023-01-27T01:44:02Z"

--- dataset_info: features: - name: Image dtype: image - name: file_name dtype: string splits: - name: train num_bytes: 131956494917.654 num_examples: 484843 download_size: 0 dataset_size: 131956494917.654 --- # Dataset Card for "tib_slides" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

bhatvineet/shrutilipi_mr

bhatvineet

"2023-03-13T18:54:45Z"

17,888

0

[ "size_categories:100K<n<1M", "format:parquet", "modality:audio", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]

null

"2023-03-13T07:12:52Z"

--- dataset_info: features: - name: audio dtype: audio - name: transcriptions dtype: string splits: - name: train num_bytes: 114253169328.11655 num_examples: 474332 - name: test num_bytes: 39048725811.21545 num_examples: 158111 download_size: 147662822982 dataset_size: 153301895139.332 --- # Dataset Card for "shrutilipi_mr" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

google/IFEval

google

"2024-08-14T08:21:56Z"

17,851

64

[ "task_categories:text-generation", "language:en", "license:apache-2.0", "size_categories:n<1K", "format:json", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "arxiv:2311.07911", "region:us" ]

[ "text-generation" ]

"2023-12-22T11:20:03Z"

--- license: apache-2.0 task_categories: - text-generation language: - en pretty_name: IFEval --- # Dataset Card for IFEval  ## Dataset Description - **Repository:** https://github.com/google-research/google-research/tree/master/instruction_following_eval - **Paper:** https://huggingface.co/papers/2311.07911 - **Leaderboard:** https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard - **Point of Contact:** [Le Hou]([email protected]) ### Dataset Summary This dataset contains the prompts used in the [Instruction-Following Eval (IFEval) benchmark](https://arxiv.org/abs/2311.07911) for large language models. It contains around 500 "verifiable instructions" such as "write in more than 400 words" and "mention the keyword of AI at least 3 times" which can be verified by heuristics. To load the dataset, run: ```python from datasets import load_dataset ifeval = load_dataset("google/IFEval") ``` ### Supported Tasks and Leaderboards The IFEval dataset is designed for evaluating chat or instruction fine-tuned language models and is one of the core benchmarks used in the [Open LLM Leaderboard](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard). ### Languages The data in IFEval are in English (BCP-47 en). ## Dataset Structure ### Data Instances An example of the `train` split looks as follows: ``` { "key": 1000, "prompt": 'Write a 300+ word summary of the wikipedia page "https://en.wikipedia.org/wiki/Raymond_III,_Count_of_Tripoli". Do not use any commas and highlight at least 3 sections that has titles in markdown format, for example *highlighted section part 1*, *highlighted section part 2*, *highlighted section part 3*.', "instruction_id_list": [ "punctuation:no_comma", "detectable_format:number_highlighted_sections", "length_constraints:number_words", ], "kwargs": [ { "num_highlights": None, "relation": None, "num_words": None, "num_placeholders": None, "prompt_to_repeat": None, "num_bullets": None, "section_spliter": None, "num_sections": None, "capital_relation": None, "capital_frequency": None, "keywords": None, "num_paragraphs": None, "language": None, "let_relation": None, "letter": None, "let_frequency": None, "end_phrase": None, "forbidden_words": None, "keyword": None, "frequency": None, "num_sentences": None, "postscript_marker": None, "first_word": None, "nth_paragraph": None, }, { "num_highlights": 3, "relation": None, "num_words": None, "num_placeholders": None, "prompt_to_repeat": None, "num_bullets": None, "section_spliter": None, "num_sections": None, "capital_relation": None, "capital_frequency": None, "keywords": None, "num_paragraphs": None, "language": None, "let_relation": None, "letter": None, "let_frequency": None, "end_phrase": None, "forbidden_words": None, "keyword": None, "frequency": None, "num_sentences": None, "postscript_marker": None, "first_word": None, "nth_paragraph": None, }, { "num_highlights": None, "relation": "at least", "num_words": 300, "num_placeholders": None, "prompt_to_repeat": None, "num_bullets": None, "section_spliter": None, "num_sections": None, "capital_relation": None, "capital_frequency": None, "keywords": None, "num_paragraphs": None, "language": None, "let_relation": None, "letter": None, "let_frequency": None, "end_phrase": None, "forbidden_words": None, "keyword": None, "frequency": None, "num_sentences": None, "postscript_marker": None, "first_word": None, "nth_paragraph": None, }, ], } ``` ### Data Fields The data fields are as follows: * `key`: A unique ID for the prompt. * `prompt`: Describes the task the model should perform. * `instruction_id_list`: An array of verifiable instructions. See Table 1 of the paper for the full set with their descriptions. * `kwargs`: An array of arguments used to specify each verifiable instruction in `instruction_id_list`. ### Data Splits | | train | |---------------|------:| | IFEval | 541 | ### Licensing Information The dataset is available under the [Apache 2.0 license](https://www.apache.org/licenses/LICENSE-2.0). ### Citation Information ``` @misc{zhou2023instructionfollowingevaluationlargelanguage, title={Instruction-Following Evaluation for Large Language Models}, author={Jeffrey Zhou and Tianjian Lu and Swaroop Mishra and Siddhartha Brahma and Sujoy Basu and Yi Luan and Denny Zhou and Le Hou}, year={2023}, eprint={2311.07911}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2311.07911}, } ```

mythicinfinity/libritts

mythicinfinity

"2024-02-09T21:19:32Z"

17,754

14

[ "task_categories:text-to-speech", "language:en", "license:cc-by-4.0", "size_categories:100K<n<1M", "format:parquet", "modality:audio", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "arxiv:1904.02882", "region:us" ]

[ "text-to-speech" ]

"2024-02-08T02:07:23Z"

--- license: cc-by-4.0 task_categories: - text-to-speech language: - en size_categories: - 10K<n<100K configs: - config_name: dev data_files: - split: dev.clean path: "data/dev.clean/dev.clean*.parquet" - config_name: clean data_files: - split: dev.clean path: "data/dev.clean/dev.clean*.parquet" - split: test.clean path: "data/test.clean/test.clean*.parquet" - split: train.clean.100 path: "data/train.clean.100/train.clean.100*.parquet" - split: train.clean.360 path: "data/train.clean.360/train.clean.360*.parquet" - config_name: other data_files: - split: dev.other path: "data/dev.other/dev.other*.parquet" - split: test.other path: "data/test.other/test.other*.parquet" - split: train.other.500 path: "data/train.other.500/train.other.500*.parquet" - config_name: all data_files: - split: dev.clean path: "data/dev.clean/dev.clean*.parquet" - split: dev.other path: "data/dev.other/dev.other*.parquet" - split: test.clean path: "data/test.clean/test.clean*.parquet" - split: test.other path: "data/test.other/test.other*.parquet" - split: train.clean.100 path: "data/train.clean.100/train.clean.100*.parquet" - split: train.clean.360 path: "data/train.clean.360/train.clean.360*.parquet" - split: train.other.500 path: "data/train.other.500/train.other.500*.parquet" --- # Dataset Card for LibriTTS  LibriTTS is a multi-speaker English corpus of approximately 585 hours of read English speech at 24kHz sampling rate, prepared by Heiga Zen with the assistance of Google Speech and Google Brain team members. The LibriTTS corpus is designed for TTS research. It is derived from the original materials (mp3 audio files from LibriVox and text files from Project Gutenberg) of the LibriSpeech corpus. ## Overview This is the LibriTTS dataset, adapted for the `datasets` library. ## Usage ### Splits There are 7 splits (dots replace dashes from the original dataset, to comply with hf naming requirements): - dev.clean - dev.other - test.clean - test.other - train.clean.100 - train.clean.360 - train.other.500 ### Configurations There are 3 configurations, each which limits the splits the `load_dataset()` function will download. The default configuration is "all". - "dev": only the "dev.clean" split (good for testing the dataset quickly) - "clean": contains only "clean" splits - "other": contains only "other" splits - "all": contains only "all" splits ### Example Loading the `clean` config with only the `train.clean.360` split. ``` load_dataset("blabble-io/libritts", "clean", split="train.clean.100") ``` Streaming is also supported. ``` load_dataset("blabble-io/libritts", streaming=True) ``` ### Columns ``` { "audio": datasets.Audio(sampling_rate=24_000), "text_normalized": datasets.Value("string"), "text_original": datasets.Value("string"), "speaker_id": datasets.Value("string"), "path": datasets.Value("string"), "chapter_id": datasets.Value("string"), "id": datasets.Value("string"), } ``` ### Example Row ``` { 'audio': { 'path': '/home/user/.cache/huggingface/datasets/downloads/extracted/5551a515e85b9e463062524539c2e1cb52ba32affe128dffd866db0205248bdd/LibriTTS/dev-clean/3081/166546/3081_166546_000028_000002.wav', 'array': ..., 'sampling_rate': 24000 }, 'text_normalized': 'How quickly he disappeared!"', 'text_original': 'How quickly he disappeared!"', 'speaker_id': '3081', 'path': '/home/user/.cache/huggingface/datasets/downloads/extracted/5551a515e85b9e463062524539c2e1cb52ba32affe128dffd866db0205248bdd/LibriTTS/dev-clean/3081/166546/3081_166546_000028_000002.wav', 'chapter_id': '166546', 'id': '3081_166546_000028_000002' } ``` ## Dataset Details ### Dataset Description - **License:** CC BY 4.0 ### Dataset Sources [optional]  - **Homepage:** https://www.openslr.org/60/ - **Paper:** https://arxiv.org/abs/1904.02882 ## Citation  ``` @ARTICLE{Zen2019-kz, title = "{LibriTTS}: A corpus derived from {LibriSpeech} for text-to-speech", author = "Zen, Heiga and Dang, Viet and Clark, Rob and Zhang, Yu and Weiss, Ron J and Jia, Ye and Chen, Zhifeng and Wu, Yonghui", abstract = "This paper introduces a new speech corpus called ``LibriTTS'' designed for text-to-speech use. It is derived from the original audio and text materials of the LibriSpeech corpus, which has been used for training and evaluating automatic speech recognition systems. The new corpus inherits desired properties of the LibriSpeech corpus while addressing a number of issues which make LibriSpeech less than ideal for text-to-speech work. The released corpus consists of 585 hours of speech data at 24kHz sampling rate from 2,456 speakers and the corresponding texts. Experimental results show that neural end-to-end TTS models trained from the LibriTTS corpus achieved above 4.0 in mean opinion scores in naturalness in five out of six evaluation speakers. The corpus is freely available for download from http://www.openslr.org/60/.", month = apr, year = 2019, copyright = "http://arxiv.org/licenses/nonexclusive-distrib/1.0/", archivePrefix = "arXiv", primaryClass = "cs.SD", eprint = "1904.02882" } ```

Helsinki-NLP/opus_openoffice

Helsinki-NLP

"2024-02-22T15:14:50Z"

17,712

7

[ "task_categories:translation", "annotations_creators:found", "language_creators:found", "multilinguality:multilingual", "source_datasets:original", "language:de", "language:en", "language:es", "language:fr", "language:ja", "language:ru", "language:sv", "language:zh", "license:unknown", "size_categories:1M<n<10M", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]

[ "translation" ]

"2022-03-02T23:29:22Z"

--- annotations_creators: - found language_creators: - found language: - de - en - es - fr - ja - ru - sv - zh license: - unknown multilinguality: - multilingual size_categories: - 10K<n<100K source_datasets: - original task_categories: - translation task_ids: [] pretty_name: OpusOpenoffice config_names: - de-en_GB - de-es - de-fr - de-ja - de-ru - de-sv - de-zh_CN - en_GB-es - en_GB-fr - en_GB-ja - en_GB-ru - en_GB-sv - en_GB-zh_CN - es-fr - es-ja - es-ru - es-sv - es-zh_CN - fr-ja - fr-ru - fr-sv - fr-zh_CN - ja-ru - ja-sv - ja-zh_CN - ru-sv - ru-zh_CN - sv-zh_CN language_bcp47: - en-GB - zh-CN dataset_info: - config_name: de-en_GB features: - name: translation dtype: translation: languages: - de - en_GB splits: - name: train num_bytes: 6201077 num_examples: 77052 download_size: 2983173 dataset_size: 6201077 - config_name: de-es features: - name: translation dtype: translation: languages: - de - es splits: - name: train num_bytes: 6571615 num_examples: 77000 download_size: 3145841 dataset_size: 6571615 - config_name: de-fr features: - name: translation dtype: translation: languages: - de - fr splits: - name: train num_bytes: 6715805 num_examples: 76684 download_size: 3167189 dataset_size: 6715805 - config_name: de-ja features: - name: translation dtype: translation: languages: - de - ja splits: - name: train num_bytes: 7084951 num_examples: 69396 download_size: 3137719 dataset_size: 7084951 - config_name: de-ru features: - name: translation dtype: translation: languages: - de - ru splits: - name: train num_bytes: 8333241 num_examples: 75511 download_size: 3585304 dataset_size: 8333241 - config_name: de-sv features: - name: translation dtype: translation: languages: - de - sv splits: - name: train num_bytes: 6288962 num_examples: 77366 download_size: 3053987 dataset_size: 6288962 - config_name: de-zh_CN features: - name: translation dtype: translation: languages: - de - zh_CN splits: - name: train num_bytes: 5836628 num_examples: 68712 download_size: 2862703 dataset_size: 5836628 - config_name: en_GB-es features: - name: translation dtype: translation: languages: - en_GB - es splits: - name: train num_bytes: 6147581 num_examples: 77646 download_size: 2933203 dataset_size: 6147581 - config_name: en_GB-fr features: - name: translation dtype: translation: languages: - en_GB - fr splits: - name: train num_bytes: 6297779 num_examples: 77696 download_size: 2952170 dataset_size: 6297779 - config_name: en_GB-ja features: - name: translation dtype: translation: languages: - en_GB - ja splits: - name: train num_bytes: 6636722 num_examples: 69149 download_size: 2920159 dataset_size: 6636722 - config_name: en_GB-ru features: - name: translation dtype: translation: languages: - en_GB - ru splits: - name: train num_bytes: 7877970 num_examples: 75401 download_size: 3356420 dataset_size: 7877970 - config_name: en_GB-sv features: - name: translation dtype: translation: languages: - en_GB - sv splits: - name: train num_bytes: 5861461 num_examples: 77815 download_size: 2839624 dataset_size: 5861461 - config_name: en_GB-zh_CN features: - name: translation dtype: translation: languages: - en_GB - zh_CN splits: - name: train num_bytes: 5424865 num_examples: 69400 download_size: 2663377 dataset_size: 5424865 - config_name: es-fr features: - name: translation dtype: translation: languages: - es - fr splits: - name: train num_bytes: 6663092 num_examples: 77417 download_size: 3115129 dataset_size: 6663092 - config_name: es-ja features: - name: translation dtype: translation: languages: - es - ja splits: - name: train num_bytes: 7005123 num_examples: 68944 download_size: 3075174 dataset_size: 7005123 - config_name: es-ru features: - name: translation dtype: translation: languages: - es - ru splits: - name: train num_bytes: 8283703 num_examples: 76461 download_size: 3533017 dataset_size: 8283703 - config_name: es-sv features: - name: translation dtype: translation: languages: - es - sv splits: - name: train num_bytes: 6232466 num_examples: 77825 download_size: 2999454 dataset_size: 6232466 - config_name: es-zh_CN features: - name: translation dtype: translation: languages: - es - zh_CN splits: - name: train num_bytes: 5776827 num_examples: 68583 download_size: 2815094 dataset_size: 5776827 - config_name: fr-ja features: - name: translation dtype: translation: languages: - fr - ja splits: - name: train num_bytes: 7160332 num_examples: 69026 download_size: 3104825 dataset_size: 7160332 - config_name: fr-ru features: - name: translation dtype: translation: languages: - fr - ru splits: - name: train num_bytes: 8432061 num_examples: 76464 download_size: 3553215 dataset_size: 8432061 - config_name: fr-sv features: - name: translation dtype: translation: languages: - fr - sv splits: - name: train num_bytes: 6373350 num_examples: 77398 download_size: 3020247 dataset_size: 6373350 - config_name: fr-zh_CN features: - name: translation dtype: translation: languages: - fr - zh_CN splits: - name: train num_bytes: 5918482 num_examples: 68723 download_size: 2834942 dataset_size: 5918482 - config_name: ja-ru features: - name: translation dtype: translation: languages: - ja - ru splits: - name: train num_bytes: 8781230 num_examples: 68589 download_size: 3534714 dataset_size: 8781230 - config_name: ja-sv features: - name: translation dtype: translation: languages: - ja - sv splits: - name: train num_bytes: 6709627 num_examples: 69154 download_size: 2983777 dataset_size: 6709627 - config_name: ja-zh_CN features: - name: translation dtype: translation: languages: - ja - zh_CN splits: - name: train num_bytes: 6397676 num_examples: 68953 download_size: 2877818 dataset_size: 6397676 - config_name: ru-sv features: - name: translation dtype: translation: languages: - ru - sv splits: - name: train num_bytes: 7966150 num_examples: 75560 download_size: 3425447 dataset_size: 7966150 - config_name: ru-zh_CN features: - name: translation dtype: translation: languages: - ru - zh_CN splits: - name: train num_bytes: 7393659 num_examples: 66259 download_size: 3224677 dataset_size: 7393659 - config_name: sv-zh_CN features: - name: translation dtype: translation: languages: - sv - zh_CN splits: - name: train num_bytes: 5492902 num_examples: 68846 download_size: 2722340 dataset_size: 5492902 configs: - config_name: de-en_GB data_files: - split: train path: de-en_GB/train-* - config_name: de-es data_files: - split: train path: de-es/train-* - config_name: de-fr data_files: - split: train path: de-fr/train-* - config_name: de-ja data_files: - split: train path: de-ja/train-* - config_name: de-ru data_files: - split: train path: de-ru/train-* - config_name: de-sv data_files: - split: train path: de-sv/train-* - config_name: de-zh_CN data_files: - split: train path: de-zh_CN/train-* - config_name: en_GB-es data_files: - split: train path: en_GB-es/train-* - config_name: en_GB-fr data_files: - split: train path: en_GB-fr/train-* - config_name: en_GB-ja data_files: - split: train path: en_GB-ja/train-* - config_name: en_GB-ru data_files: - split: train path: en_GB-ru/train-* - config_name: en_GB-sv data_files: - split: train path: en_GB-sv/train-* - config_name: en_GB-zh_CN data_files: - split: train path: en_GB-zh_CN/train-* - config_name: es-fr data_files: - split: train path: es-fr/train-* - config_name: es-ja data_files: - split: train path: es-ja/train-* - config_name: es-ru data_files: - split: train path: es-ru/train-* - config_name: es-sv data_files: - split: train path: es-sv/train-* - config_name: es-zh_CN data_files: - split: train path: es-zh_CN/train-* - config_name: fr-ja data_files: - split: train path: fr-ja/train-* - config_name: fr-ru data_files: - split: train path: fr-ru/train-* - config_name: fr-sv data_files: - split: train path: fr-sv/train-* - config_name: fr-zh_CN data_files: - split: train path: fr-zh_CN/train-* - config_name: ja-ru data_files: - split: train path: ja-ru/train-* - config_name: ja-sv data_files: - split: train path: ja-sv/train-* - config_name: ja-zh_CN data_files: - split: train path: ja-zh_CN/train-* - config_name: ru-sv data_files: - split: train path: ru-sv/train-* - config_name: ru-zh_CN data_files: - split: train path: ru-zh_CN/train-* - config_name: sv-zh_CN data_files: - split: train path: sv-zh_CN/train-* --- # Dataset Card for [Dataset Name] ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Homepage:** https://opus.nlpl.eu/OpenOffice/corpus/version/OpenOffice - **Repository:** - **Paper:** - **Leaderboard:** - **Point of Contact:** ### Dataset Summary A collection of documents from http://www.openoffice.org/. 8 languages, 28 bitexts ### Supported Tasks and Leaderboards The underlying task is machine translation. ### Languages [More Information Needed] ## Dataset Structure ### Data Instances [More Information Needed] ### Data Fields [More Information Needed] ### Data Splits [More Information Needed] ## Dataset Creation ### Curation Rationale [More Information Needed] ### Source Data #### Initial Data Collection and Normalization [More Information Needed] #### Who are the source language producers? [More Information Needed] ### Annotations #### Annotation process [More Information Needed] #### Who are the annotators? [More Information Needed] ### Personal and Sensitive Information [More Information Needed] ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed] ### Discussion of Biases [More Information Needed] ### Other Known Limitations [More Information Needed] ## Additional Information ### Dataset Curators [More Information Needed] ### Licensing Information [More Information Needed] ### Citation Information ``` @InProceedings{TIEDEMANN12.463, author = {J�rg Tiedemann}, title = {Parallel Data, Tools and Interfaces in OPUS}, booktitle = {Proceedings of the Eight International Conference on Language Resources and Evaluation (LREC'12)}, year = {2012}, month = {may}, date = {23-25}, address = {Istanbul, Turkey}, editor = {Nicoletta Calzolari (Conference Chair) and Khalid Choukri and Thierry Declerck and Mehmet Ugur Dogan and Bente Maegaard and Joseph Mariani and Jan Odijk and Stelios Piperidis}, publisher = {European Language Resources Association (ELRA)}, isbn = {978-2-9517408-7-7}, language = {english} } ``` ### Contributions Thanks to [@patil-suraj](https://github.com/patil-suraj) for adding this dataset.

MMMU/MMMU

MMMU

"2024-09-19T17:11:03Z"

17,684

242

[ "task_categories:question-answering", "task_categories:visual-question-answering", "task_categories:multiple-choice", "language:en", "license:apache-2.0", "size_categories:10K<n<100K", "format:parquet", "modality:image", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "arxiv:2311.16502", "region:us", "biology", "medical", "finance", "chemistry", "music", "art", "art_theory", "design", "business", "accounting", "economics", "manage", "marketing", "health", "medicine", "basic_medical_science", "clinical", "pharmacy", "public_health", "humanities", "social_science", "history", "literature", "sociology", "psychology", "science", "geography", "math", "physics", "engineering", "agriculture", "architecture", "computer_science", "electronics", "energy_and_power", "materials", "mechanical_engineering" ]

[ "question-answering", "visual-question-answering", "multiple-choice" ]

"2023-11-27T17:52:01Z"

--- language: - en license: apache-2.0 size_categories: - 10K<n<100K task_categories: - question-answering - visual-question-answering - multiple-choice pretty_name: mmmu dataset_info: - config_name: Accounting features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 262599.0 num_examples: 5 - name: validation num_bytes: 1598285.0 num_examples: 30 - name: test num_bytes: 22135625.0 num_examples: 380 download_size: 37363379 dataset_size: 23996509.0 - config_name: Agriculture features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 22082656.0 num_examples: 5 - name: validation num_bytes: 119217558.0 num_examples: 30 - name: test num_bytes: 993664077.0 num_examples: 287 download_size: 1158036990 dataset_size: 1134964291.0 - config_name: Architecture_and_Engineering features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 137750.0 num_examples: 5 - name: validation num_bytes: 721378.0 num_examples: 30 - name: test num_bytes: 16054607.0 num_examples: 551 download_size: 48763955 dataset_size: 16913735.0 - config_name: Art features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 6241184.0 num_examples: 5 - name: validation num_bytes: 29934534.0 num_examples: 30 - name: test num_bytes: 237801390.0 num_examples: 231 download_size: 585798641 dataset_size: 273977108.0 - config_name: Art_Theory features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 7435106.0 num_examples: 5 - name: validation num_bytes: 33481558.0 num_examples: 30 - name: test num_bytes: 553174647.0 num_examples: 429 download_size: 930525695 dataset_size: 594091311.0 - config_name: Basic_Medical_Science features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 814310.0 num_examples: 5 - name: validation num_bytes: 4125930.0 num_examples: 30 - name: test num_bytes: 48125891.0 num_examples: 326 download_size: 84666454 dataset_size: 53066131.0 - config_name: Biology features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 574342.0 num_examples: 5 - name: validation num_bytes: 8491863.0 num_examples: 30 - name: test num_bytes: 132966151.0 num_examples: 345 download_size: 410242502 dataset_size: 142032356.0 - config_name: Chemistry features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 262397.0 num_examples: 5 - name: validation num_bytes: 1518573.0 num_examples: 30 - name: test num_bytes: 37219529.0 num_examples: 603 download_size: 108345562 dataset_size: 39000499.0 - config_name: Clinical_Medicine features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 1467945.0 num_examples: 5 - name: validation num_bytes: 10882484.0 num_examples: 30 - name: test num_bytes: 98201863.0 num_examples: 325 download_size: 160611488 dataset_size: 110552292.0 - config_name: Computer_Science features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 440523.0 num_examples: 5 - name: validation num_bytes: 2072018.0 num_examples: 30 - name: test num_bytes: 32047381.0 num_examples: 371 download_size: 55640991 dataset_size: 34559922.0 - config_name: Design features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 2259873.0 num_examples: 5 - name: validation num_bytes: 17923120.0 num_examples: 30 - name: test num_bytes: 77676331.0 num_examples: 169 download_size: 142866617 dataset_size: 97859324.0 - config_name: Diagnostics_and_Laboratory_Medicine features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 2056117.0 num_examples: 5 - name: validation num_bytes: 37106233.0 num_examples: 30 - name: test num_bytes: 157003069.0 num_examples: 162 download_size: 603957093 dataset_size: 196165419.0 - config_name: Economics features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 171434.0 num_examples: 5 - name: validation num_bytes: 1487048.0 num_examples: 30 - name: test num_bytes: 11852300.0 num_examples: 267 download_size: 20777635 dataset_size: 13510782.0 - config_name: Electronics features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 123632.0 num_examples: 5 - name: validation num_bytes: 641377.0 num_examples: 30 - name: test num_bytes: 5717686.0 num_examples: 256 download_size: 11602832 dataset_size: 6482695.0 - config_name: Energy_and_Power features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 105006.0 num_examples: 5 - name: validation num_bytes: 1641935.0 num_examples: 30 - name: test num_bytes: 14748428.0 num_examples: 432 download_size: 35246567 dataset_size: 16495369.0 - config_name: Finance features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 296124.0 num_examples: 5 - name: validation num_bytes: 1071060.0 num_examples: 30 - name: test num_bytes: 12065803.0 num_examples: 355 download_size: 29551521 dataset_size: 13432987.0 - config_name: Geography features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 1494060.0 num_examples: 5 - name: validation num_bytes: 6671316.0 num_examples: 30 - name: test num_bytes: 137218400.0 num_examples: 565 download_size: 374766631 dataset_size: 145383776.0 - config_name: History features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 1444231.0 num_examples: 5 - name: validation num_bytes: 8819857.0 num_examples: 30 - name: test num_bytes: 115228815.0 num_examples: 278 download_size: 232549641 dataset_size: 125492903.0 - config_name: Literature features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 2451201.0 num_examples: 5 - name: validation num_bytes: 14241046.0 num_examples: 30 - name: test num_bytes: 50301541.0 num_examples: 112 download_size: 132145895 dataset_size: 66993788.0 - config_name: Manage features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 449514.0 num_examples: 5 - name: validation num_bytes: 3277436.0 num_examples: 30 - name: test num_bytes: 29963963.0 num_examples: 245 download_size: 51186888 dataset_size: 33690913.0 - config_name: Marketing features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 116960.0 num_examples: 5 - name: validation num_bytes: 1472981.0 num_examples: 30 - name: test num_bytes: 7732976.0 num_examples: 181 download_size: 13146078 dataset_size: 9322917.0 - config_name: Materials features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 239632.0 num_examples: 5 - name: validation num_bytes: 2305223.0 num_examples: 30 - name: test num_bytes: 25256854.0 num_examples: 458 download_size: 105773156 dataset_size: 27801709.0 - config_name: Math features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 175839.0 num_examples: 5 - name: validation num_bytes: 1444496.0 num_examples: 30 - name: test num_bytes: 27701845.0 num_examples: 505 download_size: 174098418 dataset_size: 29322180.0 - config_name: Mechanical_Engineering features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 152542.0 num_examples: 5 - name: validation num_bytes: 874988.0 num_examples: 30 - name: test num_bytes: 15093746.0 num_examples: 429 download_size: 30450114 dataset_size: 16121276.0 - config_name: Music features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 1417615.0 num_examples: 5 - name: validation num_bytes: 9359372.0 num_examples: 30 - name: test num_bytes: 134096770.0 num_examples: 334 download_size: 174725052 dataset_size: 144873757.0 - config_name: Pharmacy features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 207924.0 num_examples: 5 - name: validation num_bytes: 1656342.0 num_examples: 30 - name: test num_bytes: 31866248.0 num_examples: 430 download_size: 62721263 dataset_size: 33730514.0 - config_name: Physics features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 233734.0 num_examples: 5 - name: validation num_bytes: 1114130.0 num_examples: 30 - name: test num_bytes: 15905705.0 num_examples: 408 download_size: 35238571 dataset_size: 17253569.0 - config_name: Psychology features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 600864.0 num_examples: 5 - name: validation num_bytes: 4403886.0 num_examples: 30 - name: test num_bytes: 53813915.0 num_examples: 305 download_size: 102466671 dataset_size: 58818665.0 - config_name: Public_Health features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 234781.0 num_examples: 5 - name: validation num_bytes: 1508761.0 num_examples: 30 - name: test num_bytes: 32150088.0 num_examples: 509 download_size: 48231609 dataset_size: 33893630.0 - config_name: Sociology features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 3769220.0 num_examples: 5 - name: validation num_bytes: 18455336.0 num_examples: 30 - name: test num_bytes: 144301123.0 num_examples: 252 download_size: 310313826 dataset_size: 166525679.0 configs: - config_name: Accounting data_files: - split: dev path: Accounting/dev-* - split: validation path: Accounting/validation-* - split: test path: Accounting/test-* - config_name: Agriculture data_files: - split: dev path: Agriculture/dev-* - split: validation path: Agriculture/validation-* - split: test path: Agriculture/test-* - config_name: Architecture_and_Engineering data_files: - split: dev path: Architecture_and_Engineering/dev-* - split: validation path: Architecture_and_Engineering/validation-* - split: test path: Architecture_and_Engineering/test-* - config_name: Art data_files: - split: dev path: Art/dev-* - split: validation path: Art/validation-* - split: test path: Art/test-* - config_name: Art_Theory data_files: - split: dev path: Art_Theory/dev-* - split: validation path: Art_Theory/validation-* - split: test path: Art_Theory/test-* - config_name: Basic_Medical_Science data_files: - split: dev path: Basic_Medical_Science/dev-* - split: validation path: Basic_Medical_Science/validation-* - split: test path: Basic_Medical_Science/test-* - config_name: Biology data_files: - split: dev path: Biology/dev-* - split: validation path: Biology/validation-* - split: test path: Biology/test-* - config_name: Chemistry data_files: - split: dev path: Chemistry/dev-* - split: validation path: Chemistry/validation-* - split: test path: Chemistry/test-* - config_name: Clinical_Medicine data_files: - split: dev path: Clinical_Medicine/dev-* - split: validation path: Clinical_Medicine/validation-* - split: test path: Clinical_Medicine/test-* - config_name: Computer_Science data_files: - split: dev path: Computer_Science/dev-* - split: validation path: Computer_Science/validation-* - split: test path: Computer_Science/test-* - config_name: Design data_files: - split: dev path: Design/dev-* - split: validation path: Design/validation-* - split: test path: Design/test-* - config_name: Diagnostics_and_Laboratory_Medicine data_files: - split: dev path: Diagnostics_and_Laboratory_Medicine/dev-* - split: validation path: Diagnostics_and_Laboratory_Medicine/validation-* - split: test path: Diagnostics_and_Laboratory_Medicine/test-* - config_name: Economics data_files: - split: dev path: Economics/dev-* - split: validation path: Economics/validation-* - split: test path: Economics/test-* - config_name: Electronics data_files: - split: dev path: Electronics/dev-* - split: validation path: Electronics/validation-* - split: test path: Electronics/test-* - config_name: Energy_and_Power data_files: - split: dev path: Energy_and_Power/dev-* - split: validation path: Energy_and_Power/validation-* - split: test path: Energy_and_Power/test-* - config_name: Finance data_files: - split: dev path: Finance/dev-* - split: validation path: Finance/validation-* - split: test path: Finance/test-* - config_name: Geography data_files: - split: dev path: Geography/dev-* - split: validation path: Geography/validation-* - split: test path: Geography/test-* - config_name: History data_files: - split: dev path: History/dev-* - split: validation path: History/validation-* - split: test path: History/test-* - config_name: Literature data_files: - split: dev path: Literature/dev-* - split: validation path: Literature/validation-* - split: test path: Literature/test-* - config_name: Manage data_files: - split: dev path: Manage/dev-* - split: validation path: Manage/validation-* - split: test path: Manage/test-* - config_name: Marketing data_files: - split: dev path: Marketing/dev-* - split: validation path: Marketing/validation-* - split: test path: Marketing/test-* - config_name: Materials data_files: - split: dev path: Materials/dev-* - split: validation path: Materials/validation-* - split: test path: Materials/test-* - config_name: Math data_files: - split: dev path: Math/dev-* - split: validation path: Math/validation-* - split: test path: Math/test-* - config_name: Mechanical_Engineering data_files: - split: dev path: Mechanical_Engineering/dev-* - split: validation path: Mechanical_Engineering/validation-* - split: test path: Mechanical_Engineering/test-* - config_name: Music data_files: - split: dev path: Music/dev-* - split: validation path: Music/validation-* - split: test path: Music/test-* - config_name: Pharmacy data_files: - split: dev path: Pharmacy/dev-* - split: validation path: Pharmacy/validation-* - split: test path: Pharmacy/test-* - config_name: Physics data_files: - split: dev path: Physics/dev-* - split: validation path: Physics/validation-* - split: test path: Physics/test-* - config_name: Psychology data_files: - split: dev path: Psychology/dev-* - split: validation path: Psychology/validation-* - split: test path: Psychology/test-* - config_name: Public_Health data_files: - split: dev path: Public_Health/dev-* - split: validation path: Public_Health/validation-* - split: test path: Public_Health/test-* - config_name: Sociology data_files: - split: dev path: Sociology/dev-* - split: validation path: Sociology/validation-* - split: test path: Sociology/test-* tags: - biology - medical - finance - chemistry - music - art - art_theory - design - music - business - accounting - economics - finance - manage - marketing - health - medicine - basic_medical_science - clinical - pharmacy - public_health - humanities - social_science - history - literature - sociology - psychology - science - biology - chemistry - geography - math - physics - engineering - agriculture - architecture - computer_science - electronics - energy_and_power - materials - mechanical_engineering --- # MMMU (A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI) [**🌐 Homepage**](https://mmmu-benchmark.github.io/) | [**🏆 Leaderboard**](https://mmmu-benchmark.github.io/#leaderboard) | [**🤗 Dataset**](https://huggingface.co/datasets/MMMU/MMMU/) | [**🤗 Paper**](https://huggingface.co/papers/2311.16502) | [**📖 arXiv**](https://arxiv.org/abs/2311.16502) | [**GitHub**](https://github.com/MMMU-Benchmark/MMMU) ## 🔔News - **🛠️[2024-05-30]: Fixed duplicate option issues in Materials dataset items (validation_Materials_25; test_Materials_17, 242) and content error in validation_Materials_25.** - **🛠️[2024-04-30]: Fixed missing "-" or "^" signs in Math dataset items (dev_Math_2, validation_Math_11, 12, 16; test_Math_8, 23, 43, 113, 164, 223, 236, 287, 329, 402, 498) and corrected option errors in validation_Math_2. If you encounter any issues with the dataset, please contact us promptly!** - **🚀[2024-01-31]: We added Human Expert performance on the [Leaderboard](https://mmmu-benchmark.github.io/#leaderboard)!🌟** - **🔥[2023-12-04]: Our evaluation server for test set is now availble on [EvalAI](https://eval.ai/web/challenges/challenge-page/2179/overview). We welcome all submissions and look forward to your participation! 😆** ## Dataset Details ### Dataset Description We introduce MMMU: a new benchmark designed to evaluate multimodal models on massive multi-discipline tasks demanding college-level subject knowledge and deliberate reasoning. MMMU includes **11.5K meticulously collected multimodal questions** from college exams, quizzes, and textbooks, covering six core disciplines: Art & Design, Business, Science, Health & Medicine, Humanities & Social Science, and Tech & Engineering. These questions span **30 subjects** and **183 subfields**, comprising **30 highly heterogeneous image types**, such as charts, diagrams, maps, tables, music sheets, and chemical structures. We believe MMMU will stimulate the community to build next-generation multimodal foundation models towards expert artificial general intelligence (AGI). 🎯 **We have released a full set comprising 150 development samples and 900 validation samples. We have released 10,500 test questions without their answers.** The development set is used for few-shot/in-context learning, and the validation set is used for debugging models, selecting hyperparameters, or quick evaluations. The answers and explanations for the test set questions are withheld. You can submit your model's predictions for the **test set** on **[EvalAI](https://eval.ai/web/challenges/challenge-page/2179/overview)**. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6230d750d93e84e233882dbc/2Ulh9yznm1dvISV4xJ_Ok.png) ### Dataset Creation MMMU was created to challenge multimodal models with tasks that demand college-level subject knowledge and deliberate reasoning, pushing the boundaries of what these models can achieve in terms of expert-level perception and reasoning. The data for the MMMU dataset was manually collected by a team of college students from various disciplines, using online sources, textbooks, and lecture materials. - **Content:** The dataset contains 11.5K college-level problems across six broad disciplines (Art & Design, Business, Science, Health & Medicine, Humanities & Social Science, Tech & Engineering) and 30 college subjects. - **Image Types:** The dataset includes 30 highly heterogeneous image types, such as charts, diagrams, maps, tables, music sheets, and chemical structures, interleaved with text. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6230d750d93e84e233882dbc/Mbf8O5lEH8I8czprch0AG.png) ## 🏆 Mini-Leaderboard We show a mini-leaderboard here and please find more information in our paper or [**homepage**](https://mmmu-benchmark.github.io/). | Model | Val (900) | Test (10.5K) | |--------------------------------|:---------:|:------------:| | Expert (Best) | 88.6 | - | | Expert (Medium) | 82.6 | - | | Expert (Worst) | 76.2 | - | | GPT-4o* | **69.1** | - | | Gemini 1.5 Pro* | 62.2 | - | | InternVL2-Pro* | 62.0 | **55.7** | | Gemini 1.0 Ultra* | 59.4 | - | | Claude 3 Opus* | 59.4 | - | | GPT-4V(ision) (Playground) | 56.8 | **55.7** | | Reka Core* | 56.3 | - | | Gemini 1.5 Flash* | 56.1 | - | | SenseChat-Vision-0423-Preview* | 54.6 | 50.3 | | Reka Flash* | 53.3 | - | | Claude 3 Sonnet* | 53.1 | - | | HPT Pro* | 52.0 | - | | VILA1.5* | 51.9 | 46.9 | | Qwen-VL-MAX* | 51.4 | 46.8 | | InternVL-Chat-V1.2* | 51.6 | 46.2 | | Skywork-VL* | 51.4 | 46.2 | | LLaVA-1.6-34B* | 51.1 | 44.7 | | Claude 3 Haiku* | 50.2 | - | | Adept Fuyu-Heavy* | 48.3 | - | | Gemini 1.0 Pro* | 47.9 | - | | Marco-VL-Plus* | 46.2 | 44.3 | | Yi-VL-34B* | 45.9 | 41.6 | | Qwen-VL-PLUS* | 45.2 | 40.8 | | HPT Air* | 44.0 | - | | Reka Edge* | 42.8 | - | | Marco-VL* | 41.2 | 40.4 | | OmniLMM-12B* | 41.1 | 40.4 | | Bunny-8B* | 43.3 | 39.0 | | Bunny-4B* | 41.4 | 38.4 | | Weitu-VL-1.0-15B* | - | 38.4 | | InternLM-XComposer2-VL* | 43.0 | 38.2 | | Yi-VL-6B* | 39.1 | 37.8 | | InfiMM-Zephyr-7B* | 39.4 | 35.5 | | InternVL-Chat-V1.1* | 39.1 | 35.3 | | Math-LLaVA-13B* | 38.3 | 34.6 | | SVIT* | 38.0 | 34.1 | | MiniCPM-V* | 37.2 | 34.1 | | MiniCPM-V-2* | 37.1 | - | | Emu2-Chat* | 36.3 | 34.1 | | BLIP-2 FLAN-T5-XXL | 35.4 | 34.0 | | InstructBLIP-T5-XXL | 35.7 | 33.8 | | LLaVA-1.5-13B | 36.4 | 33.6 | | Bunny-3B* | 38.2 | 33.0 | | Qwen-VL-7B-Chat | 35.9 | 32.9 | | SPHINX* | 32.9 | 32.9 | | mPLUG-OWL2* | 32.7 | 32.1 | | BLIP-2 FLAN-T5-XL | 34.4 | 31.0 | | InstructBLIP-T5-XL | 32.9 | 30.6 | | Gemini Nano2* | 32.6 | - | | CogVLM | 32.1 | 30.1 | | Otter | 32.2 | 29.1 | | LLaMA-Adapter2-7B | 29.8 | 27.7 | | MiniGPT4-Vicuna-13B | 26.8 | 27.6 | | Adept Fuyu-8B | 27.9 | 27.4 | | Kosmos2 | 24.4 | 26.6 | | OpenFlamingo2-9B | 28.7 | 26.3 | | Frequent Choice | 22.1 | 23.9 | | Random Choice | 26.8 | 25.8 | *: results provided by the authors. ## Limitations Despite its comprehensive nature, MMMU, like any benchmark, is not without limitations. The manual curation process, albeit thorough, may carry biases. And the focus on college-level subjects might not fully be a sufficient test for Expert AGI. However, we believe it should be necessary for an Expert AGI to achieve strong performance on MMMU to demonstrate their broad and deep subject knowledge as well as expert-level understanding and reasoning capabilities. In future work, we plan to incorporate human evaluations into MMMU. This will provide a more grounded comparison between model capabilities and expert performance, shedding light on the proximity of current AI systems to achieving Expert AGI. ## Disclaimers The guidelines for the annotators emphasized strict compliance with copyright and licensing rules from the initial data source, specifically avoiding materials from websites that forbid copying and redistribution. Should you encounter any data samples potentially breaching the copyright or licensing regulations of any site, we encourage you to notify us. Upon verification, such samples will be promptly removed. ## Contact - Xiang Yue: [email protected] - Yu Su: [email protected] - Wenhu Chen: [email protected] ## Citation **BibTeX:** ```bibtex @inproceedings{yue2023mmmu, title={MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI}, author={Xiang Yue and Yuansheng Ni and Kai Zhang and Tianyu Zheng and Ruoqi Liu and Ge Zhang and Samuel Stevens and Dongfu Jiang and Weiming Ren and Yuxuan Sun and Cong Wei and Botao Yu and Ruibin Yuan and Renliang Sun and Ming Yin and Boyuan Zheng and Zhenzhu Yang and Yibo Liu and Wenhao Huang and Huan Sun and Yu Su and Wenhu Chen}, booktitle={Proceedings of CVPR}, year={2024}, } ```

sggetao/PwC

sggetao

"2024-03-30T20:03:44Z"

17,618

3

[ "license:apache-2.0", "size_categories:100K<n<1M", "format:json", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]

null

"2024-03-30T20:01:08Z"

--- license: apache-2.0 ---

alvations/c4p0-x1-en-es

alvations

"2024-03-24T03:55:08Z"

17,528

0

[ "size_categories:n<1K", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]

null

"2024-03-23T10:03:20Z"

--- dataset_info: features: - name: source dtype: string - name: target dtype: string - name: target_backto_source dtype: string - name: raw_target list: - name: generated_text dtype: string - name: raw_target_backto_source list: - name: generated_text dtype: string - name: prompt dtype: string - name: reverse_prompt dtype: string - name: source_langid dtype: string - name: target_langid dtype: string - name: target_backto_source_langid dtype: string - name: doc_id dtype: int64 - name: sent_id dtype: int64 - name: timestamp dtype: string - name: url dtype: string - name: doc_hash dtype: string splits: - name: train num_bytes: 2308 num_examples: 2 download_size: 15489 dataset_size: 2308 configs: - config_name: default data_files: - split: train path: 1f24f16745a166b0/train-* ---

weizhiwang/Open-Qwen2VL-Data

weizhiwang

"2025-04-03T02:23:45Z"

17,528

9

[ "task_categories:image-text-to-text", "size_categories:10M<n<100M", "format:parquet", "modality:image", "modality:tabular", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "arxiv:2504.00595", "region:us" ]

[ "image-text-to-text" ]

"2024-09-27T06:48:06Z"

--- task_categories: - image-text-to-text --- This repository contains the data for [Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources](https://huggingface.co/papers/2504.00595). Project page: https://victorwz.github.io/Open-Qwen2VL Code: https://github.com/Victorwz/Open-Qwen2VL

lmms-lab/GQA

lmms-lab

"2024-03-08T05:02:22Z"

17,310

14

[ "license:mit", "size_categories:10M<n<100M", "format:parquet", "modality:image", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]

null

"2023-12-26T13:11:16Z"

--- license: mit dataset_info: - config_name: challenge_all_images features: - name: id dtype: string - name: image dtype: image splits: - name: challenge num_bytes: 261636425.25 num_examples: 1590 download_size: 261271928 dataset_size: 261636425.25 - config_name: challenge_all_instructions features: - name: id dtype: string - name: imageId dtype: string - name: question dtype: string - name: isBalanced dtype: bool splits: - name: challenge num_bytes: 50797705 num_examples: 713449 download_size: 19869828 dataset_size: 50797705 - config_name: challenge_balanced_images features: - name: id dtype: string - name: image dtype: image splits: - name: challenge num_bytes: 261636425.25 num_examples: 1590 download_size: 261333538 dataset_size: 261636425.25 - config_name: challenge_balanced_instructions features: - name: id dtype: string - name: imageId dtype: string - name: question dtype: string - name: isBalanced dtype: bool splits: - name: challenge num_bytes: 3523973 num_examples: 50726 download_size: 1787024 dataset_size: 3523973 - config_name: submission_all_images features: - name: id dtype: string - name: image dtype: image splits: - name: submission num_bytes: 2314978438.875 num_examples: 15545 download_size: 2309217874 dataset_size: 2314978438.875 - config_name: submission_all_instructions features: - name: id dtype: string - name: imageId dtype: string - name: question dtype: string - name: isBalanced dtype: bool splits: - name: submission num_bytes: 298875520 num_examples: 4237524 download_size: 121458425 dataset_size: 298875520 - config_name: test_all_images features: - name: id dtype: string - name: image dtype: image splits: - name: test num_bytes: 492571840.875 num_examples: 2993 download_size: 491611526 dataset_size: 492571840.875 - config_name: test_all_instructions features: - name: id dtype: string - name: imageId dtype: string - name: question dtype: string - name: isBalanced dtype: bool splits: - name: test num_bytes: 95588974 num_examples: 1340048 download_size: 39561711 dataset_size: 95588974 - config_name: test_balanced_images features: - name: id dtype: string - name: image dtype: image splits: - name: test num_bytes: 491210370.625 num_examples: 2987 download_size: 490293506 dataset_size: 491210370.625 - config_name: test_balanced_instructions features: - name: id dtype: string - name: imageId dtype: string - name: question dtype: string - name: isBalanced dtype: bool splits: - name: test num_bytes: 6622775 num_examples: 95336 download_size: 3401070 dataset_size: 6622775 - config_name: testdev_all_images features: - name: id dtype: string - name: image dtype: image splits: - name: testdev num_bytes: 65779269.0 num_examples: 398 download_size: 65670255 dataset_size: 65779269.0 - config_name: testdev_all_instructions features: - name: id dtype: string - name: imageId dtype: string - name: question dtype: string - name: answer dtype: string - name: fullAnswer dtype: string - name: isBalanced dtype: bool - name: groups struct: - name: global dtype: string - name: local dtype: string - name: entailed dtype: string - name: equivalent dtype: string - name: types struct: - name: structural dtype: string - name: semantic dtype: string - name: detailed dtype: string - name: annotations sequence: - name: question struct: - name: objectId dtype: string - name: value dtype: string - name: answer struct: - name: objectId dtype: string - name: value dtype: string - name: fullAnswer struct: - name: objectId dtype: string - name: value dtype: string - name: semantic list: - name: operation dtype: string - name: argument dtype: string - name: dependencies sequence: int32 - name: semanticStr dtype: string splits: - name: testdev num_bytes: 86970760 num_examples: 172174 download_size: 23385535 dataset_size: 86970760 - config_name: testdev_balanced_images features: - name: id dtype: string - name: image dtype: image splits: - name: testdev num_bytes: 65779269.0 num_examples: 398 download_size: 65647745 dataset_size: 65779269.0 - config_name: testdev_balanced_instructions features: - name: id dtype: string - name: imageId dtype: string - name: question dtype: string - name: answer dtype: string - name: fullAnswer dtype: string - name: isBalanced dtype: bool - name: groups struct: - name: global dtype: string - name: local dtype: string - name: entailed dtype: string - name: equivalent dtype: string - name: types struct: - name: structural dtype: string - name: semantic dtype: string - name: detailed dtype: string - name: annotations sequence: - name: question struct: - name: objectId dtype: string - name: value dtype: string - name: answer struct: - name: objectId dtype: string - name: value dtype: string - name: fullAnswer struct: - name: objectId dtype: string - name: value dtype: string - name: semantic list: - name: operation dtype: string - name: argument dtype: string - name: dependencies sequence: int32 - name: semanticStr dtype: string splits: - name: testdev num_bytes: 6113469 num_examples: 12578 download_size: 2090335 dataset_size: 6113469 - config_name: train_all_images features: - name: id dtype: string - name: image dtype: image splits: - name: train num_bytes: 10509758457.0 num_examples: 74256 download_size: 10480239090 dataset_size: 10509758457.0 - config_name: train_all_instructions features: - name: id dtype: string - name: imageId dtype: string - name: question dtype: string - name: answer dtype: string - name: fullAnswer dtype: string - name: isBalanced dtype: bool - name: groups struct: - name: global dtype: string - name: local dtype: string - name: entailed dtype: string - name: equivalent dtype: string - name: types struct: - name: structural dtype: string - name: semantic dtype: string - name: detailed dtype: string - name: annotations sequence: - name: question struct: - name: objectId dtype: string - name: value dtype: string - name: answer struct: - name: objectId dtype: string - name: value dtype: string - name: fullAnswer struct: - name: objectId dtype: string - name: value dtype: string - name: semantic list: - name: operation dtype: string - name: argument dtype: string - name: dependencies sequence: int32 - name: semanticStr dtype: string splits: - name: train num_bytes: 6891129609 num_examples: 14305356 download_size: 1874173198 dataset_size: 6891129609 - config_name: train_balanced_images features: - name: id dtype: string - name: image dtype: image splits: - name: train num_bytes: 10200292415.5 num_examples: 72140 download_size: 10171627271 dataset_size: 10200292415.5 - config_name: train_balanced_instructions features: - name: id dtype: string - name: imageId dtype: string - name: question dtype: string - name: answer dtype: string - name: fullAnswer dtype: string - name: isBalanced dtype: bool - name: groups struct: - name: global dtype: string - name: local dtype: string - name: entailed dtype: string - name: equivalent dtype: string - name: types struct: - name: structural dtype: string - name: semantic dtype: string - name: detailed dtype: string - name: annotations sequence: - name: question struct: - name: objectId dtype: string - name: value dtype: string - name: answer struct: - name: objectId dtype: string - name: value dtype: string - name: fullAnswer struct: - name: objectId dtype: string - name: value dtype: string - name: semantic list: - name: operation dtype: string - name: argument dtype: string - name: dependencies sequence: int32 - name: semanticStr dtype: string splits: - name: train num_bytes: 460429581 num_examples: 943000 download_size: 183979778 dataset_size: 460429581 - config_name: val_all_images features: - name: id dtype: string - name: image dtype: image splits: - name: val num_bytes: 1494990904.5 num_examples: 10564 download_size: 1490744689 dataset_size: 1494990904.5 - config_name: val_all_instructions features: - name: id dtype: string - name: imageId dtype: string - name: question dtype: string - name: answer dtype: string - name: fullAnswer dtype: string - name: isBalanced dtype: bool - name: groups struct: - name: global dtype: string - name: local dtype: string - name: entailed dtype: string - name: equivalent dtype: string - name: types struct: - name: structural dtype: string - name: semantic dtype: string - name: detailed dtype: string - name: annotations sequence: - name: question struct: - name: objectId dtype: string - name: value dtype: string - name: answer struct: - name: objectId dtype: string - name: value dtype: string - name: fullAnswer struct: - name: objectId dtype: string - name: value dtype: string - name: semantic list: - name: operation dtype: string - name: argument dtype: string - name: dependencies sequence: int32 - name: semanticStr dtype: string splits: - name: val num_bytes: 967338322 num_examples: 2011853 download_size: 266476025 dataset_size: 967338322 - config_name: val_balanced_images features: - name: id dtype: string - name: image dtype: image splits: - name: val num_bytes: 1447074448.75 num_examples: 10234 download_size: 1443033919 dataset_size: 1447074448.75 - config_name: val_balanced_instructions features: - name: id dtype: string - name: imageId dtype: string - name: question dtype: string - name: answer dtype: string - name: fullAnswer dtype: string - name: isBalanced dtype: bool - name: groups struct: - name: global dtype: string - name: local dtype: string - name: entailed dtype: string - name: equivalent dtype: string - name: types struct: - name: structural dtype: string - name: semantic dtype: string - name: detailed dtype: string - name: annotations sequence: - name: question struct: - name: objectId dtype: string - name: value dtype: string - name: answer struct: - name: objectId dtype: string - name: value dtype: string - name: fullAnswer struct: - name: objectId dtype: string - name: value dtype: string - name: semantic list: - name: operation dtype: string - name: argument dtype: string - name: dependencies sequence: int32 - name: semanticStr dtype: string splits: - name: val num_bytes: 64498952 num_examples: 132062 download_size: 25794272 dataset_size: 64498952 configs: - config_name: challenge_all_images data_files: - split: challenge path: challenge_all_images/challenge-* - config_name: challenge_all_instructions data_files: - split: challenge path: challenge_all_instructions/challenge-* - config_name: challenge_balanced_images data_files: - split: challenge path: challenge_balanced_images/challenge-* - config_name: challenge_balanced_instructions data_files: - split: challenge path: challenge_balanced_instructions/challenge-* - config_name: submission_all_images data_files: - split: submission path: submission_all_images/submission-* - config_name: submission_all_instructions data_files: - split: submission path: submission_all_instructions/submission-* - config_name: test_all_images data_files: - split: test path: test_all_images/test-* - config_name: test_all_instructions data_files: - split: test path: test_all_instructions/test-* - config_name: test_balanced_images data_files: - split: test path: test_balanced_images/test-* - config_name: test_balanced_instructions data_files: - split: test path: test_balanced_instructions/test-* - config_name: testdev_all_images data_files: - split: testdev path: testdev_all_images/testdev-* - config_name: testdev_all_instructions data_files: - split: testdev path: testdev_all_instructions/testdev-* - config_name: testdev_balanced_images data_files: - split: testdev path: testdev_balanced_images/testdev-* - config_name: testdev_balanced_instructions data_files: - split: testdev path: testdev_balanced_instructions/testdev-* - config_name: train_all_images data_files: - split: train path: train_all_images/train-* - config_name: train_all_instructions data_files: - split: train path: train_all_instructions/train-* - config_name: train_balanced_images data_files: - split: train path: train_balanced_images/train-* - config_name: train_balanced_instructions data_files: - split: train path: train_balanced_instructions/train-* - config_name: val_all_images data_files: - split: val path: val_all_images/val-* - config_name: val_all_instructions data_files: - split: val path: val_all_instructions/val-* - config_name: val_balanced_images data_files: - split: val path: val_balanced_images/val-* - config_name: val_balanced_instructions data_files: - split: val path: val_balanced_instructions/val-* --- <p align="center" width="100%"> <img src="https://i.postimg.cc/g0QRgMVv/WX20240228-113337-2x.png" width="100%" height="80%"> </p> # Large-scale Multi-modality Models Evaluation Suite > Accelerating the development of large-scale multi-modality models (LMMs) with `lmms-eval` 🏠 [Homepage](https://lmms-lab.github.io/) | 📚 [Documentation](docs/README.md) | 🤗 [Huggingface Datasets](https://huggingface.co/lmms-lab) # This Dataset This is a formatted version of [GQA](hhttps://cs.stanford.edu/people/dorarad/gqa/about.html). It is used in our `lmms-eval` pipeline to allow for one-click evaluations of large multi-modality models. ``` @inproceedings{hudson2019gqa, title={Gqa: A new dataset for real-world visual reasoning and compositional question answering}, author={Hudson, Drew A and Manning, Christopher D}, booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition}, pages={6700--6709}, year={2019} } ```

facebook/xnli

facebook

"2024-01-05T08:30:52Z"

17,244

56

[ "language:ar", "language:bg", "language:de", "language:el", "language:en", "language:es", "language:fr", "language:hi", "language:ru", "language:sw", "language:th", "language:tr", "language:ur", "language:vi", "language:zh", "size_categories:1M<n<10M", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]

null

"2022-03-02T23:29:22Z"

--- language: - ar - bg - de - el - en - es - fr - hi - ru - sw - th - tr - ur - vi - zh paperswithcode_id: xnli pretty_name: Cross-lingual Natural Language Inference dataset_info: - config_name: all_languages features: - name: premise dtype: translation: languages: - ar - bg - de - el - en - es - fr - hi - ru - sw - th - tr - ur - vi - zh - name: hypothesis dtype: translation_variable_languages: languages: - ar - bg - de - el - en - es - fr - hi - ru - sw - th - tr - ur - vi - zh num_languages: 15 - name: label dtype: class_label: names: '0': entailment '1': neutral '2': contradiction splits: - name: train num_bytes: 1581471691 num_examples: 392702 - name: test num_bytes: 19387432 num_examples: 5010 - name: validation num_bytes: 9566179 num_examples: 2490 download_size: 963942271 dataset_size: 1610425302 - config_name: ar features: - name: premise dtype: string - name: hypothesis dtype: string - name: label dtype: class_label: names: '0': entailment '1': neutral '2': contradiction splits: - name: train num_bytes: 107399614 num_examples: 392702 - name: test num_bytes: 1294553 num_examples: 5010 - name: validation num_bytes: 633001 num_examples: 2490 download_size: 59215902 dataset_size: 109327168 - config_name: bg features: - name: premise dtype: string - name: hypothesis dtype: string - name: label dtype: class_label: names: '0': entailment '1': neutral '2': contradiction splits: - name: train num_bytes: 125973225 num_examples: 392702 - name: test num_bytes: 1573034 num_examples: 5010 - name: validation num_bytes: 774061 num_examples: 2490 download_size: 66117878 dataset_size: 128320320 - config_name: de features: - name: premise dtype: string - name: hypothesis dtype: string - name: label dtype: class_label: names: '0': entailment '1': neutral '2': contradiction splits: - name: train num_bytes: 84684140 num_examples: 392702 - name: test num_bytes: 996488 num_examples: 5010 - name: validation num_bytes: 494604 num_examples: 2490 download_size: 55973883 dataset_size: 86175232 - config_name: el features: - name: premise dtype: string - name: hypothesis dtype: string - name: label dtype: class_label: names: '0': entailment '1': neutral '2': contradiction splits: - name: train num_bytes: 139753358 num_examples: 392702 - name: test num_bytes: 1704785 num_examples: 5010 - name: validation num_bytes: 841226 num_examples: 2490 download_size: 74551247 dataset_size: 142299369 - config_name: en features: - name: premise dtype: string - name: hypothesis dtype: string - name: label dtype: class_label: names: '0': entailment '1': neutral '2': contradiction splits: - name: train num_bytes: 74444026 num_examples: 392702 - name: test num_bytes: 875134 num_examples: 5010 - name: validation num_bytes: 433463 num_examples: 2490 download_size: 50627367 dataset_size: 75752623 - config_name: es features: - name: premise dtype: string - name: hypothesis dtype: string - name: label dtype: class_label: names: '0': entailment '1': neutral '2': contradiction splits: - name: train num_bytes: 81383284 num_examples: 392702 - name: test num_bytes: 969813 num_examples: 5010 - name: validation num_bytes: 478422 num_examples: 2490 download_size: 53677157 dataset_size: 82831519 - config_name: fr features: - name: premise dtype: string - name: hypothesis dtype: string - name: label dtype: class_label: names: '0': entailment '1': neutral '2': contradiction splits: - name: train num_bytes: 85808779 num_examples: 392702 - name: test num_bytes: 1029239 num_examples: 5010 - name: validation num_bytes: 510104 num_examples: 2490 download_size: 55968680 dataset_size: 87348122 - config_name: hi features: - name: premise dtype: string - name: hypothesis dtype: string - name: label dtype: class_label: names: '0': entailment '1': neutral '2': contradiction splits: - name: train num_bytes: 170593964 num_examples: 392702 - name: test num_bytes: 2073073 num_examples: 5010 - name: validation num_bytes: 1023915 num_examples: 2490 download_size: 70908548 dataset_size: 173690952 - config_name: ru features: - name: premise dtype: string - name: hypothesis dtype: string - name: label dtype: class_label: names: '0': entailment '1': neutral '2': contradiction splits: - name: train num_bytes: 129859615 num_examples: 392702 - name: test num_bytes: 1603466 num_examples: 5010 - name: validation num_bytes: 786442 num_examples: 2490 download_size: 70702606 dataset_size: 132249523 - config_name: sw features: - name: premise dtype: string - name: hypothesis dtype: string - name: label dtype: class_label: names: '0': entailment '1': neutral '2': contradiction splits: - name: train num_bytes: 69285725 num_examples: 392702 - name: test num_bytes: 871651 num_examples: 5010 - name: validation num_bytes: 429850 num_examples: 2490 download_size: 45564152 dataset_size: 70587226 - config_name: th features: - name: premise dtype: string - name: hypothesis dtype: string - name: label dtype: class_label: names: '0': entailment '1': neutral '2': contradiction splits: - name: train num_bytes: 176062892 num_examples: 392702 - name: test num_bytes: 2147015 num_examples: 5010 - name: validation num_bytes: 1061160 num_examples: 2490 download_size: 77222045 dataset_size: 179271067 - config_name: tr features: - name: premise dtype: string - name: hypothesis dtype: string - name: label dtype: class_label: names: '0': entailment '1': neutral '2': contradiction splits: - name: train num_bytes: 71637140 num_examples: 392702 - name: test num_bytes: 934934 num_examples: 5010 - name: validation num_bytes: 459308 num_examples: 2490 download_size: 48509680 dataset_size: 73031382 - config_name: ur features: - name: premise dtype: string - name: hypothesis dtype: string - name: label dtype: class_label: names: '0': entailment '1': neutral '2': contradiction splits: - name: train num_bytes: 96441486 num_examples: 392702 - name: test num_bytes: 1416241 num_examples: 5010 - name: validation num_bytes: 699952 num_examples: 2490 download_size: 46682785 dataset_size: 98557679 - config_name: vi features: - name: premise dtype: string - name: hypothesis dtype: string - name: label dtype: class_label: names: '0': entailment '1': neutral '2': contradiction splits: - name: train num_bytes: 101417430 num_examples: 392702 - name: test num_bytes: 1190217 num_examples: 5010 - name: validation num_bytes: 590680 num_examples: 2490 download_size: 57690058 dataset_size: 103198327 - config_name: zh features: - name: premise dtype: string - name: hypothesis dtype: string - name: label dtype: class_label: names: '0': entailment '1': neutral '2': contradiction splits: - name: train num_bytes: 72224841 num_examples: 392702 - name: test num_bytes: 777929 num_examples: 5010 - name: validation num_bytes: 384851 num_examples: 2490 download_size: 48269855 dataset_size: 73387621 configs: - config_name: all_languages data_files: - split: train path: all_languages/train-* - split: test path: all_languages/test-* - split: validation path: all_languages/validation-* - config_name: ar data_files: - split: train path: ar/train-* - split: test path: ar/test-* - split: validation path: ar/validation-* - config_name: bg data_files: - split: train path: bg/train-* - split: test path: bg/test-* - split: validation path: bg/validation-* - config_name: de data_files: - split: train path: de/train-* - split: test path: de/test-* - split: validation path: de/validation-* - config_name: el data_files: - split: train path: el/train-* - split: test path: el/test-* - split: validation path: el/validation-* - config_name: en data_files: - split: train path: en/train-* - split: test path: en/test-* - split: validation path: en/validation-* - config_name: es data_files: - split: train path: es/train-* - split: test path: es/test-* - split: validation path: es/validation-* - config_name: fr data_files: - split: train path: fr/train-* - split: test path: fr/test-* - split: validation path: fr/validation-* - config_name: hi data_files: - split: train path: hi/train-* - split: test path: hi/test-* - split: validation path: hi/validation-* - config_name: ru data_files: - split: train path: ru/train-* - split: test path: ru/test-* - split: validation path: ru/validation-* - config_name: sw data_files: - split: train path: sw/train-* - split: test path: sw/test-* - split: validation path: sw/validation-* - config_name: th data_files: - split: train path: th/train-* - split: test path: th/test-* - split: validation path: th/validation-* - config_name: tr data_files: - split: train path: tr/train-* - split: test path: tr/test-* - split: validation path: tr/validation-* - config_name: ur data_files: - split: train path: ur/train-* - split: test path: ur/test-* - split: validation path: ur/validation-* - config_name: vi data_files: - split: train path: vi/train-* - split: test path: vi/test-* - split: validation path: vi/validation-* - config_name: zh data_files: - split: train path: zh/train-* - split: test path: zh/test-* - split: validation path: zh/validation-* --- # Dataset Card for "xnli" ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Homepage:** [https://www.nyu.edu/projects/bowman/xnli/](https://www.nyu.edu/projects/bowman/xnli/) - **Repository:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - **Paper:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - **Point of Contact:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - **Size of downloaded dataset files:** 7.74 GB - **Size of the generated dataset:** 3.23 GB - **Total amount of disk used:** 10.97 GB ### Dataset Summary XNLI is a subset of a few thousand examples from MNLI which has been translated into a 14 different languages (some low-ish resource). As with MNLI, the goal is to predict textual entailment (does sentence A imply/contradict/neither sentence B) and is a classification task (given two sentences, predict one of three labels). ### Supported Tasks and Leaderboards [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Languages [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Dataset Structure ### Data Instances #### all_languages - **Size of downloaded dataset files:** 483.96 MB - **Size of the generated dataset:** 1.61 GB - **Total amount of disk used:** 2.09 GB An example of 'train' looks as follows. ``` This example was too long and was cropped: { "hypothesis": "{\"language\": [\"ar\", \"bg\", \"de\", \"el\", \"en\", \"es\", \"fr\", \"hi\", \"ru\", \"sw\", \"th\", \"tr\", \"ur\", \"vi\", \"zh\"], \"translation\": [\"احد اع...", "label": 0, "premise": "{\"ar\": \"واحدة من رقابنا ستقوم بتنفيذ تعليماتك كلها بكل دقة\", \"bg\": \"един от нашите номера ще ви даде инструкции .\", \"de\": \"Eine ..." } ``` #### ar - **Size of downloaded dataset files:** 483.96 MB - **Size of the generated dataset:** 109.32 MB - **Total amount of disk used:** 593.29 MB An example of 'validation' looks as follows. ``` { "hypothesis": "اتصل بأمه حالما أوصلته حافلة المدرسية.", "label": 1, "premise": "وقال، ماما، لقد عدت للمنزل." } ``` #### bg - **Size of downloaded dataset files:** 483.96 MB - **Size of the generated dataset:** 128.32 MB - **Total amount of disk used:** 612.28 MB An example of 'train' looks as follows. ``` This example was too long and was cropped: { "hypothesis": "\"губиш нещата на следното ниво , ако хората си припомнят .\"...", "label": 0, "premise": "\"по време на сезона и предполагам , че на твоето ниво ще ги загубиш на следващото ниво , ако те решат да си припомнят отбора на ..." } ``` #### de - **Size of downloaded dataset files:** 483.96 MB - **Size of the generated dataset:** 86.17 MB - **Total amount of disk used:** 570.14 MB An example of 'train' looks as follows. ``` This example was too long and was cropped: { "hypothesis": "Man verliert die Dinge auf die folgende Ebene , wenn sich die Leute erinnern .", "label": 0, "premise": "\"Du weißt , während der Saison und ich schätze , auf deiner Ebene verlierst du sie auf die nächste Ebene , wenn sie sich entschl..." } ``` #### el - **Size of downloaded dataset files:** 483.96 MB - **Size of the generated dataset:** 142.30 MB - **Total amount of disk used:** 626.26 MB An example of 'validation' looks as follows. ``` This example was too long and was cropped: { "hypothesis": "\"Τηλεφώνησε στη μαμά του μόλις το σχολικό λεωφορείο τον άφησε.\"...", "label": 1, "premise": "Και είπε, Μαμά, έφτασα στο σπίτι." } ``` ### Data Fields The data fields are the same among all splits. #### all_languages - `premise`: a multilingual `string` variable, with possible languages including `ar`, `bg`, `de`, `el`, `en`. - `hypothesis`: a multilingual `string` variable, with possible languages including `ar`, `bg`, `de`, `el`, `en`. - `label`: a classification label, with possible values including `entailment` (0), `neutral` (1), `contradiction` (2). #### ar - `premise`: a `string` feature. - `hypothesis`: a `string` feature. - `label`: a classification label, with possible values including `entailment` (0), `neutral` (1), `contradiction` (2). #### bg - `premise`: a `string` feature. - `hypothesis`: a `string` feature. - `label`: a classification label, with possible values including `entailment` (0), `neutral` (1), `contradiction` (2). #### de - `premise`: a `string` feature. - `hypothesis`: a `string` feature. - `label`: a classification label, with possible values including `entailment` (0), `neutral` (1), `contradiction` (2). #### el - `premise`: a `string` feature. - `hypothesis`: a `string` feature. - `label`: a classification label, with possible values including `entailment` (0), `neutral` (1), `contradiction` (2). ### Data Splits | name |train |validation|test| |-------------|-----:|---------:|---:| |all_languages|392702| 2490|5010| |ar |392702| 2490|5010| |bg |392702| 2490|5010| |de |392702| 2490|5010| |el |392702| 2490|5010| ## Dataset Creation ### Curation Rationale [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Source Data #### Initial Data Collection and Normalization [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the source language producers? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Annotations #### Annotation process [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the annotators? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Personal and Sensitive Information [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Discussion of Biases [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Other Known Limitations [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Additional Information ### Dataset Curators [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Licensing Information [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Citation Information ``` @InProceedings{conneau2018xnli, author = {Conneau, Alexis and Rinott, Ruty and Lample, Guillaume and Williams, Adina and Bowman, Samuel R. and Schwenk, Holger and Stoyanov, Veselin}, title = {XNLI: Evaluating Cross-lingual Sentence Representations}, booktitle = {Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing}, year = {2018}, publisher = {Association for Computational Linguistics}, location = {Brussels, Belgium}, } ``` ### Contributions Thanks to [@lewtun](https://github.com/lewtun), [@mariamabarham](https://github.com/mariamabarham), [@thomwolf](https://github.com/thomwolf), [@lhoestq](https://github.com/lhoestq), [@patrickvonplaten](https://github.com/patrickvonplaten) for adding this dataset.

jkot/merged_preprocessed_parliament_commonvoice

jkot

"2023-05-01T13:35:28Z"

17,240

0

[ "size_categories:100K<n<1M", "format:parquet", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]

null

"2023-05-01T10:37:03Z"

--- dataset_info: features: - name: input_features sequence: sequence: float32 - name: labels sequence: int64 splits: - name: train num_bytes: 210499135424 num_examples: 219101 - name: test num_bytes: 11099630080 num_examples: 11555 download_size: 65027813279 dataset_size: 221598765504 --- # Dataset Card for "merged_preprocessed_parliament_commonvoice" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

misikoff/zillow

misikoff

"2024-03-20T22:24:59Z"

17,195

24

[ "task_categories:tabular-regression", "task_categories:time-series-forecasting", "language:en", "license:other", "region:us" ]

[ "tabular-regression", "time-series-forecasting" ]

"2024-02-16T16:36:27Z"

--- language: - en license: other task_categories: - tabular-regression - time-series-forecasting pretty_name: Zillow description: 'This dataset is comprised of seven different configurations of data covering different aspects of the housing market in the United States. All data is provided by Zillow. The seven configurations are: home_values_forecasts, new_construction, for_sale_listings, rentals, sales, home_values, and days_on_market. Each configuration has a different set of features and target variables. The data is provided in JSONL format.' homepage: https://www.zillow.com/research/data/ dataset_info: - config_name: days_on_market features: - name: Region ID dtype: string id: Region ID - name: Size Rank dtype: int32 id: Size Rank - name: Region dtype: string id: Region - name: Region Type dtype: class_label: names: '0': zip '1': city '2': county '3': msa '4': state '5': country - name: State dtype: string id: State - name: Home Type dtype: class_label: names: '0': multifamily '1': condo/co-op '2': SFR '3': all homes '4': all homes plus multifamily - name: Date dtype: timestamp[ms] id: Date - name: Mean Listings Price Cut Amount (Smoothed) dtype: float32 id: Mean Listings Price Cut Amount (Smoothed) - name: Percent Listings Price Cut dtype: float32 id: Percent Listings Price Cut - name: Mean Listings Price Cut Amount dtype: float32 id: Mean Listings Price Cut Amount - name: Percent Listings Price Cut (Smoothed) dtype: float32 id: Percent Listings Price Cut (Smoothed) - name: Median Days on Pending (Smoothed) dtype: float32 id: Median Days on Pending (Smoothed) - name: Median Days on Pending dtype: float32 id: Median Days on Pending splits: - name: train num_bytes: 50107320 num_examples: 586714 download_size: 229118598 dataset_size: 50107320 - config_name: for_sale_listings features: - name: Region ID dtype: string id: Region ID - name: Size Rank dtype: int32 id: Size Rank - name: Region dtype: string id: Region - name: Region Type dtype: class_label: names: '0': county '1': city '2': zip '3': country '4': msa - name: State dtype: string id: State - name: Home Type dtype: class_label: names: '0': all homes '1': all homes plus multifamily '2': SFR '3': condo/co-op '4': multifamily - name: Date dtype: timestamp[ms] id: Date - name: Median Listing Price dtype: float32 id: Median Listing Price - name: Median Listing Price (Smoothed) dtype: float32 id: Median Listing Price (Smoothed) - name: New Listings dtype: int32 id: New Listings - name: New Listings (Smoothed) dtype: int32 id: New Listings (Smoothed) - name: New Pending (Smoothed) dtype: int32 id: New Pending (Smoothed) - name: New Pending dtype: int32 id: New Pending splits: - name: train num_bytes: 49412198 num_examples: 578653 download_size: 180206592 dataset_size: 49412198 - config_name: home_values features: - name: Region ID dtype: string id: Region ID - name: Size Rank dtype: int32 id: Size Rank - name: Region dtype: string id: Region - name: Region Type dtype: class_label: names: '0': zip '1': city '2': county '3': msa '4': state '5': country - name: State dtype: string id: State - name: Home Type dtype: class_label: names: '0': multifamily '1': condo/co-op '2': SFR '3': all homes '4': all homes plus multifamily - name: Bedroom Count dtype: class_label: names: '0': 1-Bedroom '1': 2-Bedrooms '2': 3-Bedrooms '3': 4-Bedrooms '4': 5+-Bedrooms '5': All Bedrooms - name: Date dtype: timestamp[ms] id: Date - name: Bottom Tier ZHVI (Smoothed) (Seasonally Adjusted) dtype: float32 id: Bottom Tier ZHVI (Smoothed) (Seasonally Adjusted) - name: Mid Tier ZHVI (Smoothed) (Seasonally Adjusted) dtype: float32 id: Mid Tier ZHVI (Smoothed) (Seasonally Adjusted) - name: Top Tier ZHVI (Smoothed) (Seasonally Adjusted) dtype: float32 id: Top Tier ZHVI (Smoothed) (Seasonally Adjusted) splits: - name: train num_bytes: 9377759 num_examples: 117912 download_size: 41145800 dataset_size: 9377759 - config_name: home_values_forecasts features: - name: Region ID dtype: string id: Region ID - name: Size Rank dtype: int32 id: Size Rank - name: Region dtype: string id: Region - name: Region Type dtype: class_label: names: '0': county '1': city '2': zip '3': country '4': msa - name: State dtype: string id: State - name: City dtype: string id: City - name: Metro dtype: string id: Metro - name: County dtype: string id: County - name: Date dtype: timestamp[ms] id: Date - name: Month Over Month % (Smoothed) (Seasonally Adjusted) dtype: float32 id: Month Over Month % (Smoothed) (Seasonally Adjusted) - name: Quarter Over Quarter % (Smoothed) (Seasonally Adjusted) dtype: float32 id: Quarter Over Quarter % (Smoothed) (Seasonally Adjusted) - name: Year Over Year % (Smoothed) (Seasonally Adjusted) dtype: float32 id: Year Over Year % (Smoothed) (Seasonally Adjusted) - name: Month Over Month % dtype: float32 id: Month Over Month % - name: Quarter Over Quarter % dtype: float32 id: Quarter Over Quarter % - name: Year Over Year % dtype: float32 id: Year Over Year % splits: - name: train num_bytes: 3976869 num_examples: 31854 download_size: 14081979 dataset_size: 3976869 - config_name: new_construction features: - name: Region ID dtype: string id: Region ID - name: Size Rank dtype: int32 id: Size Rank - name: Region dtype: string id: Region - name: Region Type dtype: class_label: names: '0': county '1': city '2': zip '3': country '4': msa - name: State dtype: string id: State - name: Home Type dtype: class_label: names: '0': all homes '1': all homes plus multifamily '2': SFR '3': condo/co-op '4': multifamily - name: Date dtype: timestamp[ms] id: Date - name: Median Sale Price dtype: float32 id: Median Sale Price - name: Median Sale Price per Sqft dtype: float32 id: Sale Price per Sqft - name: Sales Count dtype: int32 id: Sales Count splits: - name: train num_bytes: 3624631 num_examples: 49487 download_size: 10937317 dataset_size: 3624631 - config_name: rentals features: - name: Region ID dtype: string id: Region ID - name: Size Rank dtype: int32 id: Size Rank - name: Region dtype: string id: Region - name: Region Type dtype: class_label: names: '0': county '1': city '2': zip '3': country '4': msa - name: State dtype: string id: State - name: Home Type dtype: class_label: names: '0': all homes '1': all homes plus multifamily '2': SFR '3': condo/co-op '4': multifamily - name: Date dtype: timestamp[ms] id: Date - name: Rent (Smoothed) dtype: float32 id: Rent (Smoothed) - name: Rent (Smoothed) (Seasonally Adjusted) dtype: float32 id: Rent (Smoothed) (Seasonally Adjusted) splits: - name: train num_bytes: 92914681 num_examples: 1258740 download_size: 447425069 dataset_size: 92914681 - config_name: sales features: - name: Region ID dtype: string id: Region ID - name: Size Rank dtype: int32 id: Size Rank - name: Region dtype: string id: Region - name: Region Type dtype: class_label: names: '0': county '1': city '2': zip '3': country '4': msa - name: State dtype: string id: State - name: Home Type dtype: class_label: names: '0': all homes '1': all homes plus multifamily '2': SFR '3': condo/co-op '4': multifamily - name: Date dtype: timestamp[ms] id: Date - name: Mean Sale to List Ratio (Smoothed) dtype: float32 id: Mean Sale to List Ratio (Smoothed) - name: Median Sale to List Ratio dtype: float32 id: Median Sale to List Ratio - name: Median Sale Price dtype: float32 id: Median Sale Price - name: Median Sale Price (Smoothed) (Seasonally Adjusted) dtype: float32 id: Median Sale Price (Smoothed) (Seasonally Adjusted) - name: Median Sale Price (Smoothed) dtype: float32 id: Median Sale Price (Smoothed) - name: Median Sale to List Ratio (Smoothed) dtype: float32 id: Median Sale to List Ratio (Smoothed) - name: '% Sold Below List' dtype: float32 id: '% Sold Below List' - name: '% Sold Below List (Smoothed)' dtype: float32 id: '% Sold Below List (Smoothed)' - name: '% Sold Above List' dtype: float32 id: '% Sold Above List' - name: '% Sold Above List (Smoothed)' dtype: float32 id: '% Sold Above List (Smoothed)' - name: Mean Sale to List Ratio dtype: float32 id: Mean Sale to List Ratio splits: - name: train num_bytes: 27088039 num_examples: 255024 download_size: 139297577 dataset_size: 27088039 --- # Housing Data Provided by Zillow Updated: 2023-02-01 This dataset contains several configs produced based on files available at https://www.zillow.com/research/data/. # Viewer Notes Because this repository includes the code used to process the raw Zillow data, the dataset viewer is not enabled. This is because the dataset viewer is not enabled for datasets that run arbitrary python code. For a normal viewer experience, please see the simplified version of this dataset at https://huggingface.co/datasets/misikoff/zillow-viewer. The viewer should be enabled there and the config files should match what is found here. Supported configs: - [`days_on_market`](#days-on-market): Days to pending, days to close, share of listings with a price cut, and price cuts. - [`for_sale_listings`](#for-sale-listings): Median listing price, new listings, and new pending listings. - [`home_values`](#home-values): Zillow Home Value Index (ZHVI) for all homes, mid-tier, bottom-tier, and top-tier homes. - [`home_values_forecasts`](#home-values-forecasts): Zillow Home Value Forecast (ZHVF) for all homes, mid-tier, bottom-tier, and top-tier homes. - [`new_construction`](#new-construction): Median sale price, median sale price per square foot, and sales count. - [`rentals`](#rentals): Zillow Observed Rent Index (ZORI) for all homes, mid-tier, bottom-tier, and top-tier homes. - [`sales`](#sales): Median sale price, median sale price per square foot, and sales count. ## DAYS ON MARKET AND PRICE CUTS Days to Pending: How long it takes homes in a region to change to pending status on Zillow.com after first being shown as for sale. The reported figure indicates the number of days (mean or median) that it took for homes that went pending during the week being reported, to go pending. This differs from the old “Days on Zillow” metric in that it excludes the in-contract period before a home sells. Days to Close (mean/median): Number of days between the listing going pending and the sale date. Share of Listings With a Price Cut: The number of unique properties with a list price at the end of the month that’s less than the list price at the beginning of the month, divided by the number of unique properties with an active listing at some point during the month. Price Cuts: The mean and median price cut for listings in a given region during a given time period, expressed as both dollars ($) and as a percentage (%) of list price. Base Columns - `Region ID`: dtype="string", a unique identifier for the region - `Size Rank`: dtype="int32", a rank of the region's size - `Region`: dtype="string", the name of the region - `Region Type`: dtype="class_label", the type of region - '0': zip - '1': city - '2': county - '3': msa - '4': state - '5': country - `State`: dtype="string", the US state abbreviation for the state containing the region - `Home Type`: dtype="string", the type of home - '0': multifamily - '1': condo/co-op - '2': SFR - '3': all homes - '4': all homes plus multifamily - `Date`: dtype="timestamp[ms]", the date of the last day of the week for this data Value Columns - `Mean Listings Price Cut Amount (Smoothed)`: dtype="float32" - `Percent Listings Price Cut`: dtype="float32", The number of unique properties with a list price at the end of the month that’s less than the list price at the beginning of the month, divided by the number of unique properties with an active listing at some point during the month. - `Mean Listings Price Cut Amount`: dtype="float32" - `Percent Listings Price Cut (Smoothed)`: dtype="float32" - `Median Days on Pending (Smoothed)`: dtype="float32", median number of days it takes for homes in a region to change to pending status on Zillow.com after first being shown as for sale. (smoothed) - `Median Days on Pending`: dtype="float32", median number of days it takes for homes in a region to change to pending status on Zillow.com after first being shown as for sale. ## FOR-SALE LISTINGS Base Columns - `Region ID`: dtype="string", a unique identifier for the region - `Size Rank`: dtype="int32", a rank of the region's size - `Region`: dtype="string", the name of the region - `Region Type`: dtype="class_label", the type of region - '0': zip - '1': city - '2': county - '3': msa - '4': state - `State`: dtype="string", the US state abbreviation for the state containing the region - `Home Type`: dtype="string", the type of home - '0': all homes - '1': all homes plus multifamily - '2': SFR - '3': condo/co-op - '4': multifamily - `Date`: dtype="timestamp[ms]", the date of the last day of the month for this data Value Columns - `Median Listing Price`: dtype="float32", The median price at which homes across various geographies were listed. - `Median Listing Price (Smoothed)`: dtype="float32", The median price at which homes across various geographies were listed. (smoothed) - `New Listings`: dtype="int32", how many new listings have come on the market in a given month - `New Listings (Smoothed)`: dtype="int32", how many new listings have come on the market in a given month. (smoothed) - `New Pending (Smoothed)`: dtype="int32", The count of listings that changed from for-sale to pending status on Zillow.com in a given time period. (smoothed) - `New Pending`: dtype="int32", The count of listings that changed from for-sale to pending status on Zillow.com in a given time period. ## HOME VALUES      Base Columns - `Region ID`: dtype="string", a unique identifier for the region - `Size Rank`: dtype="int32", a rank of the region's size - `Region`: dtype="string", the name of the region - `Region Type`: dtype="class_label", the type of region - '0': zip - '1': city - '2': county - '3': msa - '4': state - '5': country" - `State`: dtype="string", the US state abbreviation for the state containing the region - `Home Type`: dtype="class_label", the type of home - '0': multifamily - '1': condo/co-op - '2': SFR - '3': all homes - '4': all homes plus multifamily - `Bedroom Count`: dtype="class_label", the number of bedrooms - '0': 1-Bedroom - '1': 2-Bedrooms - '2': 3-Bedrooms - '3': 4-Bedrooms - '4': 5+-Bedrooms - '5': All Bedrooms - `Date`: dtype="timestamp[ms]", the date of the last day of the month for this data Value Columns - `Mid Tier ZHVI (Smoothed) (Seasonally Adjusted)`: dtype="float32", - `Bottom Tier ZHVI (Smoothed) (Seasonally Adjusted)`: dtype="float32", - `Top Tier ZHVI (Smoothed) (Seasonally Adjusted)`: dtype="float32", - `ZHVI`: dtype="float32", - `Mid Tier ZHVI`: dtype="float32" ## HOME VALUES FORECASTS   Base Columns - `Region ID`: dtype="string", a unique identifier for the region - `Size Rank`: dtype="int32", a rank of the region's size - `Region`: dtype="string", the name of the region - `Region Type`: dtype="class_label", the type of region - '0': county - '1': city - '2': zip - '3': country - '4': msa - `State`: dtype="string", the US state abbreviation for the state containing the region - `City`: dtype="string", - `Metro`: dtype="string", - `County`: dtype="string", - `Home Type`: dtype="string", the type of home - `Date`: dtype="timestamp[ms]", the date of these forecasts Value Columns - `Month Over Month % (Smoothed)`: dtype="float32", - `Quarter Over Quarter % (Smoothed)`: dtype="float32", - `Year Over Year % (Smoothed)`: dtype="float32" - `Month Over Month % (Raw)`: dtype="float32" - `Quarter Over Quarter % (Raw)`: dtype="float32" - `Year Over Year % (Raw)`: dtype="float32" ## NEW CONSTRUCTION Base Columns - `Region ID`: dtype="string", a unique identifier for the region - `Size Rank`: dtype="int32", a rank of the region's size - `Region`: dtype="string", the name of the region - `Region Type`: dtype="class_label", the type of region - '0': county - '1': city - '2': zip - '3': country - '4': msa - `State`: dtype="string", the US state abbreviation for the state containing the region - `Home Type`: dtype="class_label", the type of home - '0': all homes - '1': all homes plus multifamily - '2': SFR - '3': condo/co-op - '4': multifamily - `Date`: dtype="timestamp[ms]", the date of the last day of the month for this data Value Columns - `Median Sale Price`: dtype="float32", the median sale price of new construction homes that sold during the month in the specified region - `Median Sale Price per Sqft`: dtype="float32", the median sale price per square foot of new construction homes that sold during the month in the specified region - `Sales Count`: dtype="int32", the number of new construction homes that sold during the month in the specified region ## RENTALS Base Columns - `Region ID`: dtype="string", a unique identifier for the region - `Size Rank`: dtype="int32", a rank of the region's size - `Region`: dtype="string", the name of the region - `Region Type`: dtype="class_label", the type of region - '0': county - '1': city - '2': zip - '3': country - '4': msa - `State`: dtype="string", the US state abbreviation for the state containing the region - `Home Type`: dtype="string", the type of home - '0': all homes - '1': all homes plus multifamily - '2': SFR - '3': condo/co-op - '4': multifamily - `Date`: dtype="timestamp[ms]", the date of the last day of the month for this data Value Columns - `Rent (Smoothed)`: dtype="float32", Zillow Observed Rent Index (ZORI): A smoothed measure of the typical observed market rate rent across a given region. ZORI is a repeat-rent index that is weighted to the rental housing stock to ensure representativeness across the entire market, not just those homes currently listed for-rent. The index is dollar-denominated by computing the mean of listed rents that fall into the 40th to 60th percentile range for all homes and apartments in a given region, which is weighted to reflect the rental housing stock. - `Rent (Smoothed) (Seasonally Adjusted)`: dtype="float32", Zillow Observed Rent Index (ZORI) :A smoothed measure of the typical observed market rate rent across a given region. ZORI is a repeat-rent index that is weighted to the rental housing stock to ensure representativeness across the entire market, not just those homes currently listed for-rent. The index is dollar-denominated by computing the mean of listed rents that fall into the 40th to 60th percentile range for all homes and apartments in a given region, which is weighted to reflect the rental housing stock. ## SALES   Base Columns - `Region ID`: dtype="string", a unique identifier for the region - `Size Rank`: dtype="int32", a rank of the region's size - `Region`: dtype="string", the name of the region - `Region Type`: dtype="class_label", the type of region - '0': county - '1': city - '2': zip - '3': country - '4': msa - `State`: dtype="string", the US state abbreviation for the state containing the region - `Home Type`: dtype="class_label", the type of home - '0': all homes - '1': all homes plus multifamily - '2': SFR - '3': condo/co-op - '4': multifamily - `Date`: dtype="timestamp[ms]", the date of the last day of the month for this data Value Columns - `Median Sale Price`: dtype="float32", The median price at which homes across various geographies were sold. - `Median Sale Price per Sqft`: dtype="float32" The median price per square foot at which homes across various geographies were sold. - `Sales Count`: dtype="int32", The "Sales Count Nowcast" is the estimated number of unique properties that sold during the month after accounting for the latency between when sales occur and when they are reported. ## DEFINITIONS OF HOME TYPES - all Homes: Zillow defines all homes as single-family, condominium and co-operative homes with a county record. Unless specified, all series cover this segment of the housing stock. - SFR: single family residence - condo/co-op: Condominium and co-operative homes. - Multifamily 5+ units: Units in buildings with 5 or more housing units, that are not condominiums or co-ops.  # Example Usage ```python from datasets import load_dataset dataset = load_dataset("misikoff/zillow", 'home_values', trust_remote_code=True) ``` ## Example Notebook Linked below is an example notebook that demonstrates usage and analysis of one of the configs of this dataset. [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1lEPLbWsOKmNBzkPWT30RCBVxhG1LWkGg?usp=sharing)

taesiri/arxiv_db

taesiri

"2024-05-07T22:36:44Z"

17,167

4

[ "license:cc-by-nc-4.0", "region:us" ]

null

"2023-10-26T23:53:25Z"

--- license: cc-by-nc-4.0 ---

IGNF/FLAIR_1_osm_clip

IGNF

"2024-09-18T09:05:07Z"

17,158

5

[ "size_categories:10K<n<100K", "format:parquet", "modality:image", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us", "IGN" ]

null

"2023-04-27T12:28:28Z"

--- size_categories: - 10K<n<100K dataset_info: features: - name: image dtype: image - name: segmentation dtype: image - name: metadata struct: - name: address struct: - name: ISO3166-2-lvl4 dtype: string - name: ISO3166-2-lvl6 dtype: string - name: ISO3166-2-lvl7 dtype: string - name: aerialway dtype: string - name: aeroway dtype: string - name: allotments dtype: string - name: amenity dtype: string - name: bridge dtype: string - name: building dtype: string - name: city dtype: string - name: city_district dtype: string - name: club dtype: string - name: commercial dtype: string - name: country dtype: string - name: country_code dtype: string - name: county dtype: string - name: craft dtype: string - name: emergency dtype: string - name: farm dtype: string - name: farmyard dtype: string - name: hamlet dtype: string - name: healthcare dtype: string - name: highway dtype: string - name: historic dtype: string - name: house_number dtype: string - name: industrial dtype: string - name: isolated_dwelling dtype: string - name: junction dtype: string - name: landuse dtype: string - name: leisure dtype: string - name: locality dtype: string - name: man_made dtype: string - name: military dtype: string - name: municipality dtype: string - name: natural dtype: string - name: neighbourhood dtype: string - name: office dtype: string - name: place dtype: string - name: postcode dtype: string - name: province dtype: string - name: quarter dtype: string - name: railway dtype: string - name: region dtype: string - name: residential dtype: string - name: retail dtype: string - name: road dtype: string - name: shop dtype: string - name: square dtype: string - name: state dtype: string - name: state_district dtype: string - name: suburb dtype: string - name: tourism dtype: string - name: town dtype: string - name: village dtype: string - name: boundingbox sequence: string - name: camera dtype: string - name: code dtype: string - name: date dtype: string - name: dimensions sequence: int64 - name: display_name dtype: string - name: domain dtype: string - name: lat dtype: string - name: latlong sequence: float64 - name: licence dtype: string - name: lon dtype: string - name: origin sequence: float64 - name: osm_id dtype: int64 - name: osm_type dtype: string - name: patch_centroid_x dtype: float64 - name: patch_centroid_y dtype: float64 - name: patch_centroid_z dtype: float64 - name: place_id dtype: int64 - name: time dtype: string - name: unit_system dtype: string - name: zone dtype: string - name: class_rep struct: - name: class_repartition struct: - name: agricultural land dtype: float64 - name: bare soil dtype: float64 - name: brushwood dtype: float64 - name: building dtype: float64 - name: clear cut dtype: float64 - name: coniferous dtype: float64 - name: deciduous dtype: float64 - name: greenhouse dtype: float64 - name: herbaceous vegetation dtype: float64 - name: impervious surface dtype: float64 - name: ligneous dtype: float64 - name: mixed dtype: float64 - name: other dtype: float64 - name: pervious surface dtype: float64 - name: plowed land dtype: float64 - name: snow dtype: float64 - name: swimming pool dtype: float64 - name: vineyard dtype: float64 - name: water dtype: float64 - name: prompt dtype: string - name: clip_label dtype: string - name: clip_embeddings sequence: float32 splits: - name: train num_bytes: 26969627407.0 num_examples: 61712 download_size: 26975935912 dataset_size: 26969627407.0 tags: - IGN configs: - config_name: default data_files: - split: train path: data/train-* --- # Dataset Card for "FLAIR_OSM_CLIP" Dataset for the Seg2Sat model: https://github.com/RubenGres/Seg2Sat Derived from [FLAIR#1](https://huggingface.co/datasets/IGNF/FLAIR) train split. This dataset incudes the following features: - **image**: FLAIR#1 .tif files RBG bands converted into a more managable jpg format - **segmentation**: FLAIR#1 segmentation converted to JPG using the [LUT from the documentation](https://ignf.github.io/FLAIR/index_fr.html) - **metadata**: OSM metadata for the centroid of the image - **clip_label**: [CLIP ViT-H](https://github.com/openai/CLIP) description - **class_rep**: ratio of appearance of each class in the segmentation - **prompt**: Prompt used for the Seg2Sat model - **clip_embeddings**: Embedding using openai/clip-vit-base-patch32 model

fsicoli/common_voice_15_0

fsicoli

"2023-12-20T18:55:52Z"

16,944

5

[ "task_categories:automatic-speech-recognition", "language:ab", "language:af", "language:am", "language:ar", "language:as", "language:ast", "language:az", "language:ba", "language:bas", "language:be", "language:bg", "language:bn", "language:br", "language:ca", "language:ckb", "language:cnh", "language:cs", "language:cv", "language:cy", "language:da", "language:de", "language:dv", "language:dyu", "language:el", "language:en", "language:eo", "language:es", "language:et", "language:eu", "language:fa", "language:fi", "language:fr", "language:gl", "language:gn", "language:ha", "language:he", "language:hi", "language:hsb", "language:hu", "language:ia", "language:id", "language:ig", "language:is", "language:it", "language:ja", "language:ka", "language:kab", "language:kk", "language:kmr", "language:ko", "language:ky", "language:lg", "language:lo", "language:lt", "language:lv", "language:mdf", "language:mhr", "language:mk", "language:ml", "language:mn", "language:mr", "language:mrj", "language:mt", "language:myv", "language:nl", "language:oc", "language:or", "language:pl", "language:ps", "language:pt", "language:quy", "language:ro", "language:ru", "language:rw", "language:sah", "language:sat", "language:sc", "language:sk", "language:skr", "language:sl", "language:sq", "language:sr", "language:sw", "language:ta", "language:th", "language:ti", "language:tig", "language:tk", "language:tok", "language:tr", "language:tt", "language:tw", "language:ug", "language:uk", "language:ur", "language:uz", "language:vi", "language:vot", "language:yue", "language:zgh", "language:zh", "language:yo", "license:cc", "size_categories:100B<n<1T", "region:us", "mozilla", "foundation" ]

[ "automatic-speech-recognition" ]

"2023-11-13T13:27:04Z"

--- license: cc language: - ab - af - am - ar - as - ast - az - ba - bas - be - bg - bn - br - ca - ckb - cnh - cs - cv - cy - da - de - dv - dyu - el - en - eo - es - et - eu - fa - fi - fr - gl - gn - ha - he - hi - hsb - hu - ia - id - ig - is - it - ja - ka - kab - kk - kmr - ko - ky - lg - lo - lt - lv - mdf - mhr - mk - ml - mn - mr - mrj - mt - myv - nl - oc - or - pl - ps - pt - quy - ro - ru - rw - sah - sat - sc - sk - skr - sl - sq - sr - sw - ta - th - ti - tig - tk - tok - tr - tt - tw - ug - uk - ur - uz - vi - vot - yue - zgh - zh - yo task_categories: - automatic-speech-recognition pretty_name: Common Voice Corpus 15.0 size_categories: - 100B<n<1T tags: - mozilla - foundation --- # Dataset Card for Common Voice Corpus 15.0  This dataset is an unofficial version of the Mozilla Common Voice Corpus 15. It was downloaded and converted from the project's website https://commonvoice.mozilla.org/. ## Languages ``` Abkhaz, Albanian, Amharic, Arabic, Armenian, Assamese, Asturian, Azerbaijani, Basaa, Bashkir, Basque, Belarusian, Bengali, Breton, Bulgarian, Cantonese, Catalan, Central Kurdish, Chinese (China), Chinese (Hong Kong), Chinese (Taiwan), Chuvash, Czech, Danish, Dhivehi, Dioula, Dutch, English, Erzya, Esperanto, Estonian, Finnish, French, Frisian, Galician, Georgian, German, Greek, Guarani, Hakha Chin, Hausa, Hill Mari, Hindi, Hungarian, Icelandic, Igbo, Indonesian, Interlingua, Irish, Italian, Japanese, Kabyle, Kazakh, Kinyarwanda, Korean, Kurmanji Kurdish, Kyrgyz, Lao, Latvian, Lithuanian, Luganda, Macedonian, Malayalam, Maltese, Marathi, Meadow Mari, Moksha, Mongolian, Nepali, Norwegian Nynorsk, Occitan, Odia, Pashto, Persian, Polish, Portuguese, Punjabi, Quechua Chanka, Romanian, Romansh Sursilvan, Romansh Vallader, Russian, Sakha, Santali (Ol Chiki), Saraiki, Sardinian, Serbian, Slovak, Slovenian, Sorbian, Upper, Spanish, Swahili, Swedish, Taiwanese (Minnan), Tamazight, Tamil, Tatar, Thai, Tigre, Tigrinya, Toki Pona, Turkish, Turkmen, Twi, Ukrainian, Urdu, Uyghur, Uzbek, Vietnamese, Votic, Welsh, Yoruba ``` ## How to use The datasets library allows you to load and pre-process your dataset in pure Python, at scale. The dataset can be downloaded and prepared in one call to your local drive by using the load_dataset function. For example, to download the Portuguese config, simply specify the corresponding language config name (i.e., "pt" for Portuguese): ``` from datasets import load_dataset cv_15 = load_dataset("fsicoli/common_voice_15_0", "pt", split="train") ``` Using the datasets library, you can also stream the dataset on-the-fly by adding a streaming=True argument to the load_dataset function call. Loading a dataset in streaming mode loads individual samples of the dataset at a time, rather than downloading the entire dataset to disk. ``` from datasets import load_dataset cv_15 = load_dataset("fsicoli/common_voice_15_0", "pt", split="train", streaming=True) print(next(iter(cv_15))) ``` Bonus: create a PyTorch dataloader directly with your own datasets (local/streamed). ### Local ``` from datasets import load_dataset from torch.utils.data.sampler import BatchSampler, RandomSampler cv_15 = load_dataset("fsicoli/common_voice_15_0", "pt", split="train") batch_sampler = BatchSampler(RandomSampler(cv_15), batch_size=32, drop_last=False) dataloader = DataLoader(cv_15, batch_sampler=batch_sampler) ``` ### Streaming ``` from datasets import load_dataset from torch.utils.data import DataLoader cv_15 = load_dataset("fsicoli/common_voice_15_0", "pt", split="train") dataloader = DataLoader(cv_15, batch_size=32) ``` To find out more about loading and preparing audio datasets, head over to hf.co/blog/audio-datasets. ### Dataset Structure Data Instances A typical data point comprises the path to the audio file and its sentence. Additional fields include accent, age, client_id, up_votes, down_votes, gender, locale and segment. ### Licensing Information Public Domain, CC-0 ### Citation Information ``` @inproceedings{commonvoice:2020, author = {Ardila, R. and Branson, M. and Davis, K. and Henretty, M. and Kohler, M. and Meyer, J. and Morais, R. and Saunders, L. and Tyers, F. M. and Weber, G.}, title = {Common Voice: A Massively-Multilingual Speech Corpus}, booktitle = {Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020)}, pages = {4211--4215}, year = 2020 } ```

RogerQi/PH2D

RogerQi

"2025-03-31T09:27:25Z"

16,719

1

[ "task_categories:robotics", "license:mit", "arxiv:2503.13441", "region:us", "Human", "Humanoid", "Robot" ]

[ "robotics" ]

"2025-03-14T02:03:14Z"

--- license: mit task_categories: - robotics tags: - Human - Humanoid - Robot --- ## Dataset Description This dataset contains egocentric human-humanoid data that can be used to co-train manipulation policy for humanoid robot. For paper, visualization, and example code using this dataset, please refer to https://human-as-robot.github.io/ arXiv link: https://arxiv.org/abs/2503.13441 ## Task Descriptions We provide some example dataset config files that we used for our robots [here](https://github.com/RogerQi/human-policy/tree/main/hdt/configs/datasets). Data organizations - Each folder represents one task. Most HDF5 files contain ONE execution of the task specified by the language, but certain tasks, such as cup passing, contain multiple demonstrations in each HDF5. - Taskids start with `1` mean the data is a human demonstrations.

hssd/hssd-hab

hssd

"2025-02-14T02:19:58Z"

16,714

35

[ "language:en", "license:cc-by-nc-4.0", "region:us", "3D scenes", "Embodied AI" ]

null

"2023-06-04T18:59:50Z"

--- language: - en pretty_name: HSSD tags: - 3D scenes - Embodied AI license: cc-by-nc-4.0 extra_gated_heading: "Acknowledge license to accept the repository" extra_gated_prompt: "You agree to use this dataset under the [CC BY-NC 4.0 license](https://creativecommons.org/licenses/by-nc/4.0/) terms" viewer: false --- HSSD: Habitat Synthetic Scenes Dataset ================================== The [Habitat Synthetic Scenes Dataset (HSSD)](https://3dlg-hcvc.github.io/hssd/) is a human-authored 3D scene dataset that more closely mirrors real scenes than prior datasets. Our dataset represents real interiors and contains a diverse set of 211 scenes and more than 18000 models of real-world objects. <img src="https://i.imgur.com/XEkLxNs.png" width=50%> This repository provides a Habitat consumption-ready compressed version of HSSD. See [this repository](https://huggingface.co/datasets/hssd/hssd-models) for corresponding uncompressed assets. ## Dataset Structure ``` ├── objects │ ├── */*.glb │ ├── */*.collider.glb │ ├── */*.filteredSupportSurface(.ply|.glb) │ ├── */*.object_config.json ├── stages │ ├── *.glb │ ├── *.stage_config.json ├── scenes │ ├── *.scene_instance.json ├── scenes_uncluttered │ ├── *.scene_instance.json ├── scenes_articulated │ ├── *.scene_instance.json ├── scene_filter_files │ ├── *.rec_filter.json ├── metadata │ ├── *.csv │ ├── *.json ├── semantics │ ├── hssd-hab_semantic_lexicon.json │ ├── scenes | ├── *.semantic_config.json ├── urdf │ ├── <model_name> | ├── *.glb | ├── *.urdf | ├── *.ao_config.json └── hssd-hab.scene_dataset_config.json └── hssd-hab-uncluttered.scene_dataset_config.json └── hssd-hab-articulated.scene_dataset_config.json ``` - `hssd-hab.scene_dataset_config.json`: This SceneDataset config file aggregates the assets and metadata necessary to fully describe the set of stages, objects, and scenes constituting the dataset. - `objects`: 3D models representing distinct objects that are used to compose scenes. Contains configuration files, render assets, collider assets, and Receptacle mesh assets. - `stages`: A stage in Habitat is the set of static mesh components which make up the backdrop of a scene (e.g. floor, walls, stairs, etc.). - `scenes`: A scene is a single 3D world composed of a static stage and a variable number of objects. - `scene_filter_files`: These .rec_filter.json files contain mappings of Receptacle instance unique_names to active or filtered sets based on their locations and accessibility within the scene. They also contain a "within_set" defining Receptacles which can only be accessed when the parent Furniture object's "default_link" is in the "open" state. - `metadata`: The metadata directory contains several csv and json files which provide semantic mappings for objects in the dataset as well as rational mappings from regions to the types of clutter objects typically found in them to support procedural generation. - `semantics`: Primarily defines instance semantics for the scenes. *.semantic_config.json files contain the region annotations for each scene. - `urdf`: The urdf directory contains the articulated furniture assets, each contained in its own sub-directory named after the source asset. The .urdf files define the articulation properties. Each .glb file is either a render asset or Receptacle mesh connected to a rigid link. The .ao_config.json file contains habitat-specific metadata such as markersets and Receptacle definitions. ### Rearrange-ready assets: Supporting Habitat 3.0 embodied rearrangement tasks with updated colliders, adjusted and de-cluttered scene contents, receptacle meshes, and receptacle filter files. See [aihabitat.org/habitat3/](aihabitat.org/habitat3/) for more details. - `hssd-hab-uncluttered.scene_dataset_config.json`: This SceneDataset config file aggregates adds the adjusted and uncluttered scenes for rearrangement tasks. - `scenes_uncluttered`: Contains the adjusted scene instance configuration files. - `scene_filter_files`: A scene filter file organizes available Receptacle instances in a scene into active and inactive groups based on simualtion heuristics and manual edits. It is consumed by the RearrangeEpisodeGenerator to construct valid RearrangeEpisodeDatasets. ### Articulated scenes and assets: Introduced in `v0.3.0`, the `hssd-hab-articulated.scene_dataset_config.json` SceneDataset provides 202 fully articulated HSSD scenes ready for use within the AI Habitat simulation ecosystem. Note that only 161 are publicly available on this repo. The remainder and their unique assets are reserved as an internal test set. To enable more realistic indoor object manipulation, articulated 3D furniture models such as drawers, cabinets, and appliances were added to replace rigid assets. These models were converted from rigid source assets in HSSD and swapped into the scenes. Furniture is annotated with a set of Receptacles (surfaces which support small object placement such as shelves and drawers) and can be opened and closed by the agents. Receptacles are further filtered contextually in each scene to ensure that the active set is accessible to the agents. Additional annotations include point or marker sets for each furniture, region annotations, and semantic classification of objects. ## Getting Started To load HSSD scenes into the Habitat simulator, you can start by installing [habitat-sim](https://github.com/facebookresearch/habitat-sim) using instructions specified [here](https://github.com/facebookresearch/habitat-sim#installation). Once installed, you can run the interactive Habitat viewer to load a scene: ``` habitat-viewer --dataset /path/to/hssd-hab/hssd-hab.scene_dataset_config.json -- 102344280 # or ./build/viewer if compiling from source ``` You can find more information about using the interactive viewer [here](https://github.com/facebookresearch/habitat-sim#testing:~:text=path/to/data/-,Interactive%20testing,-%3A%20Use%20the%20interactive). Habitat-Sim is typically used with [Habitat-Lab](https://github.com/facebookresearch/habitat-lab), a modular high-level library for end-to-end experiments in embodied AI. To define embodied AI tasks (e.g. navigation, instruction following, question answering), train agents, and benchmark their performance using standard metrics, you can download habitat-lab using the instructions provided [here](https://github.com/facebookresearch/habitat-lab#installation). ## Changelog - `v0.3.0`: **Articulated Scenes and PARTNR support** - This major version update adds a large set of changes to support the introduction of 202 articulated HSSD scenes and the [PARTNR benchmark](https://github.com/facebookresearch/partnr-planner). - Includes improvements to stage texture/geometry and object collision shapes and receptacles. - Adds: - 2000+ articulated assets in the urdf/ directory representing and replacing rigid furniture objects. Annotated with Receptacles and semantics. - 202 new articulated scenes with rigid objects replaced by AOs. These are uncluttered and often significantly altered from originals to accommodate the new assets. - Note that test scenes and assets are removed before migration to this repo. - Receptacle filter files for new scenes annotating accessible Receptacles and "within" Receptacles (those which require opening an articulated link for access). - Note that only one link per AO is configured with an active Receptacle. This is based on logic in PARTNR and habitat-lab (default_link). - Region volume semantic annotations to all scenes - Semantic lexicon file with updated classes - Metadata files mapping object semantics and common-sense object->region sets for PARTNR - `v0.2.5`: **Rearrange-ready HSSD** - Note: this is a checkpoint. Known issues exist and continued polish is ongoing. - Adds Receptacle meshes describing support surfaces for small objects (e.g. table or shelf surfaces). - Adds collider meshes (.collider.glb) for assets with Receptacle meshes to support simulation. - Adds new scenes 'scenes_uncluttered' and new SceneDataset 'hssd-hab-uncluttered' containing adjusted and de-cluttered versions of the scenes for use in embodied rearrangement tasks. - Adds 'scene_filter_files' which sort Receptacles in each scene into active and inactive groups for RearrangeEpisode generation. - `v0.2.4`: - Recompresses several object GLBs to preserve PBR material status. - Adds CSV with object metadata and semantic lexicon files for Habitat. - Adds train/val scene splits file. - `v0.2.3`: First release.

open-social-world/EgoNormia

open-social-world

"2025-03-04T19:44:49Z"

16,711

3

[ "task_categories:visual-question-answering", "task_categories:video-text-to-text", "task_categories:question-answering", "language:en", "license:cc-by-sa-4.0", "size_categories:1K<n<10K", "format:parquet", "modality:image", "modality:text", "modality:video", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "arxiv:2502.20490", "region:us", "visual-reasoning", "perception", "predictive", "spatial", "temporal", "causal" ]

[ "visual-question-answering", "video-text-to-text", "question-answering" ]

"2025-02-01T01:25:44Z"

--- language: - en license: cc-by-sa-4.0 size_categories: - 1K<n<10K task_categories: - visual-question-answering - video-text-to-text - question-answering pretty_name: EgoNormia tags: - visual-reasoning - perception - predictive - spatial - temporal - causal --- <h1 align='center' style="text-align:center; font-weight:bold; font-size:2.0em;letter-spacing:2.0px;"> EgoNormia: Benchmarking Physical Social Norm Understanding</h1> <p align='center' style="text-align:center;font-size:1.25em;"> <a href="https://mhrezaei.com" target="_blank" style="text-decoration: none;">MohammadHossein Rezaei*</a>,  <a href="https://sofyc.github.io" target="_blank" style="text-decoration: none;">Yicheng Fu*</a>,  <a href="https://scholar.google.com/citations?user=bDIUeu4AAAAJ&hl=en" target="_blank" style="text-decoration: none;">Phil Cuvin*</a>,  <a href="https://calebziems.com" target="_blank" style="text-decoration: none;">Caleb Ziems</a>,  <a href="https://stevenyzzhang.github.io/website/" target="_blank" style="text-decoration: none;">Yanzhe Zhang</a>, <br/> <a href="https://zhuhao.me" target="_blank" style="text-decoration: none;">Hao Zhu</a>,  <a href="https://cs.stanford.edu/~diyiy/" target="_blank" style="text-decoration: none;">Diyi Yang</a>,  </p> <p align='center' style="text-align:center;font-size:1.25em;"> <a href="https://egonormia.org" title="Website" target="_blank" rel="nofollow" style="text-decoration: none;">🌎Website</a> | <a href="https://huggingface.co/datasets/open-social-world/EgoNormia" title="Dataset" target="_blank" rel="nofollow" style="text-decoration: none;">🤗 Dataset</a> | <a href="https://arxiv.org/abs/2502.20490" title="aXiv" target="_blank" rel="nofollow" style="text-decoration: none;">📄 arXiv</a> | <a href="https://hf.co/papers/2502.20490" title="Paper" target="_blank" rel="nofollow" style="text-decoration: none;">📄 HF Paper</a> </p> ## EgoNormia EgoNormia is a challenging QA benchmark that tests VLMs' ability to reason over norms in context. The datset consists of **1,853** physically grounded egocentric interaction clips from [Ego4D](https://ego4d-data.org/) and corresponding **five-way multiple-choice questions** tasks for each. <br><br> EgoNormia spans 100 distinct settings across a wide range of activities, cultures, and interactions. Unlike other visually-grounded spatiotemporal, predictive, or causal reasoning benchmarks, EgoNormia evaluates models’ ability to reason about what should be done under social norms. EgoNormia highlights cases where these norm-related objectives conflict—the richest arena for evaluating normative decision-making. ## Example Data Point <img src="image/egonormia_teaser.jpg" alt="Teaser" width="800"/> ## EgoNormia Statistics Statistics | Data Points | Video Sources | Scenarios | Types of Actions --- | --- | --- | --- | --- | Number | 1853 | 1077 | 97 | 93 <img src="image/activity_distribution.png" alt="Activity Distribution" width="400"/> ## Benchmarking Guide The supported method for benchmarking on EgoNormia is to download the github repo `git clone https://github.com/Open-Social-World/EgoNormia.git`, and then to follow the included guide for running model evaluation and benchmarking (which automatically downloads and uses this dataset). Alternatively, the HuggingFace datset can be directly downloaded and evaluated with custom code; however, this is not officially supported. ## Dataset Organization Below is a detailed explanation of the dataset's structure and its contents: ``` EgoNormia/ ├── images/ ├── videos/ # Images for dataset card │ └── {video_uid}/ │ ├── frame_all_during.jpg # Concatenated frames sampled at 1 FPS from video_during.mp4 │ ├── frame_all_prev.jpg # Concatenated frames sampled at 1 FPS from video_prev.mp4 │ ├── video_during.mp4 # Video clip capturing an action being performed │ └── video_prev.mp4 # Video clip capturing the five seconds before an action is performed └── final_data.json # JSON file with MCQs and descriptions for videos in EgoNormia ├── train-norm-updated.parquet # Parquet file for dataset visualization ├── .gitattributes # Git configuration └── README.md # README file ``` ### Annotation Format Each video includes metadata and an MCQ in the following format: ``` { "video_uid": { "id": "video_uid", "behaviors": list of str, "justifications": list of str, "correct": int, "sensibles": list of int, "taxonomy": { "0": list of string, "1": list of string, "2": list of string, "3": list of string, "4": list of string, }, "desc": str }, // Next video uid } ``` ## Limitations While multiple rounds of filtering are applied to ensure diversity in EgoNormis video clips, all video clips in EgoNormia are sourced exclusively from Ego4D, which may reflect inherent distribution biases within Ego4D. ## Contact - Yicheng Fu: [email protected] - Phil Cuvin: [email protected] - Hao Zhu: [email protected] ## Acknowledgement This research was supported in part by Other Transaction award HR00112490375 from the U.S. Defense Advanced Research Projects Agency (DARPA) Friction for Accountability in Conversational Transactions (FACT) program. We thank Google Cloud Platform and Modal Platform for their credits. We thank feedback from Yonatan Bisk and members of the SALT lab at Stanford University. The authors thank Leena Mathur and Su Li for their help in collecting out-of-domain robotics videos. ## Citation ```bibtex @misc{rezaei2025egonormiabenchmarkingphysicalsocial, title={EgoNormia: Benchmarking Physical Social Norm Understanding}, author={MohammadHossein Rezaei and Yicheng Fu and Phil Cuvin and Caleb Ziems and Yanzhe Zhang and Hao Zhu and Diyi Yang}, year={2025}, eprint={2502.20490}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2502.20490}, } ```

allenai/math_qa

allenai

"2024-01-18T11:08:38Z"

16,674

101

[ "task_categories:question-answering", "task_ids:multiple-choice-qa", "annotations_creators:crowdsourced", "language_creators:crowdsourced", "language_creators:expert-generated", "multilinguality:monolingual", "source_datasets:extended|aqua_rat", "language:en", "license:apache-2.0", "size_categories:10K<n<100K", "region:us" ]

[ "question-answering" ]

"2022-03-02T23:29:22Z"

--- annotations_creators: - crowdsourced language: - en language_creators: - crowdsourced - expert-generated license: - apache-2.0 multilinguality: - monolingual pretty_name: MathQA size_categories: - 10K<n<100K source_datasets: - extended|aqua_rat task_categories: - question-answering task_ids: - multiple-choice-qa paperswithcode_id: mathqa dataset_info: features: - name: Problem dtype: string - name: Rationale dtype: string - name: options dtype: string - name: correct dtype: string - name: annotated_formula dtype: string - name: linear_formula dtype: string - name: category dtype: string splits: - name: test num_bytes: 1844184 num_examples: 2985 - name: train num_bytes: 18368826 num_examples: 29837 - name: validation num_bytes: 2752969 num_examples: 4475 download_size: 7302821 dataset_size: 22965979 --- # Dataset Card for MathQA ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Homepage:** [https://math-qa.github.io/math-QA/](https://math-qa.github.io/math-QA/) - **Repository:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - **Paper:** [MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms](https://aclanthology.org/N19-1245/) - **Point of Contact:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - **Size of downloaded dataset files:** 7.30 MB - **Size of the generated dataset:** 22.96 MB - **Total amount of disk used:** 30.27 MB ### Dataset Summary We introduce a large-scale dataset of math word problems. Our dataset is gathered by using a new representation language to annotate over the AQuA-RAT dataset with fully-specified operational programs. AQuA-RAT has provided the questions, options, rationale, and the correct options. ### Supported Tasks and Leaderboards [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Languages [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Dataset Structure ### Data Instances #### default - **Size of downloaded dataset files:** 7.30 MB - **Size of the generated dataset:** 22.96 MB - **Total amount of disk used:** 30.27 MB An example of 'train' looks as follows. ``` { "Problem": "a multiple choice test consists of 4 questions , and each question has 5 answer choices . in how many r ways can the test be completed if every question is unanswered ?", "Rationale": "\"5 choices for each of the 4 questions , thus total r of 5 * 5 * 5 * 5 = 5 ^ 4 = 625 ways to answer all of them . answer : c .\"", "annotated_formula": "power(5, 4)", "category": "general", "correct": "c", "linear_formula": "power(n1,n0)|", "options": "a ) 24 , b ) 120 , c ) 625 , d ) 720 , e ) 1024" } ``` ### Data Fields The data fields are the same among all splits. #### default - `Problem`: a `string` feature. - `Rationale`: a `string` feature. - `options`: a `string` feature. - `correct`: a `string` feature. - `annotated_formula`: a `string` feature. - `linear_formula`: a `string` feature. - `category`: a `string` feature. ### Data Splits | name |train|validation|test| |-------|----:|---------:|---:| |default|29837| 4475|2985| ## Dataset Creation ### Curation Rationale [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Source Data #### Initial Data Collection and Normalization [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the source language producers? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Annotations #### Annotation process [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the annotators? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Personal and Sensitive Information [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Discussion of Biases [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Other Known Limitations [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Additional Information ### Dataset Curators [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Licensing Information The dataset is licensed under the [Apache License, Version 2.0](http://www.apache.org/licenses/LICENSE-2.0). ### Citation Information ``` @inproceedings{amini-etal-2019-mathqa, title = "{M}ath{QA}: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms", author = "Amini, Aida and Gabriel, Saadia and Lin, Shanchuan and Koncel-Kedziorski, Rik and Choi, Yejin and Hajishirzi, Hannaneh", booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)", month = jun, year = "2019", address = "Minneapolis, Minnesota", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/N19-1245", doi = "10.18653/v1/N19-1245", pages = "2357--2367", } ``` ### Contributions Thanks to [@thomwolf](https://github.com/thomwolf), [@lewtun](https://github.com/lewtun), [@patrickvonplaten](https://github.com/patrickvonplaten) for adding this dataset.

awettig/RedPajama-combined-15B-8k-llama

awettig

"2023-11-30T07:16:59Z"

16,408

0

[ "size_categories:1M<n<10M", "format:parquet", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]

null

"2023-11-29T05:26:03Z"

--- dataset_info: features: - name: input_ids sequence: int32 - name: attention_mask sequence: int8 - name: labels sequence: int64 splits: - name: test num_bytes: 3181819992 num_examples: 29874 - name: train num_bytes: 188533325564 num_examples: 1770133 download_size: 0 dataset_size: 191715145556 --- # Dataset Card for "RedPajama-combined-15B-8K-llama" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

gigant/tib_slides_wip

gigant

"2023-03-26T16:22:49Z"

16,368

0

[ "size_categories:100K<n<1M", "format:parquet", "modality:image", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]

null

"2023-03-26T00:20:40Z"

--- dataset_info: features: - name: Image dtype: image - name: file_name dtype: string splits: - name: train num_bytes: 161850916866.84 num_examples: 595458 download_size: 29396407498 dataset_size: 161850916866.84 --- # Dataset Card for "tib_slides_wip" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

JonasLange/DBD-research-group

JonasLange

"2023-06-27T11:26:14Z"

16,218

0

[ "size_categories:10K<n<100K", "format:parquet", "modality:audio", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]

null

"2023-06-27T08:44:41Z"

--- dataset_info: features: - name: ID dtype: string - name: Audio dtype: audio - name: Start Time (s) dtype: string - name: End Time (s) dtype: string - name: Low Freq (Hz) dtype: string - name: High Freq (Hz) dtype: string - name: Species eBird Code dtype: string - name: Call Type dtype: 'null' - name: Sex dtype: 'null' - name: Latitude dtype: float64 - name: Longitude dtype: float64 - name: Uncertainty dtype: 'null' - name: Microphone dtype: string - name: License dtype: string - name: Source dtype: string - name: BirdNet Training Data dtype: bool splits: - name: train num_bytes: 156231869250.216 num_examples: 10976 download_size: 538872707 dataset_size: 156231869250.216 --- # Dataset Card for "DBD-research-group" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

lmqg/qg_koquad

lmqg

"2022-12-02T18:53:42Z"

16,168

8

[ "task_categories:text-generation", "task_ids:language-modeling", "multilinguality:monolingual", "source_datasets:squad_es", "language:ko", "license:cc-by-4.0", "size_categories:10K<n<100K", "modality:text", "library:datasets", "library:mlcroissant", "arxiv:2210.03992", "region:us", "question-generation" ]

[ "text-generation" ]

"2022-06-02T23:42:21Z"

--- license: cc-by-4.0 pretty_name: KorQuAD for question generation language: ko multilinguality: monolingual size_categories: 10K<n<100K source_datasets: squad_es task_categories: - text-generation task_ids: - language-modeling tags: - question-generation --- # Dataset Card for "lmqg/qg_korquad" ## Dataset Description - **Repository:** [https://github.com/asahi417/lm-question-generation](https://github.com/asahi417/lm-question-generation) - **Paper:** [https://arxiv.org/abs/2210.03992](https://arxiv.org/abs/2210.03992) - **Point of Contact:** [Asahi Ushio](http://asahiushio.com/) ### Dataset Summary This is a subset of [QG-Bench](https://github.com/asahi417/lm-question-generation/blob/master/QG_BENCH.md#datasets), a unified question generation benchmark proposed in ["Generative Language Models for Paragraph-Level Question Generation: A Unified Benchmark and Evaluation, EMNLP 2022 main conference"](https://arxiv.org/abs/2210.03992). This is a modified version of [KorQuAD](https://huggingface.co/datasets/squad_kor_v1) for question generation (QG) task. Since the original dataset only contains training/validation set, we manually sample test set from training set, which has no overlap in terms of the paragraph with the training set. ### Supported Tasks and Leaderboards * `question-generation`: The dataset is assumed to be used to train a model for question generation. Success on this task is typically measured by achieving a high BLEU4/METEOR/ROUGE-L/BERTScore/MoverScore (see our paper for more in detail). ### Languages Korean (ko) ## Dataset Structure An example of 'train' looks as follows. ``` { "question": "함수해석학이 주목하는 탐구는?", "paragraph": "변화에 대한 이해와 묘사는 자연과학에 있어서 일반적인 주제이며, 미적분학은 변화를 탐구하는 강력한 도구로서 발전되었다. 함수는 변화하는 양을 묘사함에 있어서 중추적인 개념으로써 떠오르게 된다. 실수와 실변수로 구성된 함수의 엄밀한 탐구가 실해석학이라는 분야로 알려지게 되었고, 복소수에 대한 이와 같은 탐구분야는 복소해석학이라고 한다. 함수해석학은 함수의 공간(특히 무한차원)의 탐구에 주목한다. 함수해석학의 많은 응용분야 중 하나가 양자역학이다. 많은 문제들이 자연스럽게 양과 그 양의 변화율의 관계로 귀착되고, 이러한 문제들이 미분방정식으로 다루어진다. 자연의 많은 현상들이 동역학계로 기술될 수 있다. 혼돈 이론은 이러한 예측 불가능한 현상을 탐구하는 데 상당한 기여를 한다.", "answer": "함수의 공간(특히 무한차원)의 탐구", "sentence": "함수해석학은 함수의 공간(특히 무한차원)의 탐구 에 주목한다.", "paragraph_sentence": '변화에 대한 이해와 묘사는 자연과학에 있어서 일반적인 주제이며, 미적분학은 변화를 탐구하는 강력한 도구로서 발전되었다. 함수는 변화하는 양을 묘사함에 있어서 중추적인 개념으로써 떠오르게 된다. 실수와 실변수로 구성된 함수의 엄밀한 탐구가 실해석학이라는 분야로 알려지게 되었고, 복소수에 대한 이와 같은 탐구 분야는 복소해석학이라고 한다. <hl> 함수해석학은 함수의 공간(특히 무한차원)의 탐구 에 주목한다. <hl> 함수해석학의 많은 응용분야 중 하나가 양자역학이다. 많은 문제들이 자연스럽게 양과 그 양의 변화율의 관계로 귀착되고, 이러한 문제들이 미분방정식으로 다루어진다. 자연의 많은 현상들이 동역학계로 기술될 수 있다. 혼돈 이론은 이러한 예측 불가능한 현상을 탐구하는 데 상당한 기여를 한다.', "paragraph_answer": '변화에 대한 이해와 묘사는 자연과학에 있어서 일반적인 주제이며, 미적분학은 변화를 탐구하는 강력한 도구로서 발전되었다. 함수는 변화하는 양을 묘사함에 있어서 중추적인 개념으로써 떠오르게 된다. 실수와 실변수로 구성된 함수의 엄밀한 탐구가 실해석학이라는 분야로 알려지게 되었고, 복소수에 대한 이와 같은 탐구 분야는 복소해석학이라고 한다. 함수해석학은 <hl> 함수의 공간(특히 무한차원)의 탐구 <hl>에 주목한다. 함수해석학의 많은 응용분야 중 하나가 양자역학이다. 많은 문제들이 자연스럽게 양과 그 양의 변화율의 관계로 귀착되고, 이러한 문제들이 미분방정식으로 다루어진다. 자연의 많은 현상들이 동역학계로 기술될 수 있다. 혼돈 이론은 이러한 예측 불가능한 현상을 탐구하는 데 상당한 기여를 한다.', "sentence_answer": "함수해석학은 <hl> 함수의 공간(특히 무한차원)의 탐구 <hl> 에 주목한다." } ``` The data fields are the same among all splits. - `question`: a `string` feature. - `paragraph`: a `string` feature. - `answer`: a `string` feature. - `sentence`: a `string` feature. - `paragraph_answer`: a `string` feature, which is same as the paragraph but the answer is highlighted by a special token `<hl>`. - `paragraph_sentence`: a `string` feature, which is same as the paragraph but a sentence containing the answer is highlighted by a special token `<hl>`. - `sentence_answer`: a `string` feature, which is same as the sentence but the answer is highlighted by a special token `<hl>`. Each of `paragraph_answer`, `paragraph_sentence`, and `sentence_answer` feature is assumed to be used to train a question generation model, but with different information. The `paragraph_answer` and `sentence_answer` features are for answer-aware question generation and `paragraph_sentence` feature is for sentence-aware question generation. ## Data Splits |train|validation|test | |----:|---------:|----:| |54556| 5766 |5766 | ## Citation Information ``` @inproceedings{ushio-etal-2022-generative, title = "{G}enerative {L}anguage {M}odels for {P}aragraph-{L}evel {Q}uestion {G}eneration: {A} {U}nified {B}enchmark and {E}valuation", author = "Ushio, Asahi and Alva-Manchego, Fernando and Camacho-Collados, Jose", booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing", month = dec, year = "2022", address = "Abu Dhabi, U.A.E.", publisher = "Association for Computational Linguistics", } ```

fxmarty/transformers-regressions

fxmarty

"2023-09-27T13:33:28Z"

16,131

0

[ "license:mit", "region:us" ]

null

"2023-08-08T14:18:24Z"

--- license: mit ---

nyu-mll/blimp

nyu-mll

"2024-01-23T09:58:08Z"

16,130

37

[ "task_categories:text-classification", "task_ids:acceptability-classification", "annotations_creators:crowdsourced", "language_creators:machine-generated", "multilinguality:monolingual", "source_datasets:original", "language:en", "license:cc-by-4.0", "size_categories:10K<n<100K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "arxiv:1912.00582", "region:us" ]

[ "text-classification" ]

"2022-03-02T23:29:22Z"

--- annotations_creators: - crowdsourced language_creators: - machine-generated language: - en license: - cc-by-4.0 multilinguality: - monolingual size_categories: - 10K<n<100K source_datasets: - original task_categories: - text-classification task_ids: - acceptability-classification paperswithcode_id: blimp pretty_name: BLiMP dataset_info: - config_name: adjunct_island features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 165894 num_examples: 1000 download_size: 62231 dataset_size: 165894 - config_name: anaphor_gender_agreement features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 130918 num_examples: 1000 download_size: 39201 dataset_size: 130918 - config_name: anaphor_number_agreement features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 139879 num_examples: 1000 download_size: 41547 dataset_size: 139879 - config_name: animate_subject_passive features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 144423 num_examples: 1000 download_size: 47282 dataset_size: 144423 - config_name: animate_subject_trans features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 127798 num_examples: 1000 download_size: 49651 dataset_size: 127798 - config_name: causative features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 122772 num_examples: 1000 download_size: 48963 dataset_size: 122772 - config_name: complex_NP_island features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 198972 num_examples: 1000 download_size: 78211 dataset_size: 198972 - config_name: coordinate_structure_constraint_complex_left_branch features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 210912 num_examples: 1000 download_size: 67908 dataset_size: 210912 - config_name: coordinate_structure_constraint_object_extraction features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 171655 num_examples: 1000 download_size: 51584 dataset_size: 171655 - config_name: determiner_noun_agreement_1 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 156120 num_examples: 1000 download_size: 49893 dataset_size: 156120 - config_name: determiner_noun_agreement_2 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 156204 num_examples: 1000 download_size: 49527 dataset_size: 156204 - config_name: determiner_noun_agreement_irregular_1 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 164473 num_examples: 1000 download_size: 47274 dataset_size: 164473 - config_name: determiner_noun_agreement_irregular_2 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 161074 num_examples: 1000 download_size: 47422 dataset_size: 161074 - config_name: determiner_noun_agreement_with_adj_2 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 179666 num_examples: 1000 download_size: 56346 dataset_size: 179666 - config_name: determiner_noun_agreement_with_adj_irregular_1 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 184529 num_examples: 1000 download_size: 54405 dataset_size: 184529 - config_name: determiner_noun_agreement_with_adj_irregular_2 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 184396 num_examples: 1000 download_size: 54064 dataset_size: 184396 - config_name: determiner_noun_agreement_with_adjective_1 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 185126 num_examples: 1000 download_size: 55682 dataset_size: 185126 - config_name: distractor_agreement_relational_noun features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 191473 num_examples: 1000 download_size: 59641 dataset_size: 191473 - config_name: distractor_agreement_relative_clause features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 216756 num_examples: 1000 download_size: 77897 dataset_size: 216756 - config_name: drop_argument features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 109806 num_examples: 1000 download_size: 39961 dataset_size: 109806 - config_name: ellipsis_n_bar_1 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 217590 num_examples: 1000 download_size: 92776 dataset_size: 217590 - config_name: ellipsis_n_bar_2 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 233161 num_examples: 1000 download_size: 98882 dataset_size: 233161 - config_name: existential_there_object_raising features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 223741 num_examples: 1000 download_size: 76641 dataset_size: 223741 - config_name: existential_there_quantifiers_1 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 162931 num_examples: 1000 download_size: 51576 dataset_size: 162931 - config_name: existential_there_quantifiers_2 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 164826 num_examples: 1000 download_size: 52092 dataset_size: 164826 - config_name: existential_there_subject_raising features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 200063 num_examples: 1000 download_size: 59519 dataset_size: 200063 - config_name: expletive_it_object_raising features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 238615 num_examples: 1000 download_size: 88607 dataset_size: 238615 - config_name: inchoative features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 104319 num_examples: 1000 download_size: 39842 dataset_size: 104319 - config_name: intransitive features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 111097 num_examples: 1000 download_size: 42387 dataset_size: 111097 - config_name: irregular_past_participle_adjectives features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 144661 num_examples: 1000 download_size: 36654 dataset_size: 144661 - config_name: irregular_past_participle_verbs features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 125692 num_examples: 1000 download_size: 37297 dataset_size: 125692 - config_name: irregular_plural_subject_verb_agreement_1 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 165584 num_examples: 1000 download_size: 50725 dataset_size: 165584 - config_name: irregular_plural_subject_verb_agreement_2 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 153843 num_examples: 1000 download_size: 42707 dataset_size: 153843 - config_name: left_branch_island_echo_question features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 147840 num_examples: 1000 download_size: 50481 dataset_size: 147840 - config_name: left_branch_island_simple_question features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 150060 num_examples: 1000 download_size: 50293 dataset_size: 150060 - config_name: matrix_question_npi_licensor_present features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 153262 num_examples: 1000 download_size: 51899 dataset_size: 153262 - config_name: npi_present_1 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 138465 num_examples: 1000 download_size: 51981 dataset_size: 138465 - config_name: npi_present_2 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 127636 num_examples: 1000 download_size: 51661 dataset_size: 127636 - config_name: only_npi_licensor_present features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 148516 num_examples: 1000 download_size: 51361 dataset_size: 148516 - config_name: only_npi_scope features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 208902 num_examples: 1000 download_size: 84970 dataset_size: 208902 - config_name: passive_1 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 145882 num_examples: 1000 download_size: 53931 dataset_size: 145882 - config_name: passive_2 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 113960 num_examples: 1000 download_size: 40499 dataset_size: 113960 - config_name: principle_A_c_command features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 188490 num_examples: 1000 download_size: 67867 dataset_size: 188490 - config_name: principle_A_case_1 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 170398 num_examples: 1000 download_size: 61092 dataset_size: 170398 - config_name: principle_A_case_2 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 170412 num_examples: 1000 download_size: 56430 dataset_size: 170412 - config_name: principle_A_domain_1 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 171170 num_examples: 1000 download_size: 59120 dataset_size: 171170 - config_name: principle_A_domain_2 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 165333 num_examples: 1000 download_size: 58464 dataset_size: 165333 - config_name: principle_A_domain_3 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 158998 num_examples: 1000 download_size: 52859 dataset_size: 158998 - config_name: principle_A_reconstruction features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 152104 num_examples: 1000 download_size: 44480 dataset_size: 152104 - config_name: regular_plural_subject_verb_agreement_1 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 158819 num_examples: 1000 download_size: 49466 dataset_size: 158819 - config_name: regular_plural_subject_verb_agreement_2 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 153609 num_examples: 1000 download_size: 43365 dataset_size: 153609 - config_name: sentential_negation_npi_licensor_present features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 171864 num_examples: 1000 download_size: 54830 dataset_size: 171864 - config_name: sentential_negation_npi_scope features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 232098 num_examples: 1000 download_size: 90157 dataset_size: 232098 - config_name: sentential_subject_island features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 172432 num_examples: 1000 download_size: 56666 dataset_size: 172432 - config_name: superlative_quantifiers_1 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 159290 num_examples: 1000 download_size: 48453 dataset_size: 159290 - config_name: superlative_quantifiers_2 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 159340 num_examples: 1000 download_size: 50480 dataset_size: 159340 - config_name: tough_vs_raising_1 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 148636 num_examples: 1000 download_size: 44779 dataset_size: 148636 - config_name: tough_vs_raising_2 features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 169684 num_examples: 1000 download_size: 61465 dataset_size: 169684 - config_name: transitive features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 133104 num_examples: 1000 download_size: 55090 dataset_size: 133104 - config_name: wh_island features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 142340 num_examples: 1000 download_size: 52808 dataset_size: 142340 - config_name: wh_questions_object_gap features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 193045 num_examples: 1000 download_size: 70049 dataset_size: 193045 - config_name: wh_questions_subject_gap features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 195593 num_examples: 1000 download_size: 71632 dataset_size: 195593 - config_name: wh_questions_subject_gap_long_distance features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 268270 num_examples: 1000 download_size: 98913 dataset_size: 268270 - config_name: wh_vs_that_no_gap features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 188872 num_examples: 1000 download_size: 71710 dataset_size: 188872 - config_name: wh_vs_that_no_gap_long_distance features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 247039 num_examples: 1000 download_size: 95504 dataset_size: 247039 - config_name: wh_vs_that_with_gap features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 173386 num_examples: 1000 download_size: 60291 dataset_size: 173386 - config_name: wh_vs_that_with_gap_long_distance features: - name: sentence_good dtype: string - name: sentence_bad dtype: string - name: field dtype: string - name: linguistics_term dtype: string - name: UID dtype: string - name: simple_LM_method dtype: bool - name: one_prefix_method dtype: bool - name: two_prefix_method dtype: bool - name: lexically_identical dtype: bool - name: pair_id dtype: int32 splits: - name: train num_bytes: 231595 num_examples: 1000 download_size: 84147 dataset_size: 231595 configs: - config_name: adjunct_island data_files: - split: train path: adjunct_island/train-* - config_name: anaphor_gender_agreement data_files: - split: train path: anaphor_gender_agreement/train-* - config_name: anaphor_number_agreement data_files: - split: train path: anaphor_number_agreement/train-* - config_name: animate_subject_passive data_files: - split: train path: animate_subject_passive/train-* - config_name: animate_subject_trans data_files: - split: train path: animate_subject_trans/train-* - config_name: causative data_files: - split: train path: causative/train-* - config_name: complex_NP_island data_files: - split: train path: complex_NP_island/train-* - config_name: coordinate_structure_constraint_complex_left_branch data_files: - split: train path: coordinate_structure_constraint_complex_left_branch/train-* - config_name: coordinate_structure_constraint_object_extraction data_files: - split: train path: coordinate_structure_constraint_object_extraction/train-* - config_name: determiner_noun_agreement_1 data_files: - split: train path: determiner_noun_agreement_1/train-* - config_name: determiner_noun_agreement_2 data_files: - split: train path: determiner_noun_agreement_2/train-* - config_name: determiner_noun_agreement_irregular_1 data_files: - split: train path: determiner_noun_agreement_irregular_1/train-* - config_name: determiner_noun_agreement_irregular_2 data_files: - split: train path: determiner_noun_agreement_irregular_2/train-* - config_name: determiner_noun_agreement_with_adj_2 data_files: - split: train path: determiner_noun_agreement_with_adj_2/train-* - config_name: determiner_noun_agreement_with_adj_irregular_1 data_files: - split: train path: determiner_noun_agreement_with_adj_irregular_1/train-* - config_name: determiner_noun_agreement_with_adj_irregular_2 data_files: - split: train path: determiner_noun_agreement_with_adj_irregular_2/train-* - config_name: determiner_noun_agreement_with_adjective_1 data_files: - split: train path: determiner_noun_agreement_with_adjective_1/train-* - config_name: distractor_agreement_relational_noun data_files: - split: train path: distractor_agreement_relational_noun/train-* - config_name: distractor_agreement_relative_clause data_files: - split: train path: distractor_agreement_relative_clause/train-* - config_name: drop_argument data_files: - split: train path: drop_argument/train-* - config_name: ellipsis_n_bar_1 data_files: - split: train path: ellipsis_n_bar_1/train-* - config_name: ellipsis_n_bar_2 data_files: - split: train path: ellipsis_n_bar_2/train-* - config_name: existential_there_object_raising data_files: - split: train path: existential_there_object_raising/train-* - config_name: existential_there_quantifiers_1 data_files: - split: train path: existential_there_quantifiers_1/train-* - config_name: existential_there_quantifiers_2 data_files: - split: train path: existential_there_quantifiers_2/train-* - config_name: existential_there_subject_raising data_files: - split: train path: existential_there_subject_raising/train-* - config_name: expletive_it_object_raising data_files: - split: train path: expletive_it_object_raising/train-* - config_name: inchoative data_files: - split: train path: inchoative/train-* - config_name: intransitive data_files: - split: train path: intransitive/train-* - config_name: irregular_past_participle_adjectives data_files: - split: train path: irregular_past_participle_adjectives/train-* - config_name: irregular_past_participle_verbs data_files: - split: train path: irregular_past_participle_verbs/train-* - config_name: irregular_plural_subject_verb_agreement_1 data_files: - split: train path: irregular_plural_subject_verb_agreement_1/train-* - config_name: irregular_plural_subject_verb_agreement_2 data_files: - split: train path: irregular_plural_subject_verb_agreement_2/train-* - config_name: left_branch_island_echo_question data_files: - split: train path: left_branch_island_echo_question/train-* - config_name: left_branch_island_simple_question data_files: - split: train path: left_branch_island_simple_question/train-* - config_name: matrix_question_npi_licensor_present data_files: - split: train path: matrix_question_npi_licensor_present/train-* - config_name: npi_present_1 data_files: - split: train path: npi_present_1/train-* - config_name: npi_present_2 data_files: - split: train path: npi_present_2/train-* - config_name: only_npi_licensor_present data_files: - split: train path: only_npi_licensor_present/train-* - config_name: only_npi_scope data_files: - split: train path: only_npi_scope/train-* - config_name: passive_1 data_files: - split: train path: passive_1/train-* - config_name: passive_2 data_files: - split: train path: passive_2/train-* - config_name: principle_A_c_command data_files: - split: train path: principle_A_c_command/train-* - config_name: principle_A_case_1 data_files: - split: train path: principle_A_case_1/train-* - config_name: principle_A_case_2 data_files: - split: train path: principle_A_case_2/train-* - config_name: principle_A_domain_1 data_files: - split: train path: principle_A_domain_1/train-* - config_name: principle_A_domain_2 data_files: - split: train path: principle_A_domain_2/train-* - config_name: principle_A_domain_3 data_files: - split: train path: principle_A_domain_3/train-* - config_name: principle_A_reconstruction data_files: - split: train path: principle_A_reconstruction/train-* - config_name: regular_plural_subject_verb_agreement_1 data_files: - split: train path: regular_plural_subject_verb_agreement_1/train-* - config_name: regular_plural_subject_verb_agreement_2 data_files: - split: train path: regular_plural_subject_verb_agreement_2/train-* - config_name: sentential_negation_npi_licensor_present data_files: - split: train path: sentential_negation_npi_licensor_present/train-* - config_name: sentential_negation_npi_scope data_files: - split: train path: sentential_negation_npi_scope/train-* - config_name: sentential_subject_island data_files: - split: train path: sentential_subject_island/train-* - config_name: superlative_quantifiers_1 data_files: - split: train path: superlative_quantifiers_1/train-* - config_name: superlative_quantifiers_2 data_files: - split: train path: superlative_quantifiers_2/train-* - config_name: tough_vs_raising_1 data_files: - split: train path: tough_vs_raising_1/train-* - config_name: tough_vs_raising_2 data_files: - split: train path: tough_vs_raising_2/train-* - config_name: transitive data_files: - split: train path: transitive/train-* - config_name: wh_island data_files: - split: train path: wh_island/train-* - config_name: wh_questions_object_gap data_files: - split: train path: wh_questions_object_gap/train-* - config_name: wh_questions_subject_gap data_files: - split: train path: wh_questions_subject_gap/train-* - config_name: wh_questions_subject_gap_long_distance data_files: - split: train path: wh_questions_subject_gap_long_distance/train-* - config_name: wh_vs_that_no_gap data_files: - split: train path: wh_vs_that_no_gap/train-* - config_name: wh_vs_that_no_gap_long_distance data_files: - split: train path: wh_vs_that_no_gap_long_distance/train-* - config_name: wh_vs_that_with_gap data_files: - split: train path: wh_vs_that_with_gap/train-* - config_name: wh_vs_that_with_gap_long_distance data_files: - split: train path: wh_vs_that_with_gap_long_distance/train-* --- # Dataset Card for "blimp" ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Homepage:** - **Repository:** https://github.com/alexwarstadt/blimp - **Paper:** [BLiMP: The Benchmark of Linguistic Minimal Pairs for English](https://doi.org/10.1162/tacl_a_00321) - **Paper:** https://arxiv.org/abs/1912.00582 - **Point of Contact:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - **Size of downloaded dataset files:** 29.58 MB - **Size of the generated dataset:** 11.45 MB - **Total amount of disk used:** 41.03 MB ### Dataset Summary BLiMP is a challenge set for evaluating what language models (LMs) know about major grammatical phenomena in English. BLiMP consists of 67 sub-datasets, each containing 1000 minimal pairs isolating specific contrasts in syntax, morphology, or semantics. The data is automatically generated according to expert-crafted grammars. ### Supported Tasks and Leaderboards [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Languages [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Dataset Structure ### Data Instances #### adjunct_island - **Size of downloaded dataset files:** 0.36 MB - **Size of the generated dataset:** 0.17 MB - **Total amount of disk used:** 0.52 MB An example of 'train' looks as follows. ``` { "UID": "tough_vs_raising_1", "field": "syntax_semantics", "lexically_identical": false, "linguistics_term": "control_raising", "one_prefix_method": false, "pair_id": 2, "sentence_bad": "Benjamin's tutor was certain to boast about.", "sentence_good": "Benjamin's tutor was easy to boast about.", "simple_LM_method": true, "two_prefix_method": false } ``` #### anaphor_gender_agreement - **Size of downloaded dataset files:** 0.44 MB - **Size of the generated dataset:** 0.14 MB - **Total amount of disk used:** 0.57 MB An example of 'train' looks as follows. ``` { "UID": "tough_vs_raising_1", "field": "syntax_semantics", "lexically_identical": false, "linguistics_term": "control_raising", "one_prefix_method": false, "pair_id": 2, "sentence_bad": "Benjamin's tutor was certain to boast about.", "sentence_good": "Benjamin's tutor was easy to boast about.", "simple_LM_method": true, "two_prefix_method": false } ``` #### anaphor_number_agreement - **Size of downloaded dataset files:** 0.45 MB - **Size of the generated dataset:** 0.14 MB - **Total amount of disk used:** 0.59 MB An example of 'train' looks as follows. ``` { "UID": "tough_vs_raising_1", "field": "syntax_semantics", "lexically_identical": false, "linguistics_term": "control_raising", "one_prefix_method": false, "pair_id": 2, "sentence_bad": "Benjamin's tutor was certain to boast about.", "sentence_good": "Benjamin's tutor was easy to boast about.", "simple_LM_method": true, "two_prefix_method": false } ``` #### animate_subject_passive - **Size of downloaded dataset files:** 0.46 MB - **Size of the generated dataset:** 0.15 MB - **Total amount of disk used:** 0.61 MB An example of 'train' looks as follows. ``` { "UID": "tough_vs_raising_1", "field": "syntax_semantics", "lexically_identical": false, "linguistics_term": "control_raising", "one_prefix_method": false, "pair_id": 2, "sentence_bad": "Benjamin's tutor was certain to boast about.", "sentence_good": "Benjamin's tutor was easy to boast about.", "simple_LM_method": true, "two_prefix_method": false } ``` #### animate_subject_trans - **Size of downloaded dataset files:** 0.43 MB - **Size of the generated dataset:** 0.13 MB - **Total amount of disk used:** 0.57 MB An example of 'train' looks as follows. ``` { "UID": "tough_vs_raising_1", "field": "syntax_semantics", "lexically_identical": false, "linguistics_term": "control_raising", "one_prefix_method": false, "pair_id": 2, "sentence_bad": "Benjamin's tutor was certain to boast about.", "sentence_good": "Benjamin's tutor was easy to boast about.", "simple_LM_method": true, "two_prefix_method": false } ``` ### Data Fields The data fields are the same among all splits. #### adjunct_island - `sentence_good`: a `string` feature. - `sentence_bad`: a `string` feature. - `field`: a `string` feature. - `linguistics_term`: a `string` feature. - `UID`: a `string` feature. - `simple_LM_method`: a `bool` feature. - `one_prefix_method`: a `bool` feature. - `two_prefix_method`: a `bool` feature. - `lexically_identical`: a `bool` feature. - `pair_id`: a `int32` feature. #### anaphor_gender_agreement - `sentence_good`: a `string` feature. - `sentence_bad`: a `string` feature. - `field`: a `string` feature. - `linguistics_term`: a `string` feature. - `UID`: a `string` feature. - `simple_LM_method`: a `bool` feature. - `one_prefix_method`: a `bool` feature. - `two_prefix_method`: a `bool` feature. - `lexically_identical`: a `bool` feature. - `pair_id`: a `int32` feature. #### anaphor_number_agreement - `sentence_good`: a `string` feature. - `sentence_bad`: a `string` feature. - `field`: a `string` feature. - `linguistics_term`: a `string` feature. - `UID`: a `string` feature. - `simple_LM_method`: a `bool` feature. - `one_prefix_method`: a `bool` feature. - `two_prefix_method`: a `bool` feature. - `lexically_identical`: a `bool` feature. - `pair_id`: a `int32` feature. #### animate_subject_passive - `sentence_good`: a `string` feature. - `sentence_bad`: a `string` feature. - `field`: a `string` feature. - `linguistics_term`: a `string` feature. - `UID`: a `string` feature. - `simple_LM_method`: a `bool` feature. - `one_prefix_method`: a `bool` feature. - `two_prefix_method`: a `bool` feature. - `lexically_identical`: a `bool` feature. - `pair_id`: a `int32` feature. #### animate_subject_trans - `sentence_good`: a `string` feature. - `sentence_bad`: a `string` feature. - `field`: a `string` feature. - `linguistics_term`: a `string` feature. - `UID`: a `string` feature. - `simple_LM_method`: a `bool` feature. - `one_prefix_method`: a `bool` feature. - `two_prefix_method`: a `bool` feature. - `lexically_identical`: a `bool` feature. - `pair_id`: a `int32` feature. ### Data Splits | name |train| |------------------------|----:| |adjunct_island | 1000| |anaphor_gender_agreement| 1000| |anaphor_number_agreement| 1000| |animate_subject_passive | 1000| |animate_subject_trans | 1000| ## Dataset Creation ### Curation Rationale [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Source Data #### Initial Data Collection and Normalization [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the source language producers? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Annotations #### Annotation process [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the annotators? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Personal and Sensitive Information [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Discussion of Biases [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Other Known Limitations [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Additional Information ### Dataset Curators [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Licensing Information BLiMP is distributed under a [CC-BY](https://creativecommons.org/licenses/by/4.0/) license. Source: https://github.com/alexwarstadt/blimp#license ### Citation Information ``` @article{warstadt2020blimp, author = {Warstadt, Alex and Parrish, Alicia and Liu, Haokun and Mohananey, Anhad and Peng, Wei and Wang, Sheng-Fu and Bowman, Samuel R.}, title = {BLiMP: The Benchmark of Linguistic Minimal Pairs for English}, journal = {Transactions of the Association for Computational Linguistics}, volume = {8}, number = {}, pages = {377-392}, year = {2020}, doi = {10.1162/tacl\_a\_00321}, URL = {https://doi.org/10.1162/tacl_a_00321}, eprint = {https://doi.org/10.1162/tacl_a_00321}, abstract = { We introduce The Benchmark of Linguistic Minimal Pairs (BLiMP),1 a challenge set for evaluating the linguistic knowledge of language models (LMs) on major grammatical phenomena in English. BLiMP consists of 67 individual datasets, each containing 1,000 minimal pairs—that is, pairs of minimally different sentences that contrast in grammatical acceptability and isolate specific phenomenon in syntax, morphology, or semantics. We generate the data according to linguist-crafted grammar templates, and human aggregate agreement with the labels is 96.4\%. We evaluate n-gram, LSTM, and Transformer (GPT-2 and Transformer-XL) LMs by observing whether they assign a higher probability to the acceptable sentence in each minimal pair. We find that state-of-the-art models identify morphological contrasts related to agreement reliably, but they struggle with some subtle semantic and syntactic phenomena, such as negative polarity items and extraction islands. } } ``` #### Errata Some results were misreported in the published TACL version. Please refer to the corrected version on arXiv: https://arxiv.org/abs/1912.00582 ### Contributions Thanks to [@lhoestq](https://github.com/lhoestq), [@patrickvonplaten](https://github.com/patrickvonplaten), [@thomwolf](https://github.com/thomwolf) for adding this dataset.

alvations/c4p0-x1-en-ja

alvations

"2024-03-24T03:55:23Z"

15,951

0

[ "size_categories:n<1K", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]

null

"2024-03-23T09:54:37Z"

--- dataset_info: features: - name: source dtype: string - name: target dtype: string - name: target_backto_source dtype: string - name: raw_target list: - name: generated_text dtype: string - name: raw_target_backto_source list: - name: generated_text dtype: string - name: prompt dtype: string - name: reverse_prompt dtype: string - name: source_langid dtype: string - name: target_langid dtype: string - name: target_backto_source_langid dtype: string - name: doc_id dtype: int64 - name: sent_id dtype: int64 - name: timestamp dtype: string - name: url dtype: string - name: doc_hash dtype: string splits: - name: train num_bytes: 49764 num_examples: 42 download_size: 37636 dataset_size: 49764 configs: - config_name: default data_files: - split: train path: 66034f82c5c65ae4/train-* ---

DTU54DL/librispeech-augmentated-train-prepared

DTU54DL

"2022-12-05T14:21:47Z"

15,940

0

[ "size_categories:1K<n<10K", "format:parquet", "modality:audio", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]

null

"2022-11-26T21:55:59Z"

--- dataset_info: features: - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: text dtype: string - name: speaker_id dtype: int64 - name: chapter_id dtype: int64 - name: id dtype: string - name: input_features sequence: sequence: float32 - name: labels sequence: int64 splits: - name: train.360 num_bytes: 6796928865.0 num_examples: 5000 download_size: 3988873165 dataset_size: 6796928865.0 --- # Dataset Card for "librispeech-augmentated-train-prepared" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

shenyunhang/VoiceAssistant-400K

shenyunhang

"2025-03-23T08:36:31Z"

15,853

0

[ "license:apache-2.0", "region:us" ]

null

"2025-03-19T02:01:25Z"

--- license: apache-2.0 --- --- Data source: https://huggingface.co/datasets/gpt-omni/VoiceAssistant-400K 1. Question and answer audios are extracted, which results in `940,108` audio files. 2. Raw conversations are formed as multi-round chat format in `data.jsonl`, which has in total of `251,223` samples. ``` [ ... { "messages": [ { "role": "user", "content": "...<|audio|>" }, { "role": "assistant", "content": "...<|audio|>" } { "role": "user", "content": "...<|audio|>" }, { "role": "assistant", "content": "...<|audio|>" }, ... ], "audios": ["path/to/first/audio", "path/to/second/audio", "path/to/third/audio", "path/to/forth/audio", ...], }, ... ] ``` ---

lmms-lab/MMMU

lmms-lab

"2024-03-08T05:09:42Z"

15,840

4

[ "size_categories:10K<n<100K", "format:parquet", "modality:image", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]

null

"2024-01-15T06:32:16Z"

--- dataset_info: features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 57719107.0 num_examples: 150 - name: validation num_bytes: 347519954.0 num_examples: 900 - name: test num_bytes: 3271046267.0 num_examples: 10500 download_size: 3377778136 dataset_size: 3676285328.0 configs: - config_name: default data_files: - split: dev path: data/dev-* - split: validation path: data/validation-* - split: test path: data/test-* --- This is a merged version of [MMMU/MMMU](https://huggingface.co/datasets/MMMU/MMMU) with all subsets concatenated. <p align="center" width="100%"> <img src="https://i.postimg.cc/g0QRgMVv/WX20240228-113337-2x.png" width="100%" height="80%"> </p> # Large-scale Multi-modality Models Evaluation Suite > Accelerating the development of large-scale multi-modality models (LMMs) with `lmms-eval` 🏠 [Homepage](https://lmms-lab.github.io/) | 📚 [Documentation](docs/README.md) | 🤗 [Huggingface Datasets](https://huggingface.co/lmms-lab) # This Dataset This is a formatted version of [MMMU](https://github.com/MMMU-Benchmark/MMMU). It is used in our `lmms-eval` pipeline to allow for one-click evaluations of large multi-modality models. ``` @article{yue2023mmmu, title={Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi}, author={Yue, Xiang and Ni, Yuansheng and Zhang, Kai and Zheng, Tianyu and Liu, Ruoqi and Zhang, Ge and Stevens, Samuel and Jiang, Dongfu and Ren, Weiming and Sun, Yuxuan and others}, journal={arXiv preprint arXiv:2311.16502}, year={2023} } ```

pixparse/cc12m-wds

pixparse

"2023-12-15T04:50:41Z"

15,829

27

[ "task_categories:image-to-text", "license:other", "size_categories:10M<n<100M", "format:webdataset", "modality:image", "modality:text", "library:datasets", "library:webdataset", "library:mlcroissant", "arxiv:2102.08981", "region:us" ]

[ "image-to-text" ]

"2023-12-12T23:59:59Z"

--- license: other license_name: conceptual-12m license_link: LICENSE task_categories: - image-to-text size_categories: - 10M<n<100M --- # Dataset Card for Conceptual Captions 12M (CC12M) ## Dataset Description - **Repository:** [Conceptual 12M repository](https://github.com/google-research-datasets/conceptual-12m) - **Paper:** [Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts](https://arxiv.org/abs/2102.08981) - **Point of Contact:** [Conceptual Captions e-mail](mailto:[email protected]) ### Dataset Summary Conceptual 12M (CC12M) is a dataset with 12 million image-text pairs specifically meant to be used for visionand-language pre-training. Its data collection pipeline is a relaxed version of the one used in Conceptual Captions 3M (CC3M). ### Usage This instance of Conceptual Captions is in [webdataset](https://github.com/webdataset/webdataset/commits/main) .tar format. It can be used with webdataset library or upcoming releases of Hugging Face `datasets`. ...More Detail TBD ### Data Splits This dataset was downloaded using img2dataset. Images resized on download if shortest edge > 512 to shortest edge = 512. #### Train * `cc12m-train-*.tar` * Downloaded on 2021/18/22 * 2176 shards, 10968539 samples ## Additional Information ### Dataset Curators Soravit Changpinyo, Piyush Sharma, Nan Ding and Radu Soricut. ### Licensing Information The dataset may be freely used for any purpose, although acknowledgement of Google LLC ("Google") as the data source would be appreciated. The dataset is provided "AS IS" without any warranty, express or implied. Google disclaims all liability for any damages, direct or indirect, resulting from the use of the dataset. ### Citation Information ```bibtex @inproceedings{changpinyo2021cc12m, title = {{Conceptual 12M}: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts}, author = {Changpinyo, Soravit and Sharma, Piyush and Ding, Nan and Soricut, Radu}, booktitle = {CVPR}, year = {2021}, } ```

alvarobartt/mmlu-okapi-eval-es

alvarobartt

"2024-02-29T17:57:41Z"

15,789

1

[ "task_categories:multiple-choice", "task_categories:question-answering", "task_ids:multiple-choice-qa", "task_ids:open-domain-qa", "language:es", "license:cc-by-nc-4.0", "size_categories:10K<n<100K", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "arxiv:2009.03300", "arxiv:2307.16039", "region:us", "chatgpt-translated" ]

[ "multiple-choice", "question-answering" ]

"2024-02-29T12:55:40Z"

--- language: - es license: cc-by-nc-4.0 size_categories: - 10K<n<100K task_categories: - multiple-choice - question-answering task_ids: - multiple-choice-qa - open-domain-qa tags: - chatgpt-translated dataset_info: - config_name: abstract_algebra features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 1760 num_examples: 5 - name: validation num_bytes: 4246 num_examples: 11 - name: test num_bytes: 40783 num_examples: 100 download_size: 31838 dataset_size: 46789 - config_name: anatomy features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 2024 num_examples: 5 - name: validation num_bytes: 6533 num_examples: 14 - name: test num_bytes: 68781 num_examples: 134 download_size: 55543 dataset_size: 77338 - config_name: astronomy features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 4476 num_examples: 5 - name: validation num_bytes: 10713 num_examples: 16 - name: test num_bytes: 100179 num_examples: 152 download_size: 78498 dataset_size: 115368 - config_name: business_ethics features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 4608 num_examples: 5 - name: validation num_bytes: 6415 num_examples: 11 - name: test num_bytes: 69628 num_examples: 98 download_size: 62408 dataset_size: 80651 - config_name: clinical_knowledge features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 2594 num_examples: 5 - name: validation num_bytes: 14438 num_examples: 29 - name: test num_bytes: 135086 num_examples: 263 download_size: 103601 dataset_size: 152118 - config_name: college_biology features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 3177 num_examples: 5 - name: validation num_bytes: 10330 num_examples: 16 - name: test num_bytes: 103413 num_examples: 143 download_size: 87080 dataset_size: 116920 - config_name: college_chemistry features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 2779 num_examples: 5 - name: validation num_bytes: 4874 num_examples: 8 - name: test num_bytes: 52123 num_examples: 100 download_size: 51328 dataset_size: 59776 - config_name: college_computer_science features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 5805 num_examples: 5 - name: validation num_bytes: 9920 num_examples: 11 - name: test num_bytes: 89185 num_examples: 98 download_size: 82341 dataset_size: 104910 - config_name: college_mathematics features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 3089 num_examples: 5 - name: validation num_bytes: 5484 num_examples: 11 - name: test num_bytes: 50044 num_examples: 97 download_size: 51658 dataset_size: 58617 - config_name: college_medicine features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 3649 num_examples: 5 - name: validation num_bytes: 16728 num_examples: 22 - name: test num_bytes: 171553 num_examples: 171 download_size: 115167 dataset_size: 191930 - config_name: college_physics features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 2898 num_examples: 5 - name: validation num_bytes: 7335 num_examples: 11 - name: test num_bytes: 62094 num_examples: 100 download_size: 57235 dataset_size: 72327 - config_name: computer_security features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 1733 num_examples: 4 - name: validation num_bytes: 9678 num_examples: 11 - name: test num_bytes: 58507 num_examples: 100 download_size: 57512 dataset_size: 69918 - config_name: conceptual_physics features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 1965 num_examples: 5 - name: validation num_bytes: 9503 num_examples: 26 - name: test num_bytes: 86744 num_examples: 235 download_size: 69227 dataset_size: 98212 - config_name: econometrics features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 3459 num_examples: 5 - name: validation num_bytes: 10475 num_examples: 12 - name: test num_bytes: 94779 num_examples: 110 download_size: 71152 dataset_size: 108713 - config_name: electrical_engineering features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 2046 num_examples: 5 - name: validation num_bytes: 6173 num_examples: 16 - name: test num_bytes: 54302 num_examples: 145 download_size: 51393 dataset_size: 62521 - config_name: elementary_mathematics features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 2726 num_examples: 4 - name: validation num_bytes: 18444 num_examples: 40 - name: test num_bytes: 144531 num_examples: 369 download_size: 109491 dataset_size: 165701 - config_name: formal_logic features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 3619 num_examples: 5 - name: validation num_bytes: 12939 num_examples: 14 - name: test num_bytes: 96569 num_examples: 118 download_size: 63090 dataset_size: 113127 - config_name: global_facts features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 2553 num_examples: 5 - name: validation num_bytes: 3941 num_examples: 10 - name: test num_bytes: 39400 num_examples: 100 download_size: 37322 dataset_size: 45894 - config_name: high_school_biology features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 3476 num_examples: 5 - name: validation num_bytes: 23395 num_examples: 32 - name: test num_bytes: 232885 num_examples: 309 download_size: 158998 dataset_size: 259756 - config_name: high_school_chemistry features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 2507 num_examples: 5 - name: validation num_bytes: 14839 num_examples: 22 - name: test num_bytes: 120079 num_examples: 200 download_size: 90031 dataset_size: 137425 - config_name: high_school_computer_science features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 6121 num_examples: 5 - name: validation num_bytes: 6988 num_examples: 8 - name: test num_bytes: 93799 num_examples: 97 download_size: 75958 dataset_size: 106908 - config_name: high_school_european_history features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 14265 num_examples: 3 - name: validation num_bytes: 57480 num_examples: 17 - name: test num_bytes: 479646 num_examples: 148 download_size: 359755 dataset_size: 551391 - config_name: high_school_geography features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 3101 num_examples: 5 - name: validation num_bytes: 9160 num_examples: 22 - name: test num_bytes: 87342 num_examples: 192 download_size: 75260 dataset_size: 99603 - config_name: high_school_government_and_politics features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 3772 num_examples: 5 - name: validation num_bytes: 14984 num_examples: 21 - name: test num_bytes: 141849 num_examples: 193 download_size: 106607 dataset_size: 160605 - config_name: high_school_macroeconomics features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 2933 num_examples: 5 - name: validation num_bytes: 27945 num_examples: 43 - name: test num_bytes: 249710 num_examples: 387 download_size: 141531 dataset_size: 280588 - config_name: high_school_mathematics features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 2617 num_examples: 5 - name: validation num_bytes: 11798 num_examples: 28 - name: test num_bytes: 112551 num_examples: 266 download_size: 89117 dataset_size: 126966 - config_name: high_school_microeconomics features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 2710 num_examples: 5 - name: validation num_bytes: 16309 num_examples: 26 - name: test num_bytes: 160145 num_examples: 234 download_size: 98676 dataset_size: 179164 - config_name: high_school_physics features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 3173 num_examples: 5 - name: validation num_bytes: 14127 num_examples: 17 - name: test num_bytes: 123938 num_examples: 149 download_size: 90127 dataset_size: 141238 - config_name: high_school_psychology features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 3883 num_examples: 5 - name: validation num_bytes: 36566 num_examples: 60 - name: test num_bytes: 318886 num_examples: 513 download_size: 221819 dataset_size: 359335 - config_name: high_school_statistics features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 5264 num_examples: 5 - name: validation num_bytes: 21199 num_examples: 23 - name: test num_bytes: 234094 num_examples: 215 download_size: 150556 dataset_size: 260557 - config_name: high_school_us_history features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 10940 num_examples: 3 - name: validation num_bytes: 57373 num_examples: 19 - name: test num_bytes: 415443 num_examples: 149 download_size: 309982 dataset_size: 483756 - config_name: high_school_world_history features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 10120 num_examples: 5 - name: validation num_bytes: 70014 num_examples: 21 - name: test num_bytes: 629850 num_examples: 201 download_size: 441428 dataset_size: 709984 - config_name: human_aging features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 2066 num_examples: 5 - name: validation num_bytes: 10131 num_examples: 23 - name: test num_bytes: 96475 num_examples: 219 download_size: 81152 dataset_size: 108672 - config_name: human_sexuality features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 1251 num_examples: 3 - name: validation num_bytes: 5129 num_examples: 12 - name: test num_bytes: 53324 num_examples: 110 download_size: 53146 dataset_size: 59704 - config_name: international_law features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 5118 num_examples: 5 - name: validation num_bytes: 13609 num_examples: 13 - name: test num_bytes: 114851 num_examples: 121 download_size: 83492 dataset_size: 133578 - config_name: jurisprudence features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 2642 num_examples: 5 - name: validation num_bytes: 7940 num_examples: 11 - name: test num_bytes: 71653 num_examples: 108 download_size: 66964 dataset_size: 82235 - config_name: logical_fallacies features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 3160 num_examples: 5 - name: validation num_bytes: 10588 num_examples: 18 - name: test num_bytes: 103636 num_examples: 161 download_size: 66840 dataset_size: 117384 - config_name: machine_learning features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 5036 num_examples: 5 - name: validation num_bytes: 6891 num_examples: 11 - name: test num_bytes: 73135 num_examples: 112 download_size: 60833 dataset_size: 85062 - config_name: management features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 1872 num_examples: 5 - name: validation num_bytes: 3799 num_examples: 11 - name: test num_bytes: 42556 num_examples: 103 download_size: 43017 dataset_size: 48227 - config_name: marketing features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 3239 num_examples: 5 - name: validation num_bytes: 15704 num_examples: 25 - name: test num_bytes: 132425 num_examples: 231 download_size: 98948 dataset_size: 151368 - config_name: medical_genetics features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 2284 num_examples: 5 - name: validation num_bytes: 6400 num_examples: 11 - name: test num_bytes: 44372 num_examples: 100 download_size: 48735 dataset_size: 53056 - config_name: miscellaneous features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 1437 num_examples: 5 - name: validation num_bytes: 30333 num_examples: 86 - name: test num_bytes: 304980 num_examples: 760 download_size: 231606 dataset_size: 336750 - config_name: moral_disputes features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 3671 num_examples: 5 - name: validation num_bytes: 25869 num_examples: 38 - name: test num_bytes: 214143 num_examples: 327 download_size: 147774 dataset_size: 243683 - config_name: moral_scenarios features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 2657 num_examples: 3 - name: validation num_bytes: 71335 num_examples: 78 - name: test num_bytes: 683382 num_examples: 752 download_size: 213484 dataset_size: 757374 - config_name: nutrition features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 4523 num_examples: 5 - name: validation num_bytes: 17721 num_examples: 32 - name: test num_bytes: 199634 num_examples: 305 download_size: 138805 dataset_size: 221878 - config_name: philosophy features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 2058 num_examples: 5 - name: validation num_bytes: 19167 num_examples: 34 - name: test num_bytes: 161737 num_examples: 302 download_size: 121059 dataset_size: 182962 - config_name: prehistory features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 3992 num_examples: 5 - name: validation num_bytes: 21214 num_examples: 34 - name: test num_bytes: 181683 num_examples: 314 download_size: 136059 dataset_size: 206889 - config_name: professional_accounting features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 4568 num_examples: 5 - name: validation num_bytes: 29165 num_examples: 30 - name: test num_bytes: 266225 num_examples: 282 download_size: 181436 dataset_size: 299958 - config_name: professional_law features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 9431 num_examples: 4 - name: validation num_bytes: 363635 num_examples: 145 - name: test num_bytes: 3285957 num_examples: 1292 download_size: 1993775 dataset_size: 3659023 - config_name: professional_medicine features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 7060 num_examples: 4 - name: validation num_bytes: 47479 num_examples: 30 - name: test num_bytes: 446995 num_examples: 265 download_size: 311538 dataset_size: 501534 - config_name: professional_psychology features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 4597 num_examples: 5 - name: validation num_bytes: 60499 num_examples: 68 - name: test num_bytes: 471519 num_examples: 604 download_size: 325283 dataset_size: 536615 - config_name: public_relations features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 3165 num_examples: 5 - name: validation num_bytes: 9669 num_examples: 12 - name: test num_bytes: 60281 num_examples: 109 download_size: 61213 dataset_size: 73115 - config_name: security_studies features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 11199 num_examples: 5 - name: validation num_bytes: 47992 num_examples: 27 - name: test num_bytes: 427743 num_examples: 240 download_size: 282999 dataset_size: 486934 - config_name: sociology features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 3456 num_examples: 5 - name: validation num_bytes: 14660 num_examples: 21 - name: test num_bytes: 138231 num_examples: 196 download_size: 111807 dataset_size: 156347 - config_name: us_foreign_policy features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 3440 num_examples: 5 - name: validation num_bytes: 6883 num_examples: 11 - name: test num_bytes: 60635 num_examples: 99 download_size: 56816 dataset_size: 70958 - config_name: virology features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 1836 num_examples: 4 - name: validation num_bytes: 10140 num_examples: 17 - name: test num_bytes: 82841 num_examples: 165 download_size: 73952 dataset_size: 94817 - config_name: world_religions features: - name: en_question dtype: string - name: es_question dtype: string - name: en_choices sequence: string - name: es_choices sequence: string - name: en_answer dtype: int64 - name: es_answer dtype: int64 splits: - name: dev num_bytes: 1357 num_examples: 5 - name: validation num_bytes: 5669 num_examples: 19 - name: test num_bytes: 51954 num_examples: 171 download_size: 51989 dataset_size: 58980 configs: - config_name: abstract_algebra data_files: - split: dev path: abstract_algebra/dev-* - split: validation path: abstract_algebra/validation-* - split: test path: abstract_algebra/test-* - config_name: anatomy data_files: - split: dev path: anatomy/dev-* - split: validation path: anatomy/validation-* - split: test path: anatomy/test-* - config_name: astronomy data_files: - split: dev path: astronomy/dev-* - split: validation path: astronomy/validation-* - split: test path: astronomy/test-* - config_name: business_ethics data_files: - split: dev path: business_ethics/dev-* - split: validation path: business_ethics/validation-* - split: test path: business_ethics/test-* - config_name: clinical_knowledge data_files: - split: dev path: clinical_knowledge/dev-* - split: validation path: clinical_knowledge/validation-* - split: test path: clinical_knowledge/test-* - config_name: college_biology data_files: - split: dev path: college_biology/dev-* - split: validation path: college_biology/validation-* - split: test path: college_biology/test-* - config_name: college_chemistry data_files: - split: dev path: college_chemistry/dev-* - split: validation path: college_chemistry/validation-* - split: test path: college_chemistry/test-* - config_name: college_computer_science data_files: - split: dev path: college_computer_science/dev-* - split: validation path: college_computer_science/validation-* - split: test path: college_computer_science/test-* - config_name: college_mathematics data_files: - split: dev path: college_mathematics/dev-* - split: validation path: college_mathematics/validation-* - split: test path: college_mathematics/test-* - config_name: college_medicine data_files: - split: dev path: college_medicine/dev-* - split: validation path: college_medicine/validation-* - split: test path: college_medicine/test-* - config_name: college_physics data_files: - split: dev path: college_physics/dev-* - split: validation path: college_physics/validation-* - split: test path: college_physics/test-* - config_name: computer_security data_files: - split: dev path: computer_security/dev-* - split: validation path: computer_security/validation-* - split: test path: computer_security/test-* - config_name: conceptual_physics data_files: - split: dev path: conceptual_physics/dev-* - split: validation path: conceptual_physics/validation-* - split: test path: conceptual_physics/test-* - config_name: econometrics data_files: - split: dev path: econometrics/dev-* - split: validation path: econometrics/validation-* - split: test path: econometrics/test-* - config_name: electrical_engineering data_files: - split: dev path: electrical_engineering/dev-* - split: validation path: electrical_engineering/validation-* - split: test path: electrical_engineering/test-* - config_name: elementary_mathematics data_files: - split: dev path: elementary_mathematics/dev-* - split: validation path: elementary_mathematics/validation-* - split: test path: elementary_mathematics/test-* - config_name: formal_logic data_files: - split: dev path: formal_logic/dev-* - split: validation path: formal_logic/validation-* - split: test path: formal_logic/test-* - config_name: global_facts data_files: - split: dev path: global_facts/dev-* - split: validation path: global_facts/validation-* - split: test path: global_facts/test-* - config_name: high_school_biology data_files: - split: dev path: high_school_biology/dev-* - split: validation path: high_school_biology/validation-* - split: test path: high_school_biology/test-* - config_name: high_school_chemistry data_files: - split: dev path: high_school_chemistry/dev-* - split: validation path: high_school_chemistry/validation-* - split: test path: high_school_chemistry/test-* - config_name: high_school_computer_science data_files: - split: dev path: high_school_computer_science/dev-* - split: validation path: high_school_computer_science/validation-* - split: test path: high_school_computer_science/test-* - config_name: high_school_european_history data_files: - split: dev path: high_school_european_history/dev-* - split: validation path: high_school_european_history/validation-* - split: test path: high_school_european_history/test-* - config_name: high_school_geography data_files: - split: dev path: high_school_geography/dev-* - split: validation path: high_school_geography/validation-* - split: test path: high_school_geography/test-* - config_name: high_school_government_and_politics data_files: - split: dev path: high_school_government_and_politics/dev-* - split: validation path: high_school_government_and_politics/validation-* - split: test path: high_school_government_and_politics/test-* - config_name: high_school_macroeconomics data_files: - split: dev path: high_school_macroeconomics/dev-* - split: validation path: high_school_macroeconomics/validation-* - split: test path: high_school_macroeconomics/test-* - config_name: high_school_mathematics data_files: - split: dev path: high_school_mathematics/dev-* - split: validation path: high_school_mathematics/validation-* - split: test path: high_school_mathematics/test-* - config_name: high_school_microeconomics data_files: - split: dev path: high_school_microeconomics/dev-* - split: validation path: high_school_microeconomics/validation-* - split: test path: high_school_microeconomics/test-* - config_name: high_school_physics data_files: - split: dev path: high_school_physics/dev-* - split: validation path: high_school_physics/validation-* - split: test path: high_school_physics/test-* - config_name: high_school_psychology data_files: - split: dev path: high_school_psychology/dev-* - split: validation path: high_school_psychology/validation-* - split: test path: high_school_psychology/test-* - config_name: high_school_statistics data_files: - split: dev path: high_school_statistics/dev-* - split: validation path: high_school_statistics/validation-* - split: test path: high_school_statistics/test-* - config_name: high_school_us_history data_files: - split: dev path: high_school_us_history/dev-* - split: validation path: high_school_us_history/validation-* - split: test path: high_school_us_history/test-* - config_name: high_school_world_history data_files: - split: dev path: high_school_world_history/dev-* - split: validation path: high_school_world_history/validation-* - split: test path: high_school_world_history/test-* - config_name: human_aging data_files: - split: dev path: human_aging/dev-* - split: validation path: human_aging/validation-* - split: test path: human_aging/test-* - config_name: human_sexuality data_files: - split: dev path: human_sexuality/dev-* - split: validation path: human_sexuality/validation-* - split: test path: human_sexuality/test-* - config_name: international_law data_files: - split: dev path: international_law/dev-* - split: validation path: international_law/validation-* - split: test path: international_law/test-* - config_name: jurisprudence data_files: - split: dev path: jurisprudence/dev-* - split: validation path: jurisprudence/validation-* - split: test path: jurisprudence/test-* - config_name: logical_fallacies data_files: - split: dev path: logical_fallacies/dev-* - split: validation path: logical_fallacies/validation-* - split: test path: logical_fallacies/test-* - config_name: machine_learning data_files: - split: dev path: machine_learning/dev-* - split: validation path: machine_learning/validation-* - split: test path: machine_learning/test-* - config_name: management data_files: - split: dev path: management/dev-* - split: validation path: management/validation-* - split: test path: management/test-* - config_name: marketing data_files: - split: dev path: marketing/dev-* - split: validation path: marketing/validation-* - split: test path: marketing/test-* - config_name: medical_genetics data_files: - split: dev path: medical_genetics/dev-* - split: validation path: medical_genetics/validation-* - split: test path: medical_genetics/test-* - config_name: miscellaneous data_files: - split: dev path: miscellaneous/dev-* - split: validation path: miscellaneous/validation-* - split: test path: miscellaneous/test-* - config_name: moral_disputes data_files: - split: dev path: moral_disputes/dev-* - split: validation path: moral_disputes/validation-* - split: test path: moral_disputes/test-* - config_name: moral_scenarios data_files: - split: dev path: moral_scenarios/dev-* - split: validation path: moral_scenarios/validation-* - split: test path: moral_scenarios/test-* - config_name: nutrition data_files: - split: dev path: nutrition/dev-* - split: validation path: nutrition/validation-* - split: test path: nutrition/test-* - config_name: philosophy data_files: - split: dev path: philosophy/dev-* - split: validation path: philosophy/validation-* - split: test path: philosophy/test-* - config_name: prehistory data_files: - split: dev path: prehistory/dev-* - split: validation path: prehistory/validation-* - split: test path: prehistory/test-* - config_name: professional_accounting data_files: - split: dev path: professional_accounting/dev-* - split: validation path: professional_accounting/validation-* - split: test path: professional_accounting/test-* - config_name: professional_law data_files: - split: dev path: professional_law/dev-* - split: validation path: professional_law/validation-* - split: test path: professional_law/test-* - config_name: professional_medicine data_files: - split: dev path: professional_medicine/dev-* - split: validation path: professional_medicine/validation-* - split: test path: professional_medicine/test-* - config_name: professional_psychology data_files: - split: dev path: professional_psychology/dev-* - split: validation path: professional_psychology/validation-* - split: test path: professional_psychology/test-* - config_name: public_relations data_files: - split: dev path: public_relations/dev-* - split: validation path: public_relations/validation-* - split: test path: public_relations/test-* - config_name: security_studies data_files: - split: dev path: security_studies/dev-* - split: validation path: security_studies/validation-* - split: test path: security_studies/test-* - config_name: sociology data_files: - split: dev path: sociology/dev-* - split: validation path: sociology/validation-* - split: test path: sociology/test-* - config_name: us_foreign_policy data_files: - split: dev path: us_foreign_policy/dev-* - split: validation path: us_foreign_policy/validation-* - split: test path: us_foreign_policy/test-* - config_name: virology data_files: - split: dev path: virology/dev-* - split: validation path: virology/validation-* - split: test path: virology/test-* - config_name: world_religions data_files: - split: dev path: world_religions/dev-* - split: validation path: world_religions/validation-* - split: test path: world_religions/test-* --- # MMLU translated to Spanish This dataset was generated by the Natural Language Processing Group of the University of Oregon, where they used the original MMLU dataset in English and translated it into different languages using ChatGPT. This dataset only contains the Spanish translation, but the following languages are also covered within the original subsets posted by the University of Oregon at http://nlp.uoregon.edu/download/okapi-eval/datasets/. ## Disclaimer All the credits for this dataset go to the original authors of MMLU (licensed as MIT), and to the authors of this translation via ChatGPT (licensed as CC BY NC 4.0, allowing only non-commercial use). ## References * [Measuring Massive Multitask Language Understanding](https://arxiv.org/abs/2009.03300) * [Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback](https://arxiv.org/abs/2307.16039)

openbmb/DCAD-2000

openbmb

"2025-04-04T09:51:21Z"

15,764

4

[ "multilinguality:multilingual", "language:eng", "language:rus", "language:cmn", "language:deu", "language:spa", "language:fra", "language:jpn", "language:ita", "language:por", "language:pol", "language:nld", "language:ind", "language:tur", "language:vie", "language:fas", "language:kor", "language:swe", "language:hun", "language:ell", "language:ukr", "language:tha", "language:aze", "language:arb", "language:slv", "language:cat", "language:fin", "language:hbs", "language:ces", "language:fil", "language:guj", "language:nob", "language:mal", "language:bul", "language:kan", "language:hin", "language:tam", "language:ara", "language:kaz", "language:sqi", "language:pan", "language:est", "language:srp", "language:heb", "language:isl", "language:mlt", "language:mkd", "language:bos", "language:lit", "language:kat", "language:hrv", "language:ben", "language:glg", "language:ceb", "language:ron", "language:msa", "language:hye", "language:tgk", "language:mar", "language:bel", "language:nep", "language:urd", "language:slk", "language:mon", "language:swa", "language:dan", "language:eus", "language:azj", "language:sin", "language:lat", "language:als", "language:tel", "language:afr", "language:ekk", "language:ltz", "language:zsm", "language:som", "language:cym", "language:und", "language:kir", "language:nor", "language:uzb", "language:mya", "language:epo", "language:hau", "language:ary", "language:gle", "language:lvs", "language:nno", "language:ory", "language:amh", "language:tat", "language:khm", "language:arz", "language:pus", "language:lav", "language:war", "language:mlg", "language:uzn", "language:hat", "language:zul", "language:kur", "language:tgl", "language:div", "language:fry", "language:sna", "language:fao", "language:sun", "language:snd", "language:cos", "language:bak", "language:ckb", "language:asm", "language:ast", "language:ibo", "language:mri", "language:ars", "language:anp", "language:khk", "language:lao", "language:ori", "language:yid", "language:hmn", "language:jav", "language:nya", "language:tir", "language:uig", "language:wln", "language:yor", "language:swh", "language:gla", "language:xho", "language:bre", "language:sot", "language:che", "language:nan", "language:bew", "language:glk", "language:smo", "language:orm", "language:zho", "language:haw", "language:pnb", "language:oci", "language:chv", "language:kin", "language:pcm", "language:kaa", "language:lug", "language:pbt", "language:gsw", "language:min", "language:tuk", "language:lim", "language:kmr", "language:roh", "language:vec", "language:san", "language:gmh", "language:nds", "language:sco", "language:azb", "language:tsn", "language:sah", "language:pri", "language:pap", "language:plt", "language:lmo", "language:bod", "language:yue", "language:bar", "language:hif", "language:arg", "language:pms", "language:nrm", "language:vol", "language:aeb", "language:ido", "language:pam", "language:kal", "language:lus", "language:new", "language:sme", "language:nso", "language:lld", "language:ina", "language:scn", "language:hyw", "language:abk", "language:bpy", "language:lin", "language:oss", "language:que", "language:szl", "language:sdh", "language:mww", "language:mhr", "language:rmy", "language:diq", "language:srd", "language:ydd", "language:run", "language:hsb", "language:wol", "language:kiu", "language:ilo", "language:cak", "language:acm", "language:grc", "language:xmf", "language:vls", "language:tso", "language:crh", "language:nav", "language:mwl", "language:grn", "language:mui", "language:mvf", "language:udm", "language:mzn", "language:bcl", "language:ban", "language:afb", "language:cnh", "language:cbk", "language:tyv", "language:ful", "language:zea", "language:frp", "language:frr", "language:pfl", "language:lij", "language:apc", "language:mai", "language:pon", "language:eml", "language:uzs", "language:nde", "language:hil", "language:mam", "language:gom", "language:dag", "language:nap", "language:bjn", "language:hbo", "language:tet", "language:inh", "language:ven", "language:gaz", "language:tpi", "language:ajp", "language:sat", "language:wuu", "language:bam", "language:vep", "language:glv", "language:tzo", "language:bik", "language:acr", "language:twi", "language:myv", "language:ewe", "language:poh", "language:ile", "language:rue", "language:ace", "language:kha", "language:ksh", "language:hui", "language:gor", "language:krc", "language:lfn", "language:tls", "language:fur", "language:gag", "language:chk", "language:hmo", "language:kek", "language:fon", "language:ssw", "language:quh", "language:meu", "language:csb", "language:ksd", "language:ext", "language:rop", "language:aln", "language:kab", "language:shn", "language:tbz", "language:knv", "language:bqc", "language:npi", "language:rug", "language:kom", "language:kpg", "language:kbd", "language:dzo", "language:wal", "language:zlm", "language:mzh", "language:hac", "language:tum", "language:sgs", "language:fij", "language:tuc", "language:jbo", "language:iba", "language:pcd", "language:kjh", "language:ixl", "language:ndo", "language:suz", "language:mfe", "language:bxr", "language:ava", "language:bho", "language:brh", "language:ctd", "language:aym", "language:ady", "language:nbl", "language:hus", "language:gug", "language:bat", "language:hne", "language:srn", "language:ctu", "language:ton", "language:bug", "language:aoj", "language:jam", "language:lez", "language:xav", "language:luo", "language:ltg", "language:bih", "language:mrj", "language:avk", "language:kos", "language:kbp", "language:alt", "language:cfm", "language:goh", "language:lad", "language:cor", "language:quc", "language:kpv", "language:aka", "language:hak", "language:rmn", "language:pls", "language:sag", "language:rcf", "language:gym", "language:kik", "language:pag", "language:arn", "language:ngu", "language:dsb", "language:tca", "language:mni", "language:naq", "language:pdc", "language:mps", "language:olo", "language:fro", "language:fit", "language:cdo", "language:kac", "language:mdf", "language:mad", "language:cab", "language:srm", "language:toj", "language:zai", "language:guc", "language:smn", "language:ote", "language:nch", "language:prs", "language:bis", "language:cuk", "language:bzj", "language:map", "language:djk", "language:ncj", "language:mco", "language:shp", "language:ang", "language:seh", "language:ikk", "language:qvi", "language:yom", "language:top", "language:awa", "language:ike", "language:mau", "language:kum", "language:mos", "language:tly", "language:ayr", "language:tdt", "language:yap", "language:evn", "language:tah", "language:xal", "language:szy", "language:quw", "language:stq", "language:tlh", "language:otq", "language:nov", "language:skr", "language:yua", "language:raw", "language:fiu", "language:enm", "language:bbc", "language:non", "language:ber", "language:kea", "language:bua", "language:kua", "language:zza", "language:csy", "language:mnw", "language:dtp", "language:nah", "language:yao", "language:nog", "language:abt", "language:meo", "language:ame", "language:mbf", "language:chm", "language:kas", "language:crs", "language:tcy", "language:lbe", "language:cni", "language:rom", "language:zom", "language:blk", "language:efi", "language:ada", "language:koi", "language:bbj", "language:trv", "language:ach", "language:mgh", "language:gcr", "language:krl", "language:iso", "language:lki", "language:atj", "language:cmo", "language:chu", "language:gur", "language:iku", "language:sma", "language:lrc", "language:gos", "language:dty", "language:nzi", "language:btx", "language:brx", "language:bts", "language:nyu", "language:ckt", "language:guw", "language:pck", "language:quy", "language:gcf", "language:ksw", "language:nia", "language:bal", "language:nhe", "language:hwc", "language:mup", "language:dyu", "language:ami", "language:tay", "language:gaa", "language:loz", "language:abq", "language:pnt", "language:ium", "language:abs", "language:cmr", "language:shi", "language:tzm", "language:gil", "language:ewo", "language:kon", "language:sms", "language:ape", "language:tzh", "language:bci", "language:acd", "language:tab", "language:fuv", "language:swc", "language:tcz", "language:sgc", "language:aaz", "language:tvl", "language:zha", "language:pib", "language:pli", "language:bru", "language:quz", "language:cha", "language:aeu", "language:nqo", "language:mer", "language:acf", "language:rmc", "language:msi", "language:smj", "language:kng", "language:dhv", "language:doi", "language:zap", "language:hla", "language:cac", "language:pdt", "language:mbt", "language:taq", "language:bgp", "language:tyz", "language:aau", "language:mah", "language:nak", "language:kmb", "language:mjw", "language:fuf", "language:bba", "language:amu", "language:alz", "language:cop", "language:rar", "language:emp", "language:arc", "language:nyn", "language:rut", "language:lub", "language:tzj", "language:fat", "language:lzh", "language:aak", "language:nnb", "language:lhu", "language:bjv", "language:bum", "language:maq", "language:roa", "language:bvr", "language:kcg", "language:tok", "language:yrk", "language:khs", "language:rup", "language:qub", "language:jac", "language:hmr", "language:sid", "language:chr", "language:amp", "language:qug", "language:mas", "language:fkv", "language:bem", "language:cav", "language:her", "language:kwn", "language:ify", "language:gpe", "language:zpa", "language:agu", "language:ppk", "language:tiv", "language:ahk", "language:pis", "language:hns", "language:sus", "language:bon", "language:sja", "language:kri", "language:dik", "language:wrk", "language:got", "language:dar", "language:gui", "language:mak", "language:jiv", "language:kjb", "language:maz", "language:bsn", "language:dov", "language:cok", "language:rwo", "language:mag", "language:hnj", "language:krj", "language:teo", "language:enq", "language:aom", "language:ffm", "language:din", "language:ubu", "language:pwn", "language:gum", "language:sny", "language:twu", "language:med", "language:acn", "language:rme", "language:cbs", "language:abx", "language:ndc", "language:ibb", "language:pih", "language:zty", "language:rad", "language:aby", "language:zne", "language:cui", "language:lua", "language:yby", "language:bno", "language:niu", "language:agd", "language:nij", "language:agg", "language:yre", "language:fip", "language:qve", "language:tsg", "language:skg", "language:adj", "language:mfq", "language:agx", "language:kmg", "language:umb", "language:cnk", "language:nhw", "language:maa", "language:kwy", "language:jra", "language:syr", "language:inb", "language:pau", "language:xsm", "language:vap", "language:alp", "language:des", "language:syl", "language:mkn", "language:gan", "language:qwh", "language:jvn", "language:bib", "language:mpx", "language:bin", "language:klv", "language:xon", "language:jbu", "language:bdh", "language:knj", "language:ptu", "language:mmn", "language:mwq", "language:sop", "language:cgc", "language:dop", "language:mgr", "language:rmo", "language:tbc", "language:kyq", "language:zpu", "language:kkc", "language:acu", "language:ata", "language:mif", "language:tsz", "language:mbi", "language:imo", "language:fuh", "language:zyp", "language:apr", "language:att", "language:bus", "language:kqp", "language:koo", "language:bas", "language:urh", "language:bbr", "language:msy", "language:mdy", "language:nas", "language:lee", "language:mcu", "language:dig", "language:izr", "language:nfr", "language:hto", "language:mzw", "language:qxh", "language:chz", "language:guh", "language:ded", "language:bvz", "language:kkj", "language:gux", "language:ikt", "language:bnp", "language:bgt", "language:quf", "language:dwr", "language:nod", "language:yal", "language:bmr", "language:ljp", "language:xla", "language:zyb", "language:gof", "language:niv", "language:nrf", "language:npy", "language:ura", "language:dob", "language:gfk", "language:gdr", "language:sdc", "language:pjt", "language:spp", "language:irk", "language:cpa", "language:knc", "language:gvl", "language:agr", "language:njo", "language:xrb", "language:kao", "language:zpz", "language:bgr", "language:rnd", "language:ntu", "language:aai", "language:gai", "language:dgi", "language:kez", "language:dad", "language:kmh", "language:aii", "language:ifk", "language:aji", "language:noa", "language:bhl", "language:ztq", "language:gde", "language:dnj", "language:men", "language:miq", "language:isd", "language:lgg", "language:ncx", "language:gub", "language:itv", "language:tac", "language:cce", "language:kwi", "language:nhu", "language:sml", "language:pah", "language:sas", "language:cwt", "language:spy", "language:enb", "language:fai", "language:cas", "language:sue", "language:yss", "language:ozm", "language:bku", "language:biv", "language:akp", "language:dts", "language:kdr", "language:fal", "language:mmo", "language:byr", "language:cbv", "language:cbu", "language:eza", "language:kgp", "language:sda", "language:gbo", "language:mfi", "language:bdd", "language:boj", "language:blh", "language:ibg", "language:agn", "language:vmy", "language:sua", "language:gul", "language:rap", "language:bmh", "language:sxn", "language:dyi", "language:tdx", "language:car", "language:heh", "language:dgc", "language:sgb", "language:bpr", "language:gbi", "language:avu", "language:udu", "language:yli", "language:cjs", "language:gnn", "language:nhi", "language:urk", "language:kpy", "language:qup", "language:qvh", "language:pir", "language:tsc", "language:thk", "language:grt", "language:kqn", "language:hay", "language:mqb", "language:tbg", "language:bss", "language:trn", "language:jae", "language:myy", "language:ipk", "language:bao", "language:qvz", "language:dua", "language:mwv", "language:nct", "language:kyc", "language:tuo", "language:tee", "language:mop", "language:mxt", "language:qvm", "language:gkn", "language:lam", "language:ntr", "language:sbe", "language:dyo", "language:lex", "language:smk", "language:coe", "language:kpe", "language:xbi", "language:atb", "language:tcf", "language:bfo", "language:cbc", "language:swg", "language:cnt", "language:izz", "language:knf", "language:mpp", "language:kki", "language:nho", "language:kbr", "language:bmu", "language:hig", "language:qxr", "language:orv", "language:pma", "language:zpl", "language:kpr", "language:sig", "language:mxp", "language:lef", "language:mlp", "language:soq", "language:cre", "language:aey", "language:qvs", "language:sur", "language:suk", "language:cax", "language:alq", "language:chw", "language:dww", "language:gog", "language:viv", "language:qvw", "language:ted", "language:yuj", "language:ziw", "language:kto", "language:mcq", "language:sim", "language:lue", "language:cya", "language:knk", "language:tpt", "language:taj", "language:blz", "language:mil", "language:kde", "language:kpz", "language:hag", "language:vun", "language:kus", "language:lid", "language:tos", "language:bfd", "language:chd", "language:cle", "language:yon", "language:bgs", "language:lsm", "language:msb", "language:ota", "language:mxq", "language:myw", "language:aso", "language:esu", "language:kdi", "language:bhp", "language:mfz", "language:sgw", "language:xsi", "language:gun", "language:kxc", "language:mux", "language:otw", "language:cjp", "language:nyo", "language:zia", "language:cco", "language:ojb", "language:ktu", "language:cpy", "language:txu", "language:bjr", "language:bud", "language:ken", "language:bzh", "language:ipi", "language:crx", "language:cko", "language:gnd", "language:kix", "language:mmx", "language:esk", "language:kud", "language:toh", "language:byx", "language:mtp", "language:kyz", "language:lmp", "language:tiy", "language:ccp", "language:sbl", "language:tcs", "language:usp", "language:buk", "language:hvn", "language:amm", "language:kzj", "language:gng", "language:ter", "language:kij", "language:ngl", "language:pab", "language:pad", "language:kca", "language:meq", "language:niq", "language:dah", "language:lia", "language:kss", "language:bch", "language:khz", "language:nop", "language:yle", "language:ain", "language:pem", "language:yml", "language:gaw", "language:kze", "language:tby", "language:cso", "language:ifb", "language:rki", "language:aly", "language:kmu", "language:mhl", "language:kmo", "language:mva", "language:opm", "language:rtm", "language:xtn", "language:dgr", "language:ksr", "language:snp", "language:tvk", "language:zpv", "language:hrx", "language:kwj", "language:muh", "language:kak", "language:kpw", "language:akb", "language:ybb", "language:kjs", "language:wuv", "language:laj", "language:ogo", "language:nim", "language:czt", "language:aoz", "language:rro", "language:yuw", "language:heg", "language:mrw", "language:zac", "language:kpf", "language:leu", "language:nwi", "language:awx", "language:gso", "language:keo", "language:tte", "language:ceg", "language:nhy", "language:bhw", "language:gnw", "language:nin", "language:xmv", "language:crm", "language:mxv", "language:ubr", "language:gld", "language:bzi", "language:ann", "language:lac", "language:mej", "language:zpc", "language:dje", "language:caq", "language:guk", "language:wos", "language:msm", "language:zaw", "language:cap", "language:mox", "language:zab", "language:mca", "language:wrs", "language:hae", "language:nss", "language:rav", "language:uvh", "language:dga", "language:ppo", "language:arq", "language:bim", "language:lwg", "language:kms", "language:kne", "language:tkl", "language:caf", "language:zat", "language:aba", "language:chf", "language:lew", "language:npl", "language:uvl", "language:rmq", "language:mek", "language:snc", "language:nsn", "language:amn", "language:abz", "language:cek", "language:ong", "language:txq", "language:bjp", "language:gvf", "language:crk", "language:snf", "language:nhg", "language:kqw", "language:mic", "language:mie", "language:nus", "language:plu", "language:idu", "language:sll", "language:thl", "language:bef", "language:kwd", "language:mqy", "language:caa", "language:aia", "language:wer", "language:agm", "language:mbl", "language:mbs", "language:adh", "language:hub", "language:mav", "language:nab", "language:bqp", "language:guo", "language:auy", "language:big", "language:nii", "language:row", "language:kim", "language:mti", "language:otm", "language:prg", "language:icr", "language:mcp", "language:tbo", "language:chy", "language:oji", "language:kpx", "language:lbb", "language:pao", "language:xuo", "language:zgh", "language:wls", "language:aca", "language:apy", "language:wnc", "language:ssg", "language:eve", "language:mee", "language:yut", "language:kxm", "language:mur", "language:mcd", "language:cto", "language:mqj", "language:usa", "language:emi", "language:liv", "language:guz", "language:tgp", "language:ncl", "language:azg", "language:kck", "language:apb", "language:kbm", "language:sgz", "language:wsk", "language:gbm", "language:csw", "language:ctp", "language:eri", "language:vid", "language:bsq", "language:dak", "language:tif", "language:xsr", "language:mwp", "language:roo", "language:wbp", "language:gdn", "language:tgo", "language:zpm", "language:mih", "language:qvc", "language:tod", "language:abn", "language:cao", "language:kbc", "language:kog", "language:moh", "language:leh", "language:nsu", "language:okv", "language:tih", "language:zos", "language:llg", "language:gmv", "language:kyf", "language:mhx", "language:mvp", "language:naf", "language:ino", "language:dng", "language:mnk", "language:oke", "language:omw", "language:tnk", "language:xtd", "language:agt", "language:cbr", "language:eko", "language:nhk", "language:hot", "language:iou", "language:mpm", "language:myx", "language:ndh", "language:pbb", "language:rng", "language:cri", "language:bvd", "language:kmz", "language:cta", "language:blw", "language:clu", "language:cof", "language:kje", "language:nmf", "language:kbh", "language:qxn", "language:ria", "language:wed", "language:zar", "language:huv", "language:lsi", "language:msk", "language:nbq", "language:ati", "language:lww", "language:yva", "language:amr", "language:lmk", "language:tim", "language:bbb", "language:bzd", "language:djr", "language:kwf", "language:nuy", "language:poi", "language:ptp", "language:atd", "language:bps", "language:lcm", "language:mbh", "language:nuj", "language:ayp", "language:cwe", "language:geb", "language:aoi", "language:mto", "language:cbi", "language:gvn", "language:kqf", "language:rkb", "language:xed", "language:zas", "language:apz", "language:cpb", "language:ese", "language:gdg", "language:iws", "language:apu", "language:cag", "language:kdc", "language:nou", "language:too", "language:xmm", "language:beq", "language:hnn", "language:myk", "language:sby", "language:arl", "language:ncu", "language:rml", "language:gam", "language:kvn", "language:mbc", "language:mfy", "language:urt", "language:luc", "language:mio", "language:snn", "language:tar", "language:tku", "language:upv", "language:kjg", "language:btd", "language:cut", "language:mwn", "language:tue", "language:adz", "language:kyg", "language:rel", "language:tew", "language:ttc", "language:nkf", "language:yrb", "language:fub", "language:nsm", "language:nyf", "language:bkd", "language:cpc", "language:lif", "language:mwc", "language:apw", "language:azz", "language:zpo", "language:faa", "language:ood", "language:toc", "language:wmt", "language:ajg", "language:nko", "language:ssd", "language:sxb", "language:zxx", "language:not", "language:amk", "language:hch", "language:kqc", "language:aui", "language:llb", "language:avt", "language:kaq", "language:tna", "language:zpt", "language:bwd", "language:stn", "language:kgk", "language:mck", "language:bhg", "language:ifu", "language:kkl", "language:zao", "language:huu", "language:sil", "language:trq", "language:tuf", "language:wnu", "language:amf", "language:fan", "language:zdj", "language:bco", "language:kdl", "language:lln", "language:mit", "language:yaq", "language:ake", "language:ige", "language:mna", "language:nhx", "language:njn", "language:wba", "language:zaa", "language:syb", "language:qxo", "language:rgu", "language:wiu", "language:bla", "language:etr", "language:miy", "language:mjc", "language:nif", "language:pov", "language:qxl", "language:sey", "language:bxh", "language:ddg", "language:mks", "language:nki", "language:pot", "language:prf", "language:hra", "language:law", "language:plw", "language:zpi", "language:atg", "language:daf", "language:drg", "language:dru", "language:ngp", "language:boa", "language:cbt", "language:dhm", "language:ikw", "language:kqe", "language:lbj", "language:loq", "language:xsb", "language:yad", "language:kyu", "language:mcb", "language:tks", "language:cnl", "language:far", "language:miz", "language:maj", "language:mgm", "language:mib", "language:mza", "language:nhr", "language:smt", "language:ish", "language:mlu", "language:yka", "language:anv", "language:ign", "language:mir", "language:tav", "language:gyr", "language:klt", "language:apn", "language:wbm", "language:cjk", "language:dln", "language:mcf", "language:twx", "language:ldi", "language:poy", "language:yaa", "language:zae", "language:bdq", "language:con", "language:dnw", "language:gah", "language:lcp", "language:mbj", "language:xog", "language:yan", "language:sdq", "language:sgh", "language:gwi", "language:lbk", "language:ses", "language:ycn", "language:kau", "language:hix", "language:mig", "language:mlh", "language:aer", "language:amx", "language:auc", "language:cly", "language:dsh", "language:gnb", "language:neb", "language:ttt", "language:jic", "language:xtm", "language:tll", "language:apt", "language:kgr", "language:pio", "language:pmf", "language:akh", "language:box", "language:cub", "language:cux", "language:mrq", "language:bsp", "language:for", "language:kny", "language:uri", "language:zsr", "language:pce", "language:cme", "language:cot", "language:kxw", "language:omb", "language:srq", "language:vag", "language:cpu", "language:kmy", "language:ksc", "language:lai", "language:nnp", "language:ruf", "language:spm", "language:tro", "language:ttj", "language:waj", "language:raj", "language:ian", "language:ivb", "language:kmm", "language:kzf", "language:maw", "language:tuv", "language:whk", "language:aph", "language:anm", "language:mny", "language:trp", "language:are", "language:esi", "language:mhi", "language:obo", "language:bwu", "language:lwo", "language:mrg", "language:old", "language:zav", "language:snk", "language:daa", "language:fuq", "language:lud", "language:nlg", "language:sck", "language:tbl", "language:khb", "language:tpu", "language:fue", "language:tmd", "language:whg", "language:blt", "language:gqr", "language:kub", "language:ots", "language:tpp", "language:var", "language:hbb", "language:krr", "language:alj", "language:ebk", "language:goa", "language:hav", "language:kmk", "language:kqo", "language:muy", "language:njb", "language:snw", "language:wib", "language:tkr", "language:ksp", "language:lip", "language:mog", "language:nla", "language:pss", "language:zad", "language:awi", "language:frd", "language:kei", "language:kmd", "language:mim", "language:adi", "language:any", "language:arp", "language:biu", "language:bvc", "language:ghs", "language:ttq", "language:vmk", "language:zpj", "language:crl", "language:dtb", "language:dug", "language:kam", "language:nmo", "language:qva", "language:rhg", "language:taw", "language:tui", "language:uth", "language:wap", "language:zpg", "language:brb", "language:bqj", "language:cjv", "language:cnw", "language:kgf", "language:mfh", "language:mns", "language:nnw", "language:ntp", "language:oto", "language:dks", "language:mpt", "language:nmw", "language:sba", "language:sfw", "language:shu", "language:ury", "language:yrl", "language:xkg", "language:iqw", "language:kpj", "language:nfa", "language:nph", "language:nre", "language:wsg", "language:xsu", "language:nut", "language:bmk", "language:cdf", "language:enl", "language:hop", "language:ife", "language:lnd", "language:mrv", "language:nzm", "language:tem", "language:gwc", "language:udi", "language:ajz", "language:kru", "language:qvo", "language:sld", "language:yup", "language:kwu", "language:tdg", "language:ade", "language:bcw", "language:bgz", "language:cul", "language:fmu", "language:gvc", "language:ktj", "language:lis", "language:mev", "language:msc", "language:mta", "language:nbc", "language:ncq", "language:way", "language:wlv", "language:wlx", "language:jmx", "language:wni", "language:aim", "language:byv", "language:cgg", "language:fud", "language:jmc", "language:ker", "language:kia", "language:lom", "language:tnc", "language:bwx", "language:gjn", "language:guq", "language:lap", "language:mip", "language:mkl", "language:mtg", "language:mzk", "language:njm", "language:nse", "language:pne", "language:pww", "language:zam", "language:zca", "language:the", "language:dis", "language:lgl", "language:mbd", "language:mda", "language:mhy", "language:nst", "language:pkb", "language:pmq", "language:poe", "language:swk", "language:trs", "language:vot", "language:yam", "language:zpq", "language:atq", "language:bav", "language:cho", "language:chq", "language:cjo", "language:due", "language:duo", "language:etu", "language:ifa", "language:kby", "language:khq", "language:kno", "language:lem", "language:mcn", "language:mkz", "language:mnb", "language:myb", "language:niy", "language:pxm", "language:rub", "language:sju", "language:tmc", "language:tpm", "language:wob", "language:nxa", "language:sdk", "language:bhz", "language:bth", "language:crj", "language:eka", "language:khy", "language:led", "language:met", "language:mgo", "language:mus", "language:mzm", "language:naw", "language:sri", "language:tbk", "language:xbr", "language:tnl", "language:tnn", "language:awb", "language:bsc", "language:iri", "language:kpq", "language:ktm", "language:loe", "language:lun", "language:mfg", "language:moa", "language:ndj", "language:otn", "language:sjo", "language:wat", "language:bkm", "language:tuz", "language:ybi", "language:gbr", "language:gej", "language:giz", "language:gna", "language:gwr", "language:kex", "language:kle", "language:knx", "language:ktz", "language:kvj", "language:lob", "language:mhw", "language:mph", "language:pmx", "language:qus", "language:tcc", "language:azn", "language:bra", "language:gal", "language:nlv", "language:stk", "language:yux", "language:dip", "language:ivv", "language:kdj", "language:kff", "language:mnf", "language:moc", "language:mpg", "language:mua", "language:nma", "language:rim", "language:rjs", "language:rnl", "language:ssx", "language:tig", "language:urw", "language:idt", "language:mrn", "language:oki", "language:bbk", "language:bea", "language:bkq", "language:btt", "language:cou", "language:ddn", "language:did", "language:diu", "language:ilb", "language:ksj", "language:lhi", "language:ndi", "language:ngb", "language:njz", "language:nmz", "language:npo", "language:nwb", "language:pbi", "language:sbd", "language:soe", "language:tpw", "language:twb", "language:bfn", "language:boz", "language:lwl", "language:psp", "language:sgd", "language:ymp", "language:bkl", "language:bkv", "language:csk", "language:enx", "language:ess", "language:gud", "language:guu", "language:kdh", "language:krx", "language:kzn", "language:maf", "language:max", "language:mgc", "language:mvn", "language:mwm", "language:nbe", "language:nlc", "language:nxd", "language:pse", "language:sbs", "language:tlb", "language:wwa", "language:yim", "language:bkx", "language:bze", "language:kbq", "language:mry", "language:tkd", "language:ybh", "language:abi", "language:ayo", "language:bex", "language:bom", "language:bov", "language:dhg", "language:jaa", "language:kqs", "language:kqy", "language:ksb", "language:ldn", "language:log", "language:lol", "language:mfk", "language:mtj", "language:ndz", "language:ngc", "language:nio", "language:nri", "language:nuz", "language:pps", "language:shk", "language:tlj", "language:vut", "language:xnn", "language:bcc", "language:cuh", "language:hro", "language:nco", "language:nxl", "language:pex", "language:tnp", "language:vif", "language:aha", "language:avn", "language:bmv", "language:chj", "language:crt", "language:dos", "language:eto", "language:gya", "language:hlt", "language:jun", "language:ktb", "language:lgm", "language:mnx", "language:mor", "language:mug", "language:nng", "language:nnh", "language:nsa", "language:nyk", "language:otd", "language:oym", "language:phm", "language:prq", "language:saj", "language:szb", "language:tap", "language:tnr", "language:tzl", "language:wew", "language:yas", "language:yuz", "language:baw", "language:bwt", "language:bxa", "language:fli", "language:kqr", "language:lan", "language:lgr", "language:lhm", "language:mlk", "language:mve", "language:odk", "language:pea", "language:saq", "language:sea", "language:sps", "language:tio", "language:yin", "language:adl", "language:agw", "language:ald", "language:asg", "language:bnj", "language:bwi", "language:bwq", "language:dbq", "language:dow", "language:fad", "language:hoc", "language:kql", "language:ksf", "language:lea", "language:mse", "language:mzl", "language:nhd", "language:nnl", "language:nwx", "language:pbc", "language:pny", "language:tul", "language:aaa", "language:abc", "language:agq", "language:ags", "language:azo", "language:bag", "language:bax", "language:bce", "language:bfm", "language:bgf", "language:bhs", "language:bkc", "language:bkh", "language:bob", "language:bqm", "language:bri", "language:brv", "language:buo", "language:bya", "language:chp", "language:cim", "language:clo", "language:cuv", "language:dmg", "language:dtr", "language:eee", "language:ekm", "language:enc", "language:gbj", "language:gou", "language:hao", "language:hna", "language:hre", "language:isu", "language:jgo", "language:kbx", "language:kvt", "language:kxp", "language:lfa", "language:lkb", "language:lns", "language:loh", "language:lts", "language:luy", "language:mdr", "language:mfj", "language:mgg", "language:mgq", "language:mle", "language:mlw", "language:mmu", "language:mne", "language:muv", "language:mxu", "language:nge", "language:ngn", "language:njy", "language:nsk", "language:nwe", "language:nza", "language:pcg", "language:pdu", "language:pnz", "language:pwg", "language:qaa", "language:snl", "language:sox", "language:ssn", "language:syw", "language:tbj", "language:tdb", "language:thy", "language:tnt", "language:tom", "language:tpl", "language:tsb", "language:tvs", "language:udg", "language:unr", "language:wbr", "language:wms", "language:wnk", "language:wtk", "language:xmd", "language:xmg", "language:xty", "language:yav", "language:yea", "language:zuh", "license:other", "arxiv:2502.11546", "region:us", "multilingual" ]

null

"2025-03-25T04:55:24Z"

--- license: other pretty_name: dcad-2000 license_name: license license_link: LICENSE configs: - config_name: eng_Latn data_files: - split: train path: eng_Latn/*_keep.jsonl - config_name: rus_Cyrl data_files: - split: train path: rus_Cyrl/*_keep.jsonl - config_name: cmn_Hani data_files: - split: train path: cmn_Hani/*_keep.jsonl - config_name: deu_Latn data_files: - split: train path: deu_Latn/*_keep.jsonl - config_name: spa_Latn data_files: - split: train path: spa_Latn/*_keep.jsonl - config_name: fra_Latn data_files: - split: train path: fra_Latn/*_keep.jsonl - config_name: jpn_Jpan data_files: - split: train path: jpn_Jpan/*_keep.jsonl - config_name: ita_Latn data_files: - split: train path: ita_Latn/*_keep.jsonl - config_name: por_Latn data_files: - split: train path: por_Latn/*_keep.jsonl - config_name: pol_Latn data_files: - split: train path: pol_Latn/*_keep.jsonl - config_name: nld_Latn data_files: - split: train path: nld_Latn/*_keep.jsonl - config_name: ind_Latn data_files: - split: train path: ind_Latn/*_keep.jsonl - config_name: tur_Latn data_files: - split: train path: tur_Latn/*_keep.jsonl - config_name: vie_Latn data_files: - split: train path: vie_Latn/*_keep.jsonl - config_name: fas_Arab data_files: - split: train path: fas_Arab/*_keep.jsonl - config_name: kor_Hang data_files: - split: train path: kor_Hang/*_keep.jsonl - config_name: swe_Latn data_files: - split: train path: swe_Latn/*_keep.jsonl - config_name: hun_Latn data_files: - split: train path: hun_Latn/*_keep.jsonl - config_name: ell_Grek data_files: - split: train path: ell_Grek/*_keep.jsonl - config_name: ukr_Cyrl data_files: - split: train path: ukr_Cyrl/*_keep.jsonl - config_name: tha_Thai data_files: - split: train path: tha_Thai/*_keep.jsonl - config_name: aze_Latn data_files: - split: train path: aze_Latn/*_keep.jsonl - config_name: arb_Arab data_files: - split: train path: arb_Arab/*_keep.jsonl - config_name: slv_Latn data_files: - split: train path: slv_Latn/*_keep.jsonl - config_name: cat_Latn data_files: - split: train path: cat_Latn/*_keep.jsonl - config_name: fin_Latn data_files: - split: train path: fin_Latn/*_keep.jsonl - config_name: hbs_Latn data_files: - split: train path: hbs_Latn/*_keep.jsonl - config_name: ces_Latn data_files: - split: train path: ces_Latn/*_keep.jsonl - config_name: fil_Latn data_files: - split: train path: fil_Latn/*_keep.jsonl - config_name: guj_Gujr data_files: - split: train path: guj_Gujr/*_keep.jsonl - config_name: nob_Latn data_files: - split: train path: nob_Latn/*_keep.jsonl - config_name: mal_Mlym data_files: - split: train path: mal_Mlym/*_keep.jsonl - config_name: bul_Cyrl data_files: - split: train path: bul_Cyrl/*_keep.jsonl - config_name: kan_Knda data_files: - split: train path: kan_Knda/*_keep.jsonl - config_name: hin_Deva data_files: - split: train path: hin_Deva/*_keep.jsonl - config_name: tam_Taml data_files: - split: train path: tam_Taml/*_keep.jsonl - config_name: ara_Arab data_files: - split: train path: ara_Arab/*_keep.jsonl - config_name: kaz_Cyrl data_files: - split: train path: kaz_Cyrl/*_keep.jsonl - config_name: sqi_Latn data_files: - split: train path: sqi_Latn/*_keep.jsonl - config_name: pan_Guru data_files: - split: train path: pan_Guru/*_keep.jsonl - config_name: est_Latn data_files: - split: train path: est_Latn/*_keep.jsonl - config_name: srp_Cyrl data_files: - split: train path: srp_Cyrl/*_keep.jsonl - config_name: heb_Hebr data_files: - split: train path: heb_Hebr/*_keep.jsonl - config_name: isl_Latn data_files: - split: train path: isl_Latn/*_keep.jsonl - config_name: mlt_Latn data_files: - split: train path: mlt_Latn/*_keep.jsonl - config_name: mkd_Cyrl data_files: - split: train path: mkd_Cyrl/*_keep.jsonl - config_name: bos_Latn data_files: - split: train path: bos_Latn/*_keep.jsonl - config_name: lit_Latn data_files: - split: train path: lit_Latn/*_keep.jsonl - config_name: kat_Geor data_files: - split: train path: kat_Geor/*_keep.jsonl - config_name: hrv_Latn data_files: - split: train path: hrv_Latn/*_keep.jsonl - config_name: ben_Beng data_files: - split: train path: ben_Beng/*_keep.jsonl - config_name: glg_Latn data_files: - split: train path: glg_Latn/*_keep.jsonl - config_name: ceb_Latn data_files: - split: train path: ceb_Latn/*_keep.jsonl - config_name: ron_Latn data_files: - split: train path: ron_Latn/*_keep.jsonl - config_name: msa_Latn data_files: - split: train path: msa_Latn/*_keep.jsonl - config_name: hye_Armn data_files: - split: train path: hye_Armn/*_keep.jsonl - config_name: tgk_Cyrl data_files: - split: train path: tgk_Cyrl/*_keep.jsonl - config_name: mar_Deva data_files: - split: train path: mar_Deva/*_keep.jsonl - config_name: bel_Cyrl data_files: - split: train path: bel_Cyrl/*_keep.jsonl - config_name: nep_Deva data_files: - split: train path: nep_Deva/*_keep.jsonl - config_name: urd_Arab data_files: - split: train path: urd_Arab/*_keep.jsonl - config_name: slk_Latn data_files: - split: train path: slk_Latn/*_keep.jsonl - config_name: mon_Cyrl data_files: - split: train path: mon_Cyrl/*_keep.jsonl - config_name: swa_Latn data_files: - split: train path: swa_Latn/*_keep.jsonl - config_name: dan_Latn data_files: - split: train path: dan_Latn/*_keep.jsonl - config_name: eus_Latn data_files: - split: train path: eus_Latn/*_keep.jsonl - config_name: azj_Latn data_files: - split: train path: azj_Latn/*_keep.jsonl - config_name: sin_Sinh data_files: - split: train path: sin_Sinh/*_keep.jsonl - config_name: lat_Latn data_files: - split: train path: lat_Latn/*_keep.jsonl - config_name: als_Latn data_files: - split: train path: als_Latn/*_keep.jsonl - config_name: tel_Telu data_files: - split: train path: tel_Telu/*_keep.jsonl - config_name: afr_Latn data_files: - split: train path: afr_Latn/*_keep.jsonl - config_name: ekk_Latn data_files: - split: train path: ekk_Latn/*_keep.jsonl - config_name: ltz_Latn data_files: - split: train path: ltz_Latn/*_keep.jsonl - config_name: zsm_Latn data_files: - split: train path: zsm_Latn/*_keep.jsonl - config_name: som_Latn data_files: - split: train path: som_Latn/*_keep.jsonl - config_name: cym_Latn data_files: - split: train path: cym_Latn/*_keep.jsonl - config_name: und_Kana data_files: - split: train path: und_Kana/*_keep.jsonl - config_name: kir_Cyrl data_files: - split: train path: kir_Cyrl/*_keep.jsonl - config_name: nor_Latn data_files: - split: train path: nor_Latn/*_keep.jsonl - config_name: uzb_Latn data_files: - split: train path: uzb_Latn/*_keep.jsonl - config_name: mya_Mymr data_files: - split: train path: mya_Mymr/*_keep.jsonl - config_name: epo_Latn data_files: - split: train path: epo_Latn/*_keep.jsonl - config_name: hau_Latn data_files: - split: train path: hau_Latn/*_keep.jsonl - config_name: ary_Arab data_files: - split: train path: ary_Arab/*_keep.jsonl - config_name: gle_Latn data_files: - split: train path: gle_Latn/*_keep.jsonl - config_name: lvs_Latn data_files: - split: train path: lvs_Latn/*_keep.jsonl - config_name: nno_Latn data_files: - split: train path: nno_Latn/*_keep.jsonl - config_name: und_Bamu data_files: - split: train path: und_Bamu/*_keep.jsonl - config_name: ory_Orya data_files: - split: train path: ory_Orya/*_keep.jsonl - config_name: amh_Ethi data_files: - split: train path: amh_Ethi/*_keep.jsonl - config_name: tat_Cyrl data_files: - split: train path: tat_Cyrl/*_keep.jsonl - config_name: khm_Khmr data_files: - split: train path: khm_Khmr/*_keep.jsonl - config_name: und_Copt data_files: - split: train path: und_Copt/*_keep.jsonl - config_name: und_Tang data_files: - split: train path: und_Tang/*_keep.jsonl - config_name: und_Xsux data_files: - split: train path: und_Xsux/*_keep.jsonl - config_name: arz_Arab data_files: - split: train path: arz_Arab/*_keep.jsonl - config_name: pus_Arab data_files: - split: train path: pus_Arab/*_keep.jsonl - config_name: lav_Latn data_files: - split: train path: lav_Latn/*_keep.jsonl - config_name: hbs_Cyrl data_files: - split: train path: hbs_Cyrl/*_keep.jsonl - config_name: und_Yiii data_files: - split: train path: und_Yiii/*_keep.jsonl - config_name: war_Latn data_files: - split: train path: war_Latn/*_keep.jsonl - config_name: multi_Latn data_files: - split: train path: multi_Latn/*_keep.jsonl - config_name: und_Hira data_files: - split: train path: und_Hira/*_keep.jsonl - config_name: mlg_Latn data_files: - split: train path: mlg_Latn/*_keep.jsonl - config_name: uzn_Cyrl data_files: - split: train path: uzn_Cyrl/*_keep.jsonl - config_name: hat_Latn data_files: - split: train path: hat_Latn/*_keep.jsonl - config_name: zul_Latn data_files: - split: train path: zul_Latn/*_keep.jsonl - config_name: kur_Latn data_files: - split: train path: kur_Latn/*_keep.jsonl - config_name: tgl_Latn data_files: - split: train path: tgl_Latn/*_keep.jsonl - config_name: uzb_Cyrl data_files: - split: train path: uzb_Cyrl/*_keep.jsonl - config_name: div_Thaa data_files: - split: train path: div_Thaa/*_keep.jsonl - config_name: und_Laoo data_files: - split: train path: und_Laoo/*_keep.jsonl - config_name: fry_Latn data_files: - split: train path: fry_Latn/*_keep.jsonl - config_name: sna_Latn data_files: - split: train path: sna_Latn/*_keep.jsonl - config_name: und_Cyrl data_files: - split: train path: und_Cyrl/*_keep.jsonl - config_name: fao_Latn data_files: - split: train path: fao_Latn/*_keep.jsonl - config_name: sun_Latn data_files: - split: train path: sun_Latn/*_keep.jsonl - config_name: und_Kits data_files: - split: train path: und_Kits/*_keep.jsonl - config_name: und_Hluw data_files: - split: train path: und_Hluw/*_keep.jsonl - config_name: snd_Arab data_files: - split: train path: snd_Arab/*_keep.jsonl - config_name: cos_Latn data_files: - split: train path: cos_Latn/*_keep.jsonl - config_name: bak_Cyrl data_files: - split: train path: bak_Cyrl/*_keep.jsonl - config_name: ckb_Arab data_files: - split: train path: ckb_Arab/*_keep.jsonl - config_name: asm_Beng data_files: - split: train path: asm_Beng/*_keep.jsonl - config_name: und_Grek data_files: - split: train path: und_Grek/*_keep.jsonl - config_name: jpn_Japn data_files: - split: train path: jpn_Japn/*_keep.jsonl - config_name: ast_Latn data_files: - split: train path: ast_Latn/*_keep.jsonl - config_name: ibo_Latn data_files: - split: train path: ibo_Latn/*_keep.jsonl - config_name: mri_Latn data_files: - split: train path: mri_Latn/*_keep.jsonl - config_name: und_Lina data_files: - split: train path: und_Lina/*_keep.jsonl - config_name: ars_Arab data_files: - split: train path: ars_Arab/*_keep.jsonl - config_name: und_Shrd data_files: - split: train path: und_Shrd/*_keep.jsonl - config_name: anp_Deva data_files: - split: train path: anp_Deva/*_keep.jsonl - config_name: khk_Cyrl data_files: - split: train path: khk_Cyrl/*_keep.jsonl - config_name: und_Samr data_files: - split: train path: und_Samr/*_keep.jsonl - config_name: lao_Laoo data_files: - split: train path: lao_Laoo/*_keep.jsonl - config_name: ori_Orya data_files: - split: train path: ori_Orya/*_keep.jsonl - config_name: und_Cans data_files: - split: train path: und_Cans/*_keep.jsonl - config_name: yid_Hebr data_files: - split: train path: yid_Hebr/*_keep.jsonl - config_name: hmn_Latn data_files: - split: train path: hmn_Latn/*_keep.jsonl - config_name: jav_Latn data_files: - split: train path: jav_Latn/*_keep.jsonl - config_name: nya_Latn data_files: - split: train path: nya_Latn/*_keep.jsonl - config_name: und_Mend data_files: - split: train path: und_Mend/*_keep.jsonl - config_name: und_Adlm data_files: - split: train path: und_Adlm/*_keep.jsonl - config_name: und_Egyp data_files: - split: train path: und_Egyp/*_keep.jsonl - config_name: tir_Ethi data_files: - split: train path: tir_Ethi/*_keep.jsonl - config_name: uig_Arab data_files: - split: train path: uig_Arab/*_keep.jsonl - config_name: wln_Latn data_files: - split: train path: wln_Latn/*_keep.jsonl - config_name: und_Syrc data_files: - split: train path: und_Syrc/*_keep.jsonl - config_name: yor_Latn data_files: - split: train path: yor_Latn/*_keep.jsonl - config_name: swh_Latn data_files: - split: train path: swh_Latn/*_keep.jsonl - config_name: gla_Latn data_files: - split: train path: gla_Latn/*_keep.jsonl - config_name: xho_Latn data_files: - split: train path: xho_Latn/*_keep.jsonl - config_name: uzn_Latn data_files: - split: train path: uzn_Latn/*_keep.jsonl - config_name: bre_Latn data_files: - split: train path: bre_Latn/*_keep.jsonl - config_name: sot_Latn data_files: - split: train path: sot_Latn/*_keep.jsonl - config_name: che_Cyrl data_files: - split: train path: che_Cyrl/*_keep.jsonl - config_name: nan_Latn data_files: - split: train path: nan_Latn/*_keep.jsonl - config_name: tel_Latn data_files: - split: train path: tel_Latn/*_keep.jsonl - config_name: bew_Latn data_files: - split: train path: bew_Latn/*_keep.jsonl - config_name: glk_Arab data_files: - split: train path: glk_Arab/*_keep.jsonl - config_name: smo_Latn data_files: - split: train path: smo_Latn/*_keep.jsonl - config_name: orm_Latn data_files: - split: train path: orm_Latn/*_keep.jsonl - config_name: zho_Hani data_files: - split: train path: zho_Hani/*_keep.jsonl - config_name: haw_Latn data_files: - split: train path: haw_Latn/*_keep.jsonl - config_name: pnb_Arab data_files: - split: train path: pnb_Arab/*_keep.jsonl - config_name: und_Linb data_files: - split: train path: und_Linb/*_keep.jsonl - config_name: oci_Latn data_files: - split: train path: oci_Latn/*_keep.jsonl - config_name: chv_Cyrl data_files: - split: train path: chv_Cyrl/*_keep.jsonl - config_name: kin_Latn data_files: - split: train path: kin_Latn/*_keep.jsonl - config_name: und_Brai data_files: - split: train path: und_Brai/*_keep.jsonl - config_name: srp_Latn data_files: - split: train path: srp_Latn/*_keep.jsonl - config_name: und_Hung data_files: - split: train path: und_Hung/*_keep.jsonl - config_name: und_Sgnw data_files: - split: train path: und_Sgnw/*_keep.jsonl - config_name: pcm_Latn data_files: - split: train path: pcm_Latn/*_keep.jsonl - config_name: kaa_Cyrl data_files: - split: train path: kaa_Cyrl/*_keep.jsonl - config_name: lug_Latn data_files: - split: train path: lug_Latn/*_keep.jsonl - config_name: pbt_Arab data_files: - split: train path: pbt_Arab/*_keep.jsonl - config_name: aze_Arab data_files: - split: train path: aze_Arab/*_keep.jsonl - config_name: gsw_Latn data_files: - split: train path: gsw_Latn/*_keep.jsonl - config_name: min_Latn data_files: - split: train path: min_Latn/*_keep.jsonl - config_name: tuk_Latn data_files: - split: train path: tuk_Latn/*_keep.jsonl - config_name: lim_Latn data_files: - split: train path: lim_Latn/*_keep.jsonl - config_name: kmr_Latn data_files: - split: train path: kmr_Latn/*_keep.jsonl - config_name: und_Nshu data_files: - split: train path: und_Nshu/*_keep.jsonl - config_name: roh_Latn data_files: - split: train path: roh_Latn/*_keep.jsonl - config_name: und_Bali data_files: - split: train path: und_Bali/*_keep.jsonl - config_name: und_Lana data_files: - split: train path: und_Lana/*_keep.jsonl - config_name: vec_Latn data_files: - split: train path: vec_Latn/*_keep.jsonl - config_name: san_Deva data_files: - split: train path: san_Deva/*_keep.jsonl - config_name: und_Modi data_files: - split: train path: und_Modi/*_keep.jsonl - config_name: gmh_Latn data_files: - split: train path: gmh_Latn/*_keep.jsonl - config_name: nds_Latn data_files: - split: train path: nds_Latn/*_keep.jsonl - config_name: sco_Latn data_files: - split: train path: sco_Latn/*_keep.jsonl - config_name: und_Mong data_files: - split: train path: und_Mong/*_keep.jsonl - config_name: und_Ethi data_files: - split: train path: und_Ethi/*_keep.jsonl - config_name: azb_Arab data_files: - split: train path: azb_Arab/*_keep.jsonl - config_name: tsn_Latn data_files: - split: train path: tsn_Latn/*_keep.jsonl - config_name: rus_Latn data_files: - split: train path: rus_Latn/*_keep.jsonl - config_name: und_Hebr data_files: - split: train path: und_Hebr/*_keep.jsonl - config_name: mon_Latn data_files: - split: train path: mon_Latn/*_keep.jsonl - config_name: und_Saur data_files: - split: train path: und_Saur/*_keep.jsonl - config_name: tgk_Latn data_files: - split: train path: tgk_Latn/*_keep.jsonl - config_name: sah_Cyrl data_files: - split: train path: sah_Cyrl/*_keep.jsonl - config_name: pri_Latn data_files: - split: train path: pri_Latn/*_keep.jsonl - config_name: pap_Latn data_files: - split: train path: pap_Latn/*_keep.jsonl - config_name: plt_Latn data_files: - split: train path: plt_Latn/*_keep.jsonl - config_name: lmo_Latn data_files: - split: train path: lmo_Latn/*_keep.jsonl - config_name: bod_Tibt data_files: - split: train path: bod_Tibt/*_keep.jsonl - config_name: und_Vaii data_files: - split: train path: und_Vaii/*_keep.jsonl - config_name: yue_Hani data_files: - split: train path: yue_Hani/*_keep.jsonl - config_name: und_Dupl data_files: - split: train path: und_Dupl/*_keep.jsonl - config_name: und_Glag data_files: - split: train path: und_Glag/*_keep.jsonl - config_name: und_Thai data_files: - split: train path: und_Thai/*_keep.jsonl - config_name: bar_Latn data_files: - split: train path: bar_Latn/*_keep.jsonl - config_name: und_Thaa data_files: - split: train path: und_Thaa/*_keep.jsonl - config_name: hif_Latn data_files: - split: train path: hif_Latn/*_keep.jsonl - config_name: und_Runr data_files: - split: train path: und_Runr/*_keep.jsonl - config_name: arg_Latn data_files: - split: train path: arg_Latn/*_keep.jsonl - config_name: pms_Latn data_files: - split: train path: pms_Latn/*_keep.jsonl - config_name: kat_Latn data_files: - split: train path: kat_Latn/*_keep.jsonl - config_name: nrm_Latn data_files: - split: train path: nrm_Latn/*_keep.jsonl - config_name: vol_Latn data_files: - split: train path: vol_Latn/*_keep.jsonl - config_name: aeb_Arab data_files: - split: train path: aeb_Arab/*_keep.jsonl - config_name: und_Khmr data_files: - split: train path: und_Khmr/*_keep.jsonl - config_name: und_Geor data_files: - split: train path: und_Geor/*_keep.jsonl - config_name: ido_Latn data_files: - split: train path: ido_Latn/*_keep.jsonl - config_name: pam_Latn data_files: - split: train path: pam_Latn/*_keep.jsonl - config_name: kal_Latn data_files: - split: train path: kal_Latn/*_keep.jsonl - config_name: und_Dsrt data_files: - split: train path: und_Dsrt/*_keep.jsonl - config_name: und_Tibt data_files: - split: train path: und_Tibt/*_keep.jsonl - config_name: und_Mymr data_files: - split: train path: und_Mymr/*_keep.jsonl - config_name: lus_Latn data_files: - split: train path: lus_Latn/*_keep.jsonl - config_name: und_Armn data_files: - split: train path: und_Armn/*_keep.jsonl - config_name: und_Mroo data_files: - split: train path: und_Mroo/*_keep.jsonl - config_name: und_Bopo data_files: - split: train path: und_Bopo/*_keep.jsonl - config_name: new_Deva data_files: - split: train path: new_Deva/*_keep.jsonl - config_name: sme_Latn data_files: - split: train path: sme_Latn/*_keep.jsonl - config_name: und_Khar data_files: - split: train path: und_Khar/*_keep.jsonl - config_name: und_Mtei data_files: - split: train path: und_Mtei/*_keep.jsonl - config_name: nso_Latn data_files: - split: train path: nso_Latn/*_keep.jsonl - config_name: lld_Latn data_files: - split: train path: lld_Latn/*_keep.jsonl - config_name: ina_Latn data_files: - split: train path: ina_Latn/*_keep.jsonl - config_name: scn_Latn data_files: - split: train path: scn_Latn/*_keep.jsonl - config_name: und_Deva data_files: - split: train path: und_Deva/*_keep.jsonl - config_name: und_Brah data_files: - split: train path: und_Brah/*_keep.jsonl - config_name: und_Bhks data_files: - split: train path: und_Bhks/*_keep.jsonl - config_name: hyw_Armn data_files: - split: train path: hyw_Armn/*_keep.jsonl - config_name: abk_Cyrl data_files: - split: train path: abk_Cyrl/*_keep.jsonl - config_name: bew_Cyrl data_files: - split: train path: bew_Cyrl/*_keep.jsonl - config_name: und_Telu data_files: - split: train path: und_Telu/*_keep.jsonl - config_name: und_Merc data_files: - split: train path: und_Merc/*_keep.jsonl - config_name: bpy_Beng data_files: - split: train path: bpy_Beng/*_keep.jsonl - config_name: tgk_Arab data_files: - split: train path: tgk_Arab/*_keep.jsonl - config_name: lin_Latn data_files: - split: train path: lin_Latn/*_keep.jsonl - config_name: oss_Cyrl data_files: - split: train path: oss_Cyrl/*_keep.jsonl - config_name: que_Latn data_files: - split: train path: que_Latn/*_keep.jsonl - config_name: szl_Latn data_files: - split: train path: szl_Latn/*_keep.jsonl - config_name: sdh_Arab data_files: - split: train path: sdh_Arab/*_keep.jsonl - config_name: mww_Latn data_files: - split: train path: mww_Latn/*_keep.jsonl - config_name: mhr_Cyrl data_files: - split: train path: mhr_Cyrl/*_keep.jsonl - config_name: und_Hmnp data_files: - split: train path: und_Hmnp/*_keep.jsonl - config_name: und_Orya data_files: - split: train path: und_Orya/*_keep.jsonl - config_name: und_Kali data_files: - split: train path: und_Kali/*_keep.jsonl - config_name: rmy_Latn data_files: - split: train path: rmy_Latn/*_keep.jsonl - config_name: diq_Latn data_files: - split: train path: diq_Latn/*_keep.jsonl - config_name: srd_Latn data_files: - split: train path: srd_Latn/*_keep.jsonl - config_name: und_Plrd data_files: - split: train path: und_Plrd/*_keep.jsonl - config_name: und_Phag data_files: - split: train path: und_Phag/*_keep.jsonl - config_name: ydd_Hebr data_files: - split: train path: ydd_Hebr/*_keep.jsonl - config_name: und_Hmng data_files: - split: train path: und_Hmng/*_keep.jsonl - config_name: run_Latn data_files: - split: train path: run_Latn/*_keep.jsonl - config_name: und_Nkoo data_files: - split: train path: und_Nkoo/*_keep.jsonl - config_name: hsb_Latn data_files: - split: train path: hsb_Latn/*_keep.jsonl - config_name: und_Lisu data_files: - split: train path: und_Lisu/*_keep.jsonl - config_name: wol_Latn data_files: - split: train path: wol_Latn/*_keep.jsonl - config_name: und_Gran data_files: - split: train path: und_Gran/*_keep.jsonl - config_name: urd_Latn data_files: - split: train path: urd_Latn/*_keep.jsonl - config_name: und_Cher data_files: - split: train path: und_Cher/*_keep.jsonl - config_name: kiu_Latn data_files: - split: train path: kiu_Latn/*_keep.jsonl - config_name: ilo_Latn data_files: - split: train path: ilo_Latn/*_keep.jsonl - config_name: und_Taml data_files: - split: train path: und_Taml/*_keep.jsonl - config_name: cak_Latn data_files: - split: train path: cak_Latn/*_keep.jsonl - config_name: und_Gonm data_files: - split: train path: und_Gonm/*_keep.jsonl - config_name: acm_Arab data_files: - split: train path: acm_Arab/*_keep.jsonl - config_name: und_Tnsa data_files: - split: train path: und_Tnsa/*_keep.jsonl - config_name: und_Cprt data_files: - split: train path: und_Cprt/*_keep.jsonl - config_name: grc_Grek data_files: - split: train path: grc_Grek/*_keep.jsonl - config_name: xmf_Geor data_files: - split: train path: xmf_Geor/*_keep.jsonl - config_name: vls_Latn data_files: - split: train path: vls_Latn/*_keep.jsonl - config_name: und_Gujr data_files: - split: train path: und_Gujr/*_keep.jsonl - config_name: und_Cari data_files: - split: train path: und_Cari/*_keep.jsonl - config_name: tso_Latn data_files: - split: train path: tso_Latn/*_keep.jsonl - config_name: crh_Latn data_files: - split: train path: crh_Latn/*_keep.jsonl - config_name: nav_Latn data_files: - split: train path: nav_Latn/*_keep.jsonl - config_name: mwl_Latn data_files: - split: train path: mwl_Latn/*_keep.jsonl - config_name: und_Diak data_files: - split: train path: und_Diak/*_keep.jsonl - config_name: tat_Latn data_files: - split: train path: tat_Latn/*_keep.jsonl - config_name: grn_Latn data_files: - split: train path: grn_Latn/*_keep.jsonl - config_name: mui_Latn data_files: - split: train path: mui_Latn/*_keep.jsonl - config_name: hin_Latn data_files: - split: train path: hin_Latn/*_keep.jsonl - config_name: mvf_Mong data_files: - split: train path: mvf_Mong/*_keep.jsonl - config_name: udm_Cyrl data_files: - split: train path: udm_Cyrl/*_keep.jsonl - config_name: mzn_Arab data_files: - split: train path: mzn_Arab/*_keep.jsonl - config_name: und_Marc data_files: - split: train path: und_Marc/*_keep.jsonl - config_name: und_Talu data_files: - split: train path: und_Talu/*_keep.jsonl - config_name: und_Vith data_files: - split: train path: und_Vith/*_keep.jsonl - config_name: bcl_Latn data_files: - split: train path: bcl_Latn/*_keep.jsonl - config_name: und_Nagm data_files: - split: train path: und_Nagm/*_keep.jsonl - config_name: und_Mani data_files: - split: train path: und_Mani/*_keep.jsonl - config_name: ban_Latn data_files: - split: train path: ban_Latn/*_keep.jsonl - config_name: und_Mlym data_files: - split: train path: und_Mlym/*_keep.jsonl - config_name: afb_Arab data_files: - split: train path: afb_Arab/*_keep.jsonl - config_name: und_Java data_files: - split: train path: und_Java/*_keep.jsonl - config_name: cnh_Latn data_files: - split: train path: cnh_Latn/*_keep.jsonl - config_name: und_Ahom data_files: - split: train path: und_Ahom/*_keep.jsonl - config_name: cbk_Latn data_files: - split: train path: cbk_Latn/*_keep.jsonl - config_name: kaa_Latn data_files: - split: train path: kaa_Latn/*_keep.jsonl - config_name: tyv_Cyrl data_files: - split: train path: tyv_Cyrl/*_keep.jsonl - config_name: kur_Arab data_files: - split: train path: kur_Arab/*_keep.jsonl - config_name: ful_Latn data_files: - split: train path: ful_Latn/*_keep.jsonl - config_name: und_Beng data_files: - split: train path: und_Beng/*_keep.jsonl - config_name: zea_Latn data_files: - split: train path: zea_Latn/*_keep.jsonl - config_name: frp_Latn data_files: - split: train path: frp_Latn/*_keep.jsonl - config_name: frr_Latn data_files: - split: train path: frr_Latn/*_keep.jsonl - config_name: pfl_Latn data_files: - split: train path: pfl_Latn/*_keep.jsonl - config_name: lij_Latn data_files: - split: train path: lij_Latn/*_keep.jsonl - config_name: apc_Arab data_files: - split: train path: apc_Arab/*_keep.jsonl - config_name: mai_Deva data_files: - split: train path: mai_Deva/*_keep.jsonl - config_name: und_Wara data_files: - split: train path: und_Wara/*_keep.jsonl - config_name: und_Palm data_files: - split: train path: und_Palm/*_keep.jsonl - config_name: pon_Latn data_files: - split: train path: pon_Latn/*_keep.jsonl - config_name: bak_Latn data_files: - split: train path: bak_Latn/*_keep.jsonl - config_name: eml_Latn data_files: - split: train path: eml_Latn/*_keep.jsonl - config_name: uzs_Arab data_files: - split: train path: uzs_Arab/*_keep.jsonl - config_name: nde_Latn data_files: - split: train path: nde_Latn/*_keep.jsonl - config_name: hil_Latn data_files: - split: train path: hil_Latn/*_keep.jsonl - config_name: mam_Latn data_files: - split: train path: mam_Latn/*_keep.jsonl - config_name: gom_Latn data_files: - split: train path: gom_Latn/*_keep.jsonl - config_name: dag_Latn data_files: - split: train path: dag_Latn/*_keep.jsonl - config_name: nap_Latn data_files: - split: train path: nap_Latn/*_keep.jsonl - config_name: bjn_Latn data_files: - split: train path: bjn_Latn/*_keep.jsonl - config_name: und_Khoj data_files: - split: train path: und_Khoj/*_keep.jsonl - config_name: hbo_Hebr data_files: - split: train path: hbo_Hebr/*_keep.jsonl - config_name: tet_Latn data_files: - split: train path: tet_Latn/*_keep.jsonl - config_name: inh_Cyrl data_files: - split: train path: inh_Cyrl/*_keep.jsonl - config_name: ven_Latn data_files: - split: train path: ven_Latn/*_keep.jsonl - config_name: gaz_Latn data_files: - split: train path: gaz_Latn/*_keep.jsonl - config_name: tpi_Latn data_files: - split: train path: tpi_Latn/*_keep.jsonl - config_name: und_Sidd data_files: - split: train path: und_Sidd/*_keep.jsonl - config_name: ajp_Arab data_files: - split: train path: ajp_Arab/*_keep.jsonl - config_name: sat_Olck data_files: - split: train path: sat_Olck/*_keep.jsonl - config_name: wuu_Hani data_files: - split: train path: wuu_Hani/*_keep.jsonl - config_name: bam_Latn data_files: - split: train path: bam_Latn/*_keep.jsonl - config_name: vep_Latn data_files: - split: train path: vep_Latn/*_keep.jsonl - config_name: glv_Latn data_files: - split: train path: glv_Latn/*_keep.jsonl - config_name: tzo_Latn data_files: - split: train path: tzo_Latn/*_keep.jsonl - config_name: bik_Latn data_files: - split: train path: bik_Latn/*_keep.jsonl - config_name: und_Rohg data_files: - split: train path: und_Rohg/*_keep.jsonl - config_name: acr_Latn data_files: - split: train path: acr_Latn/*_keep.jsonl - config_name: twi_Latn data_files: - split: train path: twi_Latn/*_keep.jsonl - config_name: myv_Cyrl data_files: - split: train path: myv_Cyrl/*_keep.jsonl - config_name: ewe_Latn data_files: - split: train path: ewe_Latn/*_keep.jsonl - config_name: poh_Latn data_files: - split: train path: poh_Latn/*_keep.jsonl - config_name: und_Avst data_files: - split: train path: und_Avst/*_keep.jsonl - config_name: ile_Latn data_files: - split: train path: ile_Latn/*_keep.jsonl - config_name: rue_Cyrl data_files: - split: train path: rue_Cyrl/*_keep.jsonl - config_name: und_Ougr data_files: - split: train path: und_Ougr/*_keep.jsonl - config_name: und_Wcho data_files: - split: train path: und_Wcho/*_keep.jsonl - config_name: ace_Latn data_files: - split: train path: ace_Latn/*_keep.jsonl - config_name: kha_Latn data_files: - split: train path: kha_Latn/*_keep.jsonl - config_name: und_Yezi data_files: - split: train path: und_Yezi/*_keep.jsonl - config_name: und_Ital data_files: - split: train path: und_Ital/*_keep.jsonl - config_name: und_Kthi data_files: - split: train path: und_Kthi/*_keep.jsonl - config_name: und_Takr data_files: - split: train path: und_Takr/*_keep.jsonl - config_name: ksh_Latn data_files: - split: train path: ksh_Latn/*_keep.jsonl - config_name: hui_Latn data_files: - split: train path: hui_Latn/*_keep.jsonl - config_name: gor_Latn data_files: - split: train path: gor_Latn/*_keep.jsonl - config_name: krc_Cyrl data_files: - split: train path: krc_Cyrl/*_keep.jsonl - config_name: lfn_Latn data_files: - split: train path: lfn_Latn/*_keep.jsonl - config_name: tls_Latn data_files: - split: train path: tls_Latn/*_keep.jsonl - config_name: fur_Latn data_files: - split: train path: fur_Latn/*_keep.jsonl - config_name: und_Tavt data_files: - split: train path: und_Tavt/*_keep.jsonl - config_name: gag_Latn data_files: - split: train path: gag_Latn/*_keep.jsonl - config_name: chk_Latn data_files: - split: train path: chk_Latn/*_keep.jsonl - config_name: hmo_Latn data_files: - split: train path: hmo_Latn/*_keep.jsonl - config_name: kek_Latn data_files: - split: train path: kek_Latn/*_keep.jsonl - config_name: fon_Latn data_files: - split: train path: fon_Latn/*_keep.jsonl - config_name: ssw_Latn data_files: - split: train path: ssw_Latn/*_keep.jsonl - config_name: quh_Latn data_files: - split: train path: quh_Latn/*_keep.jsonl - config_name: meu_Latn data_files: - split: train path: meu_Latn/*_keep.jsonl - config_name: csb_Latn data_files: - split: train path: csb_Latn/*_keep.jsonl - config_name: ksd_Latn data_files: - split: train path: ksd_Latn/*_keep.jsonl - config_name: ext_Latn data_files: - split: train path: ext_Latn/*_keep.jsonl - config_name: rop_Latn data_files: - split: train path: rop_Latn/*_keep.jsonl - config_name: und_Tfng data_files: - split: train path: und_Tfng/*_keep.jsonl - config_name: aln_Latn data_files: - split: train path: aln_Latn/*_keep.jsonl - config_name: kab_Latn data_files: - split: train path: kab_Latn/*_keep.jsonl - config_name: shn_Mymr data_files: - split: train path: shn_Mymr/*_keep.jsonl - config_name: tbz_Latn data_files: - split: train path: tbz_Latn/*_keep.jsonl - config_name: knv_Latn data_files: - split: train path: knv_Latn/*_keep.jsonl - config_name: bqc_Latn data_files: - split: train path: bqc_Latn/*_keep.jsonl - config_name: und_Elba data_files: - split: train path: und_Elba/*_keep.jsonl - config_name: und_Zanb data_files: - split: train path: und_Zanb/*_keep.jsonl - config_name: npi_Deva data_files: - split: train path: npi_Deva/*_keep.jsonl - config_name: rug_Latn data_files: - split: train path: rug_Latn/*_keep.jsonl - config_name: und_Tale data_files: - split: train path: und_Tale/*_keep.jsonl - config_name: kom_Cyrl data_files: - split: train path: kom_Cyrl/*_keep.jsonl - config_name: kpg_Latn data_files: - split: train path: kpg_Latn/*_keep.jsonl - config_name: kbd_Cyrl data_files: - split: train path: kbd_Cyrl/*_keep.jsonl - config_name: dzo_Tibt data_files: - split: train path: dzo_Tibt/*_keep.jsonl - config_name: wal_Latn data_files: - split: train path: wal_Latn/*_keep.jsonl - config_name: zlm_Latn data_files: - split: train path: zlm_Latn/*_keep.jsonl - config_name: und_Soyo data_files: - split: train path: und_Soyo/*_keep.jsonl - config_name: mzh_Latn data_files: - split: train path: mzh_Latn/*_keep.jsonl - config_name: pan_Latn data_files: - split: train path: pan_Latn/*_keep.jsonl - config_name: hac_Arab data_files: - split: train path: hac_Arab/*_keep.jsonl - config_name: und_Sogo data_files: - split: train path: und_Sogo/*_keep.jsonl - config_name: tum_Latn data_files: - split: train path: tum_Latn/*_keep.jsonl - config_name: sgs_Latn data_files: - split: train path: sgs_Latn/*_keep.jsonl - config_name: fij_Latn data_files: - split: train path: fij_Latn/*_keep.jsonl - config_name: tuc_Latn data_files: - split: train path: tuc_Latn/*_keep.jsonl - config_name: und_Dogr data_files: - split: train path: und_Dogr/*_keep.jsonl - config_name: und_Kawi data_files: - split: train path: und_Kawi/*_keep.jsonl - config_name: jbo_Latn data_files: - split: train path: jbo_Latn/*_keep.jsonl - config_name: iba_Latn data_files: - split: train path: iba_Latn/*_keep.jsonl - config_name: pcd_Latn data_files: - split: train path: pcd_Latn/*_keep.jsonl - config_name: kjh_Cyrl data_files: - split: train path: kjh_Cyrl/*_keep.jsonl - config_name: ixl_Latn data_files: - split: train path: ixl_Latn/*_keep.jsonl - config_name: und_Phli data_files: - split: train path: und_Phli/*_keep.jsonl - config_name: und_Cham data_files: - split: train path: und_Cham/*_keep.jsonl - config_name: und_Guru data_files: - split: train path: und_Guru/*_keep.jsonl - config_name: ndo_Latn data_files: - split: train path: ndo_Latn/*_keep.jsonl - config_name: suz_Deva data_files: - split: train path: suz_Deva/*_keep.jsonl - config_name: und_Nbat data_files: - split: train path: und_Nbat/*_keep.jsonl - config_name: und_Nand data_files: - split: train path: und_Nand/*_keep.jsonl - config_name: mfe_Latn data_files: - split: train path: mfe_Latn/*_keep.jsonl - config_name: bxr_Cyrl data_files: - split: train path: bxr_Cyrl/*_keep.jsonl - config_name: ava_Cyrl data_files: - split: train path: ava_Cyrl/*_keep.jsonl - config_name: und_Osma data_files: - split: train path: und_Osma/*_keep.jsonl - config_name: bho_Deva data_files: - split: train path: bho_Deva/*_keep.jsonl - config_name: brh_Arab data_files: - split: train path: brh_Arab/*_keep.jsonl - config_name: und_Sind data_files: - split: train path: und_Sind/*_keep.jsonl - config_name: ctd_Latn data_files: - split: train path: ctd_Latn/*_keep.jsonl - config_name: aym_Latn data_files: - split: train path: aym_Latn/*_keep.jsonl - config_name: ady_Cyrl data_files: - split: train path: ady_Cyrl/*_keep.jsonl - config_name: nbl_Latn data_files: - split: train path: nbl_Latn/*_keep.jsonl - config_name: gom_Deva data_files: - split: train path: gom_Deva/*_keep.jsonl - config_name: hus_Latn data_files: - split: train path: hus_Latn/*_keep.jsonl - config_name: gug_Latn data_files: - split: train path: gug_Latn/*_keep.jsonl - config_name: und_Pauc data_files: - split: train path: und_Pauc/*_keep.jsonl - config_name: und_Sogd data_files: - split: train path: und_Sogd/*_keep.jsonl - config_name: bat_Latn data_files: - split: train path: bat_Latn/*_keep.jsonl - config_name: guj_Deva data_files: - split: train path: guj_Deva/*_keep.jsonl - config_name: hne_Deva data_files: - split: train path: hne_Deva/*_keep.jsonl - config_name: srn_Latn data_files: - split: train path: srn_Latn/*_keep.jsonl - config_name: ctu_Latn data_files: - split: train path: ctu_Latn/*_keep.jsonl - config_name: san_Latn data_files: - split: train path: san_Latn/*_keep.jsonl - config_name: ton_Latn data_files: - split: train path: ton_Latn/*_keep.jsonl - config_name: bug_Latn data_files: - split: train path: bug_Latn/*_keep.jsonl - config_name: aoj_Latn data_files: - split: train path: aoj_Latn/*_keep.jsonl - config_name: jam_Latn data_files: - split: train path: jam_Latn/*_keep.jsonl - config_name: und_Sylo data_files: - split: train path: und_Sylo/*_keep.jsonl - config_name: lez_Cyrl data_files: - split: train path: lez_Cyrl/*_keep.jsonl - config_name: xav_Latn data_files: - split: train path: xav_Latn/*_keep.jsonl - config_name: luo_Latn data_files: - split: train path: luo_Latn/*_keep.jsonl - config_name: ltg_Latn data_files: - split: train path: ltg_Latn/*_keep.jsonl - config_name: bih_Deva data_files: - split: train path: bih_Deva/*_keep.jsonl - config_name: uig_Cyrl data_files: - split: train path: uig_Cyrl/*_keep.jsonl - config_name: mrj_Cyrl data_files: - split: train path: mrj_Cyrl/*_keep.jsonl - config_name: avk_Latn data_files: - split: train path: avk_Latn/*_keep.jsonl - config_name: kos_Latn data_files: - split: train path: kos_Latn/*_keep.jsonl - config_name: kbp_Latn data_files: - split: train path: kbp_Latn/*_keep.jsonl - config_name: alt_Cyrl data_files: - split: train path: alt_Cyrl/*_keep.jsonl - config_name: cfm_Latn data_files: - split: train path: cfm_Latn/*_keep.jsonl - config_name: goh_Latn data_files: - split: train path: goh_Latn/*_keep.jsonl - config_name: lad_Latn data_files: - split: train path: lad_Latn/*_keep.jsonl - config_name: und_Rjng data_files: - split: train path: und_Rjng/*_keep.jsonl - config_name: cor_Latn data_files: - split: train path: cor_Latn/*_keep.jsonl - config_name: quc_Latn data_files: - split: train path: quc_Latn/*_keep.jsonl - config_name: und_Goth data_files: - split: train path: und_Goth/*_keep.jsonl - config_name: kpv_Cyrl data_files: - split: train path: kpv_Cyrl/*_keep.jsonl - config_name: und_Chrs data_files: - split: train path: und_Chrs/*_keep.jsonl - config_name: aka_Latn data_files: - split: train path: aka_Latn/*_keep.jsonl - config_name: und_Phlp data_files: - split: train path: und_Phlp/*_keep.jsonl - config_name: hak_Latn data_files: - split: train path: hak_Latn/*_keep.jsonl - config_name: rmn_Latn data_files: - split: train path: rmn_Latn/*_keep.jsonl - config_name: pls_Latn data_files: - split: train path: pls_Latn/*_keep.jsonl - config_name: sag_Latn data_files: - split: train path: sag_Latn/*_keep.jsonl - config_name: min_Arab data_files: - split: train path: min_Arab/*_keep.jsonl - config_name: und_Tglg data_files: - split: train path: und_Tglg/*_keep.jsonl - config_name: rcf_Latn data_files: - split: train path: rcf_Latn/*_keep.jsonl - config_name: som_Arab data_files: - split: train path: som_Arab/*_keep.jsonl - config_name: gym_Latn data_files: - split: train path: gym_Latn/*_keep.jsonl - config_name: und_Mand data_files: - split: train path: und_Mand/*_keep.jsonl - config_name: kik_Latn data_files: - split: train path: kik_Latn/*_keep.jsonl - config_name: pag_Latn data_files: - split: train path: pag_Latn/*_keep.jsonl - config_name: arn_Latn data_files: - split: train path: arn_Latn/*_keep.jsonl - config_name: und_Shaw data_files: - split: train path: und_Shaw/*_keep.jsonl - config_name: ngu_Latn data_files: - split: train path: ngu_Latn/*_keep.jsonl - config_name: dsb_Latn data_files: - split: train path: dsb_Latn/*_keep.jsonl - config_name: tca_Latn data_files: - split: train path: tca_Latn/*_keep.jsonl - config_name: mni_Mtei data_files: - split: train path: mni_Mtei/*_keep.jsonl - config_name: naq_Latn data_files: - split: train path: naq_Latn/*_keep.jsonl - config_name: pdc_Latn data_files: - split: train path: pdc_Latn/*_keep.jsonl - config_name: mps_Latn data_files: - split: train path: mps_Latn/*_keep.jsonl - config_name: und_Hatr data_files: - split: train path: und_Hatr/*_keep.jsonl - config_name: olo_Latn data_files: - split: train path: olo_Latn/*_keep.jsonl - config_name: fro_Latn data_files: - split: train path: fro_Latn/*_keep.jsonl - config_name: fit_Latn data_files: - split: train path: fit_Latn/*_keep.jsonl - config_name: crh_Cyrl data_files: - split: train path: crh_Cyrl/*_keep.jsonl - config_name: cdo_Latn data_files: - split: train path: cdo_Latn/*_keep.jsonl - config_name: kac_Latn data_files: - split: train path: kac_Latn/*_keep.jsonl - config_name: mdf_Cyrl data_files: - split: train path: mdf_Cyrl/*_keep.jsonl - config_name: mad_Latn data_files: - split: train path: mad_Latn/*_keep.jsonl - config_name: cab_Latn data_files: - split: train path: cab_Latn/*_keep.jsonl - config_name: srm_Latn data_files: - split: train path: srm_Latn/*_keep.jsonl - config_name: toj_Latn data_files: - split: train path: toj_Latn/*_keep.jsonl - config_name: zai_Latn data_files: - split: train path: zai_Latn/*_keep.jsonl - config_name: guc_Latn data_files: - split: train path: guc_Latn/*_keep.jsonl - config_name: smn_Latn data_files: - split: train path: smn_Latn/*_keep.jsonl - config_name: ote_Latn data_files: - split: train path: ote_Latn/*_keep.jsonl - config_name: nch_Latn data_files: - split: train path: nch_Latn/*_keep.jsonl - config_name: und_Bugi data_files: - split: train path: und_Bugi/*_keep.jsonl - config_name: prs_Arab data_files: - split: train path: prs_Arab/*_keep.jsonl - config_name: tuk_Arab data_files: - split: train path: tuk_Arab/*_keep.jsonl - config_name: bis_Latn data_files: - split: train path: bis_Latn/*_keep.jsonl - config_name: cuk_Latn data_files: - split: train path: cuk_Latn/*_keep.jsonl - config_name: bzj_Latn data_files: - split: train path: bzj_Latn/*_keep.jsonl - config_name: map_Latn data_files: - split: train path: map_Latn/*_keep.jsonl - config_name: djk_Latn data_files: - split: train path: djk_Latn/*_keep.jsonl - config_name: ncj_Latn data_files: - split: train path: ncj_Latn/*_keep.jsonl - config_name: und_Olck data_files: - split: train path: und_Olck/*_keep.jsonl - config_name: mco_Latn data_files: - split: train path: mco_Latn/*_keep.jsonl - config_name: shp_Latn data_files: - split: train path: shp_Latn/*_keep.jsonl - config_name: und_Tagb data_files: - split: train path: und_Tagb/*_keep.jsonl - config_name: ang_Latn data_files: - split: train path: ang_Latn/*_keep.jsonl - config_name: seh_Latn data_files: - split: train path: seh_Latn/*_keep.jsonl - config_name: ikk_Latn data_files: - split: train path: ikk_Latn/*_keep.jsonl - config_name: qvi_Latn data_files: - split: train path: qvi_Latn/*_keep.jsonl - config_name: yom_Latn data_files: - split: train path: yom_Latn/*_keep.jsonl - config_name: top_Latn data_files: - split: train path: top_Latn/*_keep.jsonl - config_name: awa_Deva data_files: - split: train path: awa_Deva/*_keep.jsonl - config_name: ike_Cans data_files: - split: train path: ike_Cans/*_keep.jsonl - config_name: mau_Latn data_files: - split: train path: mau_Latn/*_keep.jsonl - config_name: kum_Cyrl data_files: - split: train path: kum_Cyrl/*_keep.jsonl - config_name: mos_Latn data_files: - split: train path: mos_Latn/*_keep.jsonl - config_name: tly_Latn data_files: - split: train path: tly_Latn/*_keep.jsonl - config_name: und_Prti data_files: - split: train path: und_Prti/*_keep.jsonl - config_name: ayr_Latn data_files: - split: train path: ayr_Latn/*_keep.jsonl - config_name: tdt_Latn data_files: - split: train path: tdt_Latn/*_keep.jsonl - config_name: yap_Latn data_files: - split: train path: yap_Latn/*_keep.jsonl - config_name: evn_Cyrl data_files: - split: train path: evn_Cyrl/*_keep.jsonl - config_name: tah_Latn data_files: - split: train path: tah_Latn/*_keep.jsonl - config_name: xal_Cyrl data_files: - split: train path: xal_Cyrl/*_keep.jsonl - config_name: szy_Latn data_files: - split: train path: szy_Latn/*_keep.jsonl - config_name: quw_Latn data_files: - split: train path: quw_Latn/*_keep.jsonl - config_name: stq_Latn data_files: - split: train path: stq_Latn/*_keep.jsonl - config_name: tlh_Latn data_files: - split: train path: tlh_Latn/*_keep.jsonl - config_name: otq_Latn data_files: - split: train path: otq_Latn/*_keep.jsonl - config_name: und_Narb data_files: - split: train path: und_Narb/*_keep.jsonl - config_name: nov_Latn data_files: - split: train path: nov_Latn/*_keep.jsonl - config_name: skr_Arab data_files: - split: train path: skr_Arab/*_keep.jsonl - config_name: yua_Latn data_files: - split: train path: yua_Latn/*_keep.jsonl - config_name: raw_Latn data_files: - split: train path: raw_Latn/*_keep.jsonl - config_name: und_Sarb data_files: - split: train path: und_Sarb/*_keep.jsonl - config_name: fiu_Latn data_files: - split: train path: fiu_Latn/*_keep.jsonl - config_name: enm_Latn data_files: - split: train path: enm_Latn/*_keep.jsonl - config_name: bbc_Latn data_files: - split: train path: bbc_Latn/*_keep.jsonl - config_name: und_Lydi data_files: - split: train path: und_Lydi/*_keep.jsonl - config_name: non_Latn data_files: - split: train path: non_Latn/*_keep.jsonl - config_name: und_Ugar data_files: - split: train path: und_Ugar/*_keep.jsonl - config_name: ber_Latn data_files: - split: train path: ber_Latn/*_keep.jsonl - config_name: kea_Latn data_files: - split: train path: kea_Latn/*_keep.jsonl - config_name: uig_Latn data_files: - split: train path: uig_Latn/*_keep.jsonl - config_name: bua_Cyrl data_files: - split: train path: bua_Cyrl/*_keep.jsonl - config_name: kua_Latn data_files: - split: train path: kua_Latn/*_keep.jsonl - config_name: zza_Latn data_files: - split: train path: zza_Latn/*_keep.jsonl - config_name: csy_Latn data_files: - split: train path: csy_Latn/*_keep.jsonl - config_name: mnw_Mymr data_files: - split: train path: mnw_Mymr/*_keep.jsonl - config_name: dtp_Latn data_files: - split: train path: dtp_Latn/*_keep.jsonl - config_name: nah_Latn data_files: - split: train path: nah_Latn/*_keep.jsonl - config_name: yao_Latn data_files: - split: train path: yao_Latn/*_keep.jsonl - config_name: azj_Cyrl data_files: - split: train path: azj_Cyrl/*_keep.jsonl - config_name: hau_Arab data_files: - split: train path: hau_Arab/*_keep.jsonl - config_name: nog_Cyrl data_files: - split: train path: nog_Cyrl/*_keep.jsonl - config_name: abt_Latn data_files: - split: train path: abt_Latn/*_keep.jsonl - config_name: meo_Latn data_files: - split: train path: meo_Latn/*_keep.jsonl - config_name: ame_Latn data_files: - split: train path: ame_Latn/*_keep.jsonl - config_name: mbf_Latn data_files: - split: train path: mbf_Latn/*_keep.jsonl - config_name: chm_Cyrl data_files: - split: train path: chm_Cyrl/*_keep.jsonl - config_name: arb_Latn data_files: - split: train path: arb_Latn/*_keep.jsonl - config_name: kas_Arab data_files: - split: train path: kas_Arab/*_keep.jsonl - config_name: tam_Latn data_files: - split: train path: tam_Latn/*_keep.jsonl - config_name: crs_Latn data_files: - split: train path: crs_Latn/*_keep.jsonl - config_name: tcy_Knda data_files: - split: train path: tcy_Knda/*_keep.jsonl - config_name: lbe_Cyrl data_files: - split: train path: lbe_Cyrl/*_keep.jsonl - config_name: cni_Latn data_files: - split: train path: cni_Latn/*_keep.jsonl - config_name: ben_Latn data_files: - split: train path: ben_Latn/*_keep.jsonl - config_name: rom_Latn data_files: - split: train path: rom_Latn/*_keep.jsonl - config_name: zom_Latn data_files: - split: train path: zom_Latn/*_keep.jsonl - config_name: blk_Mymr data_files: - split: train path: blk_Mymr/*_keep.jsonl - config_name: efi_Latn data_files: - split: train path: efi_Latn/*_keep.jsonl - config_name: ada_Latn data_files: - split: train path: ada_Latn/*_keep.jsonl - config_name: und_Buhd data_files: - split: train path: und_Buhd/*_keep.jsonl - config_name: koi_Cyrl data_files: - split: train path: koi_Cyrl/*_keep.jsonl - config_name: und_Perm data_files: - split: train path: und_Perm/*_keep.jsonl - config_name: bbj_Latn data_files: - split: train path: bbj_Latn/*_keep.jsonl - config_name: trv_Latn data_files: - split: train path: trv_Latn/*_keep.jsonl - config_name: ach_Latn data_files: - split: train path: ach_Latn/*_keep.jsonl - config_name: mgh_Latn data_files: - split: train path: mgh_Latn/*_keep.jsonl - config_name: kas_Latn data_files: - split: train path: kas_Latn/*_keep.jsonl - config_name: gcr_Latn data_files: - split: train path: gcr_Latn/*_keep.jsonl - config_name: krl_Latn data_files: - split: train path: krl_Latn/*_keep.jsonl - config_name: iso_Latn data_files: - split: train path: iso_Latn/*_keep.jsonl - config_name: lki_Arab data_files: - split: train path: lki_Arab/*_keep.jsonl - config_name: atj_Latn data_files: - split: train path: atj_Latn/*_keep.jsonl - config_name: cmo_Latn data_files: - split: train path: cmo_Latn/*_keep.jsonl - config_name: chu_Cyrl data_files: - split: train path: chu_Cyrl/*_keep.jsonl - config_name: gur_Latn data_files: - split: train path: gur_Latn/*_keep.jsonl - config_name: mni_Beng data_files: - split: train path: mni_Beng/*_keep.jsonl - config_name: iku_Cans data_files: - split: train path: iku_Cans/*_keep.jsonl - config_name: sma_Latn data_files: - split: train path: sma_Latn/*_keep.jsonl - config_name: lrc_Arab data_files: - split: train path: lrc_Arab/*_keep.jsonl - config_name: gos_Latn data_files: - split: train path: gos_Latn/*_keep.jsonl - config_name: dty_Deva data_files: - split: train path: dty_Deva/*_keep.jsonl - config_name: nzi_Latn data_files: - split: train path: nzi_Latn/*_keep.jsonl - config_name: btx_Latn data_files: - split: train path: btx_Latn/*_keep.jsonl - config_name: brx_Deva data_files: - split: train path: brx_Deva/*_keep.jsonl - config_name: bts_Latn data_files: - split: train path: bts_Latn/*_keep.jsonl - config_name: nyu_Latn data_files: - split: train path: nyu_Latn/*_keep.jsonl - config_name: ckt_Latn data_files: - split: train path: ckt_Latn/*_keep.jsonl - config_name: guw_Latn data_files: - split: train path: guw_Latn/*_keep.jsonl - config_name: pck_Latn data_files: - split: train path: pck_Latn/*_keep.jsonl - config_name: quy_Latn data_files: - split: train path: quy_Latn/*_keep.jsonl - config_name: gcf_Latn data_files: - split: train path: gcf_Latn/*_keep.jsonl - config_name: ksw_Mymr data_files: - split: train path: ksw_Mymr/*_keep.jsonl - config_name: nia_Latn data_files: - split: train path: nia_Latn/*_keep.jsonl - config_name: bal_Arab data_files: - split: train path: bal_Arab/*_keep.jsonl - config_name: nhe_Latn data_files: - split: train path: nhe_Latn/*_keep.jsonl - config_name: hwc_Latn data_files: - split: train path: hwc_Latn/*_keep.jsonl - config_name: mup_Deva data_files: - split: train path: mup_Deva/*_keep.jsonl - config_name: dyu_Latn data_files: - split: train path: dyu_Latn/*_keep.jsonl - config_name: ami_Latn data_files: - split: train path: ami_Latn/*_keep.jsonl - config_name: tay_Latn data_files: - split: train path: tay_Latn/*_keep.jsonl - config_name: gaa_Latn data_files: - split: train path: gaa_Latn/*_keep.jsonl - config_name: loz_Latn data_files: - split: train path: loz_Latn/*_keep.jsonl - config_name: abq_Cyrl data_files: - split: train path: abq_Cyrl/*_keep.jsonl - config_name: pnt_Grek data_files: - split: train path: pnt_Grek/*_keep.jsonl - config_name: snd_Latn data_files: - split: train path: snd_Latn/*_keep.jsonl - config_name: ium_Latn data_files: - split: train path: ium_Latn/*_keep.jsonl - config_name: abs_Latn data_files: - split: train path: abs_Latn/*_keep.jsonl - config_name: cmr_Latn data_files: - split: train path: cmr_Latn/*_keep.jsonl - config_name: shi_Latn data_files: - split: train path: shi_Latn/*_keep.jsonl - config_name: tzm_Tfng data_files: - split: train path: tzm_Tfng/*_keep.jsonl - config_name: gil_Latn data_files: - split: train path: gil_Latn/*_keep.jsonl - config_name: ewo_Latn data_files: - split: train path: ewo_Latn/*_keep.jsonl - config_name: kon_Latn data_files: - split: train path: kon_Latn/*_keep.jsonl - config_name: sms_Latn data_files: - split: train path: sms_Latn/*_keep.jsonl - config_name: ape_Latn data_files: - split: train path: ape_Latn/*_keep.jsonl - config_name: tzh_Latn data_files: - split: train path: tzh_Latn/*_keep.jsonl - config_name: bci_Latn data_files: - split: train path: bci_Latn/*_keep.jsonl - config_name: acd_Latn data_files: - split: train path: acd_Latn/*_keep.jsonl - config_name: tab_Cyrl data_files: - split: train path: tab_Cyrl/*_keep.jsonl - config_name: fuv_Latn data_files: - split: train path: fuv_Latn/*_keep.jsonl - config_name: swc_Latn data_files: - split: train path: swc_Latn/*_keep.jsonl - config_name: tcz_Latn data_files: - split: train path: tcz_Latn/*_keep.jsonl - config_name: und_Elym data_files: - split: train path: und_Elym/*_keep.jsonl - config_name: sgc_Latn data_files: - split: train path: sgc_Latn/*_keep.jsonl - config_name: aaz_Latn data_files: - split: train path: aaz_Latn/*_keep.jsonl - config_name: tly_Arab data_files: - split: train path: tly_Arab/*_keep.jsonl - config_name: tvl_Latn data_files: - split: train path: tvl_Latn/*_keep.jsonl - config_name: zha_Latn data_files: - split: train path: zha_Latn/*_keep.jsonl - config_name: pib_Latn data_files: - split: train path: pib_Latn/*_keep.jsonl - config_name: pli_Deva data_files: - split: train path: pli_Deva/*_keep.jsonl - config_name: bru_Latn data_files: - split: train path: bru_Latn/*_keep.jsonl - config_name: quz_Latn data_files: - split: train path: quz_Latn/*_keep.jsonl - config_name: cha_Latn data_files: - split: train path: cha_Latn/*_keep.jsonl - config_name: aeu_Latn data_files: - split: train path: aeu_Latn/*_keep.jsonl - config_name: bjn_Arab data_files: - split: train path: bjn_Arab/*_keep.jsonl - config_name: nqo_Nkoo data_files: - split: train path: nqo_Nkoo/*_keep.jsonl - config_name: mer_Latn data_files: - split: train path: mer_Latn/*_keep.jsonl - config_name: acf_Latn data_files: - split: train path: acf_Latn/*_keep.jsonl - config_name: rmc_Latn data_files: - split: train path: rmc_Latn/*_keep.jsonl - config_name: msi_Latn data_files: - split: train path: msi_Latn/*_keep.jsonl - config_name: smj_Latn data_files: - split: train path: smj_Latn/*_keep.jsonl - config_name: kng_Latn data_files: - split: train path: kng_Latn/*_keep.jsonl - config_name: dhv_Latn data_files: - split: train path: dhv_Latn/*_keep.jsonl - config_name: doi_Deva data_files: - split: train path: doi_Deva/*_keep.jsonl - config_name: zap_Latn data_files: - split: train path: zap_Latn/*_keep.jsonl - config_name: hla_Latn data_files: - split: train path: hla_Latn/*_keep.jsonl - config_name: cac_Latn data_files: - split: train path: cac_Latn/*_keep.jsonl - config_name: pdt_Latn data_files: - split: train path: pdt_Latn/*_keep.jsonl - config_name: mbt_Latn data_files: - split: train path: mbt_Latn/*_keep.jsonl - config_name: taq_Latn data_files: - split: train path: taq_Latn/*_keep.jsonl - config_name: bgp_Latn data_files: - split: train path: bgp_Latn/*_keep.jsonl - config_name: tyz_Latn data_files: - split: train path: tyz_Latn/*_keep.jsonl - config_name: aau_Latn data_files: - split: train path: aau_Latn/*_keep.jsonl - config_name: mah_Latn data_files: - split: train path: mah_Latn/*_keep.jsonl - config_name: nak_Latn data_files: - split: train path: nak_Latn/*_keep.jsonl - config_name: kmb_Latn data_files: - split: train path: kmb_Latn/*_keep.jsonl - config_name: mjw_Latn data_files: - split: train path: mjw_Latn/*_keep.jsonl - config_name: fuf_Latn data_files: - split: train path: fuf_Latn/*_keep.jsonl - config_name: bba_Latn data_files: - split: train path: bba_Latn/*_keep.jsonl - config_name: ron_Cyrl data_files: - split: train path: ron_Cyrl/*_keep.jsonl - config_name: amu_Latn data_files: - split: train path: amu_Latn/*_keep.jsonl - config_name: alz_Latn data_files: - split: train path: alz_Latn/*_keep.jsonl - config_name: cop_Copt data_files: - split: train path: cop_Copt/*_keep.jsonl - config_name: rar_Latn data_files: - split: train path: rar_Latn/*_keep.jsonl - config_name: emp_Latn data_files: - split: train path: emp_Latn/*_keep.jsonl - config_name: arc_Syrc data_files: - split: train path: arc_Syrc/*_keep.jsonl - config_name: nyn_Latn data_files: - split: train path: nyn_Latn/*_keep.jsonl - config_name: rut_Cyrl data_files: - split: train path: rut_Cyrl/*_keep.jsonl - config_name: lub_Latn data_files: - split: train path: lub_Latn/*_keep.jsonl - config_name: tzj_Latn data_files: - split: train path: tzj_Latn/*_keep.jsonl - config_name: fat_Latn data_files: - split: train path: fat_Latn/*_keep.jsonl - config_name: lzh_Hani data_files: - split: train path: lzh_Hani/*_keep.jsonl - config_name: aak_Latn data_files: - split: train path: aak_Latn/*_keep.jsonl - config_name: nnb_Latn data_files: - split: train path: nnb_Latn/*_keep.jsonl - config_name: lhu_Latn data_files: - split: train path: lhu_Latn/*_keep.jsonl - config_name: bjv_Latn data_files: - split: train path: bjv_Latn/*_keep.jsonl - config_name: bum_Latn data_files: - split: train path: bum_Latn/*_keep.jsonl - config_name: maq_Latn data_files: - split: train path: maq_Latn/*_keep.jsonl - config_name: roa_Latn data_files: - split: train path: roa_Latn/*_keep.jsonl - config_name: bvr_Latn data_files: - split: train path: bvr_Latn/*_keep.jsonl - config_name: kcg_Latn data_files: - split: train path: kcg_Latn/*_keep.jsonl - config_name: tok_Latn data_files: - split: train path: tok_Latn/*_keep.jsonl - config_name: yrk_Cyrl data_files: - split: train path: yrk_Cyrl/*_keep.jsonl - config_name: khs_Latn data_files: - split: train path: khs_Latn/*_keep.jsonl - config_name: rup_Latn data_files: - split: train path: rup_Latn/*_keep.jsonl - config_name: tuk_Cyrl data_files: - split: train path: tuk_Cyrl/*_keep.jsonl - config_name: qub_Latn data_files: - split: train path: qub_Latn/*_keep.jsonl - config_name: jac_Latn data_files: - split: train path: jac_Latn/*_keep.jsonl - config_name: hmr_Latn data_files: - split: train path: hmr_Latn/*_keep.jsonl - config_name: sid_Latn data_files: - split: train path: sid_Latn/*_keep.jsonl - config_name: chr_Cher data_files: - split: train path: chr_Cher/*_keep.jsonl - config_name: amp_Latn data_files: - split: train path: amp_Latn/*_keep.jsonl - config_name: qug_Latn data_files: - split: train path: qug_Latn/*_keep.jsonl - config_name: mas_Latn data_files: - split: train path: mas_Latn/*_keep.jsonl - config_name: fkv_Latn data_files: - split: train path: fkv_Latn/*_keep.jsonl - config_name: mal_Latn data_files: - split: train path: mal_Latn/*_keep.jsonl - config_name: bem_Latn data_files: - split: train path: bem_Latn/*_keep.jsonl - config_name: cav_Latn data_files: - split: train path: cav_Latn/*_keep.jsonl - config_name: her_Latn data_files: - split: train path: her_Latn/*_keep.jsonl - config_name: kwn_Latn data_files: - split: train path: kwn_Latn/*_keep.jsonl - config_name: ify_Latn data_files: - split: train path: ify_Latn/*_keep.jsonl - config_name: asm_Latn data_files: - split: train path: asm_Latn/*_keep.jsonl - config_name: gpe_Latn data_files: - split: train path: gpe_Latn/*_keep.jsonl - config_name: zpa_Latn data_files: - split: train path: zpa_Latn/*_keep.jsonl - config_name: agu_Latn data_files: - split: train path: agu_Latn/*_keep.jsonl - config_name: ppk_Latn data_files: - split: train path: ppk_Latn/*_keep.jsonl - config_name: tiv_Latn data_files: - split: train path: tiv_Latn/*_keep.jsonl - config_name: npi_Latn data_files: - split: train path: npi_Latn/*_keep.jsonl - config_name: ahk_Latn data_files: - split: train path: ahk_Latn/*_keep.jsonl - config_name: pis_Latn data_files: - split: train path: pis_Latn/*_keep.jsonl - config_name: hns_Latn data_files: - split: train path: hns_Latn/*_keep.jsonl - config_name: sus_Latn data_files: - split: train path: sus_Latn/*_keep.jsonl - config_name: hak_Hani data_files: - split: train path: hak_Hani/*_keep.jsonl - config_name: bon_Latn data_files: - split: train path: bon_Latn/*_keep.jsonl - config_name: sja_Latn data_files: - split: train path: sja_Latn/*_keep.jsonl - config_name: kas_Deva data_files: - split: train path: kas_Deva/*_keep.jsonl - config_name: mar_Latn data_files: - split: train path: mar_Latn/*_keep.jsonl - config_name: kri_Latn data_files: - split: train path: kri_Latn/*_keep.jsonl - config_name: dik_Latn data_files: - split: train path: dik_Latn/*_keep.jsonl - config_name: wrk_Latn data_files: - split: train path: wrk_Latn/*_keep.jsonl - config_name: got_Goth data_files: - split: train path: got_Goth/*_keep.jsonl - config_name: dar_Cyrl data_files: - split: train path: dar_Cyrl/*_keep.jsonl - config_name: gui_Latn data_files: - split: train path: gui_Latn/*_keep.jsonl - config_name: mak_Latn data_files: - split: train path: mak_Latn/*_keep.jsonl - config_name: jiv_Latn data_files: - split: train path: jiv_Latn/*_keep.jsonl - config_name: kjb_Latn data_files: - split: train path: kjb_Latn/*_keep.jsonl - config_name: maz_Latn data_files: - split: train path: maz_Latn/*_keep.jsonl - config_name: bsn_Latn data_files: - split: train path: bsn_Latn/*_keep.jsonl - config_name: dov_Latn data_files: - split: train path: dov_Latn/*_keep.jsonl - config_name: cok_Latn data_files: - split: train path: cok_Latn/*_keep.jsonl - config_name: rwo_Latn data_files: - split: train path: rwo_Latn/*_keep.jsonl - config_name: mag_Deva data_files: - split: train path: mag_Deva/*_keep.jsonl - config_name: hnj_Latn data_files: - split: train path: hnj_Latn/*_keep.jsonl - config_name: krj_Latn data_files: - split: train path: krj_Latn/*_keep.jsonl - config_name: teo_Latn data_files: - split: train path: teo_Latn/*_keep.jsonl - config_name: enq_Latn data_files: - split: train path: enq_Latn/*_keep.jsonl - config_name: aom_Latn data_files: - split: train path: aom_Latn/*_keep.jsonl - config_name: ffm_Latn data_files: - split: train path: ffm_Latn/*_keep.jsonl - config_name: din_Latn data_files: - split: train path: din_Latn/*_keep.jsonl - config_name: ubu_Latn data_files: - split: train path: ubu_Latn/*_keep.jsonl - config_name: pwn_Latn data_files: - split: train path: pwn_Latn/*_keep.jsonl - config_name: gum_Latn data_files: - split: train path: gum_Latn/*_keep.jsonl - config_name: sny_Latn data_files: - split: train path: sny_Latn/*_keep.jsonl - config_name: twu_Latn data_files: - split: train path: twu_Latn/*_keep.jsonl - config_name: med_Latn data_files: - split: train path: med_Latn/*_keep.jsonl - config_name: acn_Latn data_files: - split: train path: acn_Latn/*_keep.jsonl - config_name: rme_Latn data_files: - split: train path: rme_Latn/*_keep.jsonl - config_name: cbs_Latn data_files: - split: train path: cbs_Latn/*_keep.jsonl - config_name: abx_Latn data_files: - split: train path: abx_Latn/*_keep.jsonl - config_name: ndc_Latn data_files: - split: train path: ndc_Latn/*_keep.jsonl - config_name: ibb_Latn data_files: - split: train path: ibb_Latn/*_keep.jsonl - config_name: pih_Latn data_files: - split: train path: pih_Latn/*_keep.jsonl - config_name: zty_Latn data_files: - split: train path: zty_Latn/*_keep.jsonl - config_name: rad_Latn data_files: - split: train path: rad_Latn/*_keep.jsonl - config_name: aby_Latn data_files: - split: train path: aby_Latn/*_keep.jsonl - config_name: zne_Latn data_files: - split: train path: zne_Latn/*_keep.jsonl - config_name: cui_Latn data_files: - split: train path: cui_Latn/*_keep.jsonl - config_name: lua_Latn data_files: - split: train path: lua_Latn/*_keep.jsonl - config_name: yby_Latn data_files: - split: train path: yby_Latn/*_keep.jsonl - config_name: bno_Latn data_files: - split: train path: bno_Latn/*_keep.jsonl - config_name: niu_Latn data_files: - split: train path: niu_Latn/*_keep.jsonl - config_name: agd_Latn data_files: - split: train path: agd_Latn/*_keep.jsonl - config_name: nij_Latn data_files: - split: train path: nij_Latn/*_keep.jsonl - config_name: agg_Latn data_files: - split: train path: agg_Latn/*_keep.jsonl - config_name: yre_Latn data_files: - split: train path: yre_Latn/*_keep.jsonl - config_name: fip_Latn data_files: - split: train path: fip_Latn/*_keep.jsonl - config_name: qve_Latn data_files: - split: train path: qve_Latn/*_keep.jsonl - config_name: tsg_Latn data_files: - split: train path: tsg_Latn/*_keep.jsonl - config_name: skg_Latn data_files: - split: train path: skg_Latn/*_keep.jsonl - config_name: adj_Latn data_files: - split: train path: adj_Latn/*_keep.jsonl - config_name: mfq_Latn data_files: - split: train path: mfq_Latn/*_keep.jsonl - config_name: agx_Cyrl data_files: - split: train path: agx_Cyrl/*_keep.jsonl - config_name: kmg_Latn data_files: - split: train path: kmg_Latn/*_keep.jsonl - config_name: umb_Latn data_files: - split: train path: umb_Latn/*_keep.jsonl - config_name: cnk_Latn data_files: - split: train path: cnk_Latn/*_keep.jsonl - config_name: nhw_Latn data_files: - split: train path: nhw_Latn/*_keep.jsonl - config_name: maa_Latn data_files: - split: train path: maa_Latn/*_keep.jsonl - config_name: kwy_Latn data_files: - split: train path: kwy_Latn/*_keep.jsonl - config_name: jra_Latn data_files: - split: train path: jra_Latn/*_keep.jsonl - config_name: syr_Syrc data_files: - split: train path: syr_Syrc/*_keep.jsonl - config_name: inb_Latn data_files: - split: train path: inb_Latn/*_keep.jsonl - config_name: pau_Latn data_files: - split: train path: pau_Latn/*_keep.jsonl - config_name: xsm_Latn data_files: - split: train path: xsm_Latn/*_keep.jsonl - config_name: vap_Latn data_files: - split: train path: vap_Latn/*_keep.jsonl - config_name: alp_Latn data_files: - split: train path: alp_Latn/*_keep.jsonl - config_name: des_Latn data_files: - split: train path: des_Latn/*_keep.jsonl - config_name: syl_Latn data_files: - split: train path: syl_Latn/*_keep.jsonl - config_name: kmr_Cyrl data_files: - split: train path: kmr_Cyrl/*_keep.jsonl - config_name: mkn_Latn data_files: - split: train path: mkn_Latn/*_keep.jsonl - config_name: gan_Hani data_files: - split: train path: gan_Hani/*_keep.jsonl - config_name: qwh_Latn data_files: - split: train path: qwh_Latn/*_keep.jsonl - config_name: jvn_Latn data_files: - split: train path: jvn_Latn/*_keep.jsonl - config_name: bib_Latn data_files: - split: train path: bib_Latn/*_keep.jsonl - config_name: ckt_Cyrl data_files: - split: train path: ckt_Cyrl/*_keep.jsonl - config_name: mpx_Latn data_files: - split: train path: mpx_Latn/*_keep.jsonl - config_name: bin_Latn data_files: - split: train path: bin_Latn/*_keep.jsonl - config_name: klv_Latn data_files: - split: train path: klv_Latn/*_keep.jsonl - config_name: xon_Latn data_files: - split: train path: xon_Latn/*_keep.jsonl - config_name: jbu_Latn data_files: - split: train path: jbu_Latn/*_keep.jsonl - config_name: bdh_Latn data_files: - split: train path: bdh_Latn/*_keep.jsonl - config_name: knj_Latn data_files: - split: train path: knj_Latn/*_keep.jsonl - config_name: ptu_Latn data_files: - split: train path: ptu_Latn/*_keep.jsonl - config_name: mmn_Latn data_files: - split: train path: mmn_Latn/*_keep.jsonl - config_name: mwq_Latn data_files: - split: train path: mwq_Latn/*_keep.jsonl - config_name: sop_Latn data_files: - split: train path: sop_Latn/*_keep.jsonl - config_name: cgc_Latn data_files: - split: train path: cgc_Latn/*_keep.jsonl - config_name: rmy_Cyrl data_files: - split: train path: rmy_Cyrl/*_keep.jsonl - config_name: dop_Latn data_files: - split: train path: dop_Latn/*_keep.jsonl - config_name: mgr_Latn data_files: - split: train path: mgr_Latn/*_keep.jsonl - config_name: rmo_Latn data_files: - split: train path: rmo_Latn/*_keep.jsonl - config_name: tbc_Latn data_files: - split: train path: tbc_Latn/*_keep.jsonl - config_name: kyq_Latn data_files: - split: train path: kyq_Latn/*_keep.jsonl - config_name: zpu_Latn data_files: - split: train path: zpu_Latn/*_keep.jsonl - config_name: kkc_Latn data_files: - split: train path: kkc_Latn/*_keep.jsonl - config_name: acu_Latn data_files: - split: train path: acu_Latn/*_keep.jsonl - config_name: ata_Latn data_files: - split: train path: ata_Latn/*_keep.jsonl - config_name: gag_Cyrl data_files: - split: train path: gag_Cyrl/*_keep.jsonl - config_name: kan_Latn data_files: - split: train path: kan_Latn/*_keep.jsonl - config_name: mif_Latn data_files: - split: train path: mif_Latn/*_keep.jsonl - config_name: sus_Arab data_files: - split: train path: sus_Arab/*_keep.jsonl - config_name: tsz_Latn data_files: - split: train path: tsz_Latn/*_keep.jsonl - config_name: mbi_Latn data_files: - split: train path: mbi_Latn/*_keep.jsonl - config_name: imo_Latn data_files: - split: train path: imo_Latn/*_keep.jsonl - config_name: fuh_Latn data_files: - split: train path: fuh_Latn/*_keep.jsonl - config_name: zyp_Latn data_files: - split: train path: zyp_Latn/*_keep.jsonl - config_name: apr_Latn data_files: - split: train path: apr_Latn/*_keep.jsonl - config_name: att_Latn data_files: - split: train path: att_Latn/*_keep.jsonl - config_name: bus_Latn data_files: - split: train path: bus_Latn/*_keep.jsonl - config_name: kqp_Latn data_files: - split: train path: kqp_Latn/*_keep.jsonl - config_name: koo_Latn data_files: - split: train path: koo_Latn/*_keep.jsonl - config_name: bas_Latn data_files: - split: train path: bas_Latn/*_keep.jsonl - config_name: urh_Latn data_files: - split: train path: urh_Latn/*_keep.jsonl - config_name: bbr_Latn data_files: - split: train path: bbr_Latn/*_keep.jsonl - config_name: msy_Latn data_files: - split: train path: msy_Latn/*_keep.jsonl - config_name: mdy_Ethi data_files: - split: train path: mdy_Ethi/*_keep.jsonl - config_name: nas_Latn data_files: - split: train path: nas_Latn/*_keep.jsonl - config_name: lee_Latn data_files: - split: train path: lee_Latn/*_keep.jsonl - config_name: mcu_Latn data_files: - split: train path: mcu_Latn/*_keep.jsonl - config_name: mrj_Latn data_files: - split: train path: mrj_Latn/*_keep.jsonl - config_name: dig_Latn data_files: - split: train path: dig_Latn/*_keep.jsonl - config_name: izr_Latn data_files: - split: train path: izr_Latn/*_keep.jsonl - config_name: nfr_Latn data_files: - split: train path: nfr_Latn/*_keep.jsonl - config_name: hto_Latn data_files: - split: train path: hto_Latn/*_keep.jsonl - config_name: mzw_Latn data_files: - split: train path: mzw_Latn/*_keep.jsonl - config_name: qxh_Latn data_files: - split: train path: qxh_Latn/*_keep.jsonl - config_name: chz_Latn data_files: - split: train path: chz_Latn/*_keep.jsonl - config_name: guh_Latn data_files: - split: train path: guh_Latn/*_keep.jsonl - config_name: ded_Latn data_files: - split: train path: ded_Latn/*_keep.jsonl - config_name: bvz_Latn data_files: - split: train path: bvz_Latn/*_keep.jsonl - config_name: kkj_Latn data_files: - split: train path: kkj_Latn/*_keep.jsonl - config_name: gux_Latn data_files: - split: train path: gux_Latn/*_keep.jsonl - config_name: ikt_Latn data_files: - split: train path: ikt_Latn/*_keep.jsonl - config_name: bnp_Latn data_files: - split: train path: bnp_Latn/*_keep.jsonl - config_name: bgt_Latn data_files: - split: train path: bgt_Latn/*_keep.jsonl - config_name: quf_Latn data_files: - split: train path: quf_Latn/*_keep.jsonl - config_name: dwr_Latn data_files: - split: train path: dwr_Latn/*_keep.jsonl - config_name: nod_Thai data_files: - split: train path: nod_Thai/*_keep.jsonl - config_name: yal_Latn data_files: - split: train path: yal_Latn/*_keep.jsonl - config_name: bmr_Latn data_files: - split: train path: bmr_Latn/*_keep.jsonl - config_name: ljp_Latn data_files: - split: train path: ljp_Latn/*_keep.jsonl - config_name: xla_Latn data_files: - split: train path: xla_Latn/*_keep.jsonl - config_name: zyb_Latn data_files: - split: train path: zyb_Latn/*_keep.jsonl - config_name: gof_Latn data_files: - split: train path: gof_Latn/*_keep.jsonl - config_name: niv_Cyrl data_files: - split: train path: niv_Cyrl/*_keep.jsonl - config_name: nrf_Latn data_files: - split: train path: nrf_Latn/*_keep.jsonl - config_name: npy_Latn data_files: - split: train path: npy_Latn/*_keep.jsonl - config_name: ura_Latn data_files: - split: train path: ura_Latn/*_keep.jsonl - config_name: dob_Latn data_files: - split: train path: dob_Latn/*_keep.jsonl - config_name: gfk_Latn data_files: - split: train path: gfk_Latn/*_keep.jsonl - config_name: gdr_Latn data_files: - split: train path: gdr_Latn/*_keep.jsonl - config_name: sdc_Latn data_files: - split: train path: sdc_Latn/*_keep.jsonl - config_name: pjt_Latn data_files: - split: train path: pjt_Latn/*_keep.jsonl - config_name: spp_Latn data_files: - split: train path: spp_Latn/*_keep.jsonl - config_name: irk_Latn data_files: - split: train path: irk_Latn/*_keep.jsonl - config_name: cpa_Latn data_files: - split: train path: cpa_Latn/*_keep.jsonl - config_name: knc_Latn data_files: - split: train path: knc_Latn/*_keep.jsonl - config_name: gvl_Latn data_files: - split: train path: gvl_Latn/*_keep.jsonl - config_name: agr_Latn data_files: - split: train path: agr_Latn/*_keep.jsonl - config_name: njo_Latn data_files: - split: train path: njo_Latn/*_keep.jsonl - config_name: xrb_Latn data_files: - split: train path: xrb_Latn/*_keep.jsonl - config_name: kao_Latn data_files: - split: train path: kao_Latn/*_keep.jsonl - config_name: zpz_Latn data_files: - split: train path: zpz_Latn/*_keep.jsonl - config_name: bgr_Latn data_files: - split: train path: bgr_Latn/*_keep.jsonl - config_name: rnd_Latn data_files: - split: train path: rnd_Latn/*_keep.jsonl - config_name: ntu_Latn data_files: - split: train path: ntu_Latn/*_keep.jsonl - config_name: aai_Latn data_files: - split: train path: aai_Latn/*_keep.jsonl - config_name: gai_Latn data_files: - split: train path: gai_Latn/*_keep.jsonl - config_name: dgi_Latn data_files: - split: train path: dgi_Latn/*_keep.jsonl - config_name: kez_Latn data_files: - split: train path: kez_Latn/*_keep.jsonl - config_name: dad_Latn data_files: - split: train path: dad_Latn/*_keep.jsonl - config_name: kmh_Latn data_files: - split: train path: kmh_Latn/*_keep.jsonl - config_name: aii_Syrc data_files: - split: train path: aii_Syrc/*_keep.jsonl - config_name: ifk_Latn data_files: - split: train path: ifk_Latn/*_keep.jsonl - config_name: aji_Latn data_files: - split: train path: aji_Latn/*_keep.jsonl - config_name: noa_Latn data_files: - split: train path: noa_Latn/*_keep.jsonl - config_name: bhl_Latn data_files: - split: train path: bhl_Latn/*_keep.jsonl - config_name: ztq_Latn data_files: - split: train path: ztq_Latn/*_keep.jsonl - config_name: rmn_Cyrl data_files: - split: train path: rmn_Cyrl/*_keep.jsonl - config_name: gde_Latn data_files: - split: train path: gde_Latn/*_keep.jsonl - config_name: dnj_Latn data_files: - split: train path: dnj_Latn/*_keep.jsonl - config_name: men_Latn data_files: - split: train path: men_Latn/*_keep.jsonl - config_name: miq_Latn data_files: - split: train path: miq_Latn/*_keep.jsonl - config_name: mdf_Latn data_files: - split: train path: mdf_Latn/*_keep.jsonl - config_name: isd_Latn data_files: - split: train path: isd_Latn/*_keep.jsonl - config_name: lgg_Latn data_files: - split: train path: lgg_Latn/*_keep.jsonl - config_name: ncx_Latn data_files: - split: train path: ncx_Latn/*_keep.jsonl - config_name: gub_Latn data_files: - split: train path: gub_Latn/*_keep.jsonl - config_name: itv_Latn data_files: - split: train path: itv_Latn/*_keep.jsonl - config_name: tac_Latn data_files: - split: train path: tac_Latn/*_keep.jsonl - config_name: cce_Latn data_files: - split: train path: cce_Latn/*_keep.jsonl - config_name: kwi_Latn data_files: - split: train path: kwi_Latn/*_keep.jsonl - config_name: nhu_Latn data_files: - split: train path: nhu_Latn/*_keep.jsonl - config_name: snd_Deva data_files: - split: train path: snd_Deva/*_keep.jsonl - config_name: sml_Latn data_files: - split: train path: sml_Latn/*_keep.jsonl - config_name: pah_Latn data_files: - split: train path: pah_Latn/*_keep.jsonl - config_name: sas_Latn data_files: - split: train path: sas_Latn/*_keep.jsonl - config_name: cwt_Latn data_files: - split: train path: cwt_Latn/*_keep.jsonl - config_name: spy_Latn data_files: - split: train path: spy_Latn/*_keep.jsonl - config_name: enb_Latn data_files: - split: train path: enb_Latn/*_keep.jsonl - config_name: fai_Latn data_files: - split: train path: fai_Latn/*_keep.jsonl - config_name: cas_Latn data_files: - split: train path: cas_Latn/*_keep.jsonl - config_name: sue_Latn data_files: - split: train path: sue_Latn/*_keep.jsonl - config_name: yss_Latn data_files: - split: train path: yss_Latn/*_keep.jsonl - config_name: ozm_Latn data_files: - split: train path: ozm_Latn/*_keep.jsonl - config_name: bku_Latn data_files: - split: train path: bku_Latn/*_keep.jsonl - config_name: biv_Latn data_files: - split: train path: biv_Latn/*_keep.jsonl - config_name: akp_Latn data_files: - split: train path: akp_Latn/*_keep.jsonl - config_name: dts_Latn data_files: - split: train path: dts_Latn/*_keep.jsonl - config_name: kdr_Latn data_files: - split: train path: kdr_Latn/*_keep.jsonl - config_name: fal_Latn data_files: - split: train path: fal_Latn/*_keep.jsonl - config_name: mmo_Latn data_files: - split: train path: mmo_Latn/*_keep.jsonl - config_name: byr_Latn data_files: - split: train path: byr_Latn/*_keep.jsonl - config_name: cbv_Latn data_files: - split: train path: cbv_Latn/*_keep.jsonl - config_name: cbu_Latn data_files: - split: train path: cbu_Latn/*_keep.jsonl - config_name: eza_Latn data_files: - split: train path: eza_Latn/*_keep.jsonl - config_name: kgp_Latn data_files: - split: train path: kgp_Latn/*_keep.jsonl - config_name: sda_Latn data_files: - split: train path: sda_Latn/*_keep.jsonl - config_name: gbo_Latn data_files: - split: train path: gbo_Latn/*_keep.jsonl - config_name: mfi_Latn data_files: - split: train path: mfi_Latn/*_keep.jsonl - config_name: bdd_Latn data_files: - split: train path: bdd_Latn/*_keep.jsonl - config_name: boj_Latn data_files: - split: train path: boj_Latn/*_keep.jsonl - config_name: blh_Latn data_files: - split: train path: blh_Latn/*_keep.jsonl - config_name: ibg_Latn data_files: - split: train path: ibg_Latn/*_keep.jsonl - config_name: agn_Latn data_files: - split: train path: agn_Latn/*_keep.jsonl - config_name: vmy_Latn data_files: - split: train path: vmy_Latn/*_keep.jsonl - config_name: sua_Latn data_files: - split: train path: sua_Latn/*_keep.jsonl - config_name: gul_Latn data_files: - split: train path: gul_Latn/*_keep.jsonl - config_name: rap_Latn data_files: - split: train path: rap_Latn/*_keep.jsonl - config_name: bmh_Latn data_files: - split: train path: bmh_Latn/*_keep.jsonl - config_name: sxn_Latn data_files: - split: train path: sxn_Latn/*_keep.jsonl - config_name: dyi_Latn data_files: - split: train path: dyi_Latn/*_keep.jsonl - config_name: tdx_Latn data_files: - split: train path: tdx_Latn/*_keep.jsonl - config_name: car_Latn data_files: - split: train path: car_Latn/*_keep.jsonl - config_name: heh_Latn data_files: - split: train path: heh_Latn/*_keep.jsonl - config_name: dgc_Latn data_files: - split: train path: dgc_Latn/*_keep.jsonl - config_name: sgb_Latn data_files: - split: train path: sgb_Latn/*_keep.jsonl - config_name: bpr_Latn data_files: - split: train path: bpr_Latn/*_keep.jsonl - config_name: gbi_Latn data_files: - split: train path: gbi_Latn/*_keep.jsonl - config_name: avu_Latn data_files: - split: train path: avu_Latn/*_keep.jsonl - config_name: udu_Latn data_files: - split: train path: udu_Latn/*_keep.jsonl - config_name: yli_Latn data_files: - split: train path: yli_Latn/*_keep.jsonl - config_name: cjs_Cyrl data_files: - split: train path: cjs_Cyrl/*_keep.jsonl - config_name: gnn_Latn data_files: - split: train path: gnn_Latn/*_keep.jsonl - config_name: nhi_Latn data_files: - split: train path: nhi_Latn/*_keep.jsonl - config_name: urk_Thai data_files: - split: train path: urk_Thai/*_keep.jsonl - config_name: kpy_Cyrl data_files: - split: train path: kpy_Cyrl/*_keep.jsonl - config_name: qup_Latn data_files: - split: train path: qup_Latn/*_keep.jsonl - config_name: qvh_Latn data_files: - split: train path: qvh_Latn/*_keep.jsonl - config_name: pir_Latn data_files: - split: train path: pir_Latn/*_keep.jsonl - config_name: tsc_Latn data_files: - split: train path: tsc_Latn/*_keep.jsonl - config_name: bxr_Latn data_files: - split: train path: bxr_Latn/*_keep.jsonl - config_name: thk_Latn data_files: - split: train path: thk_Latn/*_keep.jsonl - config_name: grt_Beng data_files: - split: train path: grt_Beng/*_keep.jsonl - config_name: kqn_Latn data_files: - split: train path: kqn_Latn/*_keep.jsonl - config_name: hay_Latn data_files: - split: train path: hay_Latn/*_keep.jsonl - config_name: mqb_Latn data_files: - split: train path: mqb_Latn/*_keep.jsonl - config_name: tbg_Latn data_files: - split: train path: tbg_Latn/*_keep.jsonl - config_name: bss_Latn data_files: - split: train path: bss_Latn/*_keep.jsonl - config_name: trn_Latn data_files: - split: train path: trn_Latn/*_keep.jsonl - config_name: jae_Latn data_files: - split: train path: jae_Latn/*_keep.jsonl - config_name: myy_Latn data_files: - split: train path: myy_Latn/*_keep.jsonl - config_name: ipk_Latn data_files: - split: train path: ipk_Latn/*_keep.jsonl - config_name: bao_Latn data_files: - split: train path: bao_Latn/*_keep.jsonl - config_name: qvz_Latn data_files: - split: train path: qvz_Latn/*_keep.jsonl - config_name: dua_Latn data_files: - split: train path: dua_Latn/*_keep.jsonl - config_name: mwv_Latn data_files: - split: train path: mwv_Latn/*_keep.jsonl - config_name: nct_Latn data_files: - split: train path: nct_Latn/*_keep.jsonl - config_name: kyc_Latn data_files: - split: train path: kyc_Latn/*_keep.jsonl - config_name: tuo_Latn data_files: - split: train path: tuo_Latn/*_keep.jsonl - config_name: tee_Latn data_files: - split: train path: tee_Latn/*_keep.jsonl - config_name: mop_Latn data_files: - split: train path: mop_Latn/*_keep.jsonl - config_name: mxt_Latn data_files: - split: train path: mxt_Latn/*_keep.jsonl - config_name: qvm_Latn data_files: - split: train path: qvm_Latn/*_keep.jsonl - config_name: gkn_Latn data_files: - split: train path: gkn_Latn/*_keep.jsonl - config_name: lam_Latn data_files: - split: train path: lam_Latn/*_keep.jsonl - config_name: ntr_Latn data_files: - split: train path: ntr_Latn/*_keep.jsonl - config_name: sbe_Latn data_files: - split: train path: sbe_Latn/*_keep.jsonl - config_name: dyo_Latn data_files: - split: train path: dyo_Latn/*_keep.jsonl - config_name: lex_Latn data_files: - split: train path: lex_Latn/*_keep.jsonl - config_name: smk_Latn data_files: - split: train path: smk_Latn/*_keep.jsonl - config_name: coe_Latn data_files: - split: train path: coe_Latn/*_keep.jsonl - config_name: kpe_Latn data_files: - split: train path: kpe_Latn/*_keep.jsonl - config_name: mni_Latn data_files: - split: train path: mni_Latn/*_keep.jsonl - config_name: xbi_Latn data_files: - split: train path: xbi_Latn/*_keep.jsonl - config_name: atb_Latn data_files: - split: train path: atb_Latn/*_keep.jsonl - config_name: tcf_Latn data_files: - split: train path: tcf_Latn/*_keep.jsonl - config_name: bfo_Latn data_files: - split: train path: bfo_Latn/*_keep.jsonl - config_name: cbc_Latn data_files: - split: train path: cbc_Latn/*_keep.jsonl - config_name: swg_Latn data_files: - split: train path: swg_Latn/*_keep.jsonl - config_name: niv_Latn data_files: - split: train path: niv_Latn/*_keep.jsonl - config_name: cnt_Latn data_files: - split: train path: cnt_Latn/*_keep.jsonl - config_name: izz_Latn data_files: - split: train path: izz_Latn/*_keep.jsonl - config_name: knf_Latn data_files: - split: train path: knf_Latn/*_keep.jsonl - config_name: mpp_Latn data_files: - split: train path: mpp_Latn/*_keep.jsonl - config_name: kki_Latn data_files: - split: train path: kki_Latn/*_keep.jsonl - config_name: nho_Latn data_files: - split: train path: nho_Latn/*_keep.jsonl - config_name: sat_Latn data_files: - split: train path: sat_Latn/*_keep.jsonl - config_name: kbr_Latn data_files: - split: train path: kbr_Latn/*_keep.jsonl - config_name: bmu_Latn data_files: - split: train path: bmu_Latn/*_keep.jsonl - config_name: hig_Latn data_files: - split: train path: hig_Latn/*_keep.jsonl - config_name: qxr_Latn data_files: - split: train path: qxr_Latn/*_keep.jsonl - config_name: orv_Cyrl data_files: - split: train path: orv_Cyrl/*_keep.jsonl - config_name: pma_Latn data_files: - split: train path: pma_Latn/*_keep.jsonl - config_name: zpl_Latn data_files: - split: train path: zpl_Latn/*_keep.jsonl - config_name: kpr_Latn data_files: - split: train path: kpr_Latn/*_keep.jsonl - config_name: sig_Latn data_files: - split: train path: sig_Latn/*_keep.jsonl - config_name: ory_Latn data_files: - split: train path: ory_Latn/*_keep.jsonl - config_name: mxp_Latn data_files: - split: train path: mxp_Latn/*_keep.jsonl - config_name: lef_Latn data_files: - split: train path: lef_Latn/*_keep.jsonl - config_name: mlp_Latn data_files: - split: train path: mlp_Latn/*_keep.jsonl - config_name: soq_Latn data_files: - split: train path: soq_Latn/*_keep.jsonl - config_name: cre_Latn data_files: - split: train path: cre_Latn/*_keep.jsonl - config_name: aey_Latn data_files: - split: train path: aey_Latn/*_keep.jsonl - config_name: qvs_Latn data_files: - split: train path: qvs_Latn/*_keep.jsonl - config_name: sur_Latn data_files: - split: train path: sur_Latn/*_keep.jsonl - config_name: knc_Arab data_files: - split: train path: knc_Arab/*_keep.jsonl - config_name: suk_Latn data_files: - split: train path: suk_Latn/*_keep.jsonl - config_name: cax_Latn data_files: - split: train path: cax_Latn/*_keep.jsonl - config_name: alq_Latn data_files: - split: train path: alq_Latn/*_keep.jsonl - config_name: chw_Latn data_files: - split: train path: chw_Latn/*_keep.jsonl - config_name: dww_Latn data_files: - split: train path: dww_Latn/*_keep.jsonl - config_name: gog_Latn data_files: - split: train path: gog_Latn/*_keep.jsonl - config_name: viv_Latn data_files: - split: train path: viv_Latn/*_keep.jsonl - config_name: qvw_Latn data_files: - split: train path: qvw_Latn/*_keep.jsonl - config_name: ted_Latn data_files: - split: train path: ted_Latn/*_keep.jsonl - config_name: yuj_Latn data_files: - split: train path: yuj_Latn/*_keep.jsonl - config_name: ziw_Latn data_files: - split: train path: ziw_Latn/*_keep.jsonl - config_name: kto_Latn data_files: - split: train path: kto_Latn/*_keep.jsonl - config_name: mcq_Latn data_files: - split: train path: mcq_Latn/*_keep.jsonl - config_name: sim_Latn data_files: - split: train path: sim_Latn/*_keep.jsonl - config_name: koi_Latn data_files: - split: train path: koi_Latn/*_keep.jsonl - config_name: lue_Latn data_files: - split: train path: lue_Latn/*_keep.jsonl - config_name: cya_Latn data_files: - split: train path: cya_Latn/*_keep.jsonl - config_name: knk_Latn data_files: - split: train path: knk_Latn/*_keep.jsonl - config_name: tpt_Latn data_files: - split: train path: tpt_Latn/*_keep.jsonl - config_name: taj_Deva data_files: - split: train path: taj_Deva/*_keep.jsonl - config_name: blz_Latn data_files: - split: train path: blz_Latn/*_keep.jsonl - config_name: mil_Latn data_files: - split: train path: mil_Latn/*_keep.jsonl - config_name: kde_Latn data_files: - split: train path: kde_Latn/*_keep.jsonl - config_name: kpz_Latn data_files: - split: train path: kpz_Latn/*_keep.jsonl - config_name: hag_Latn data_files: - split: train path: hag_Latn/*_keep.jsonl - config_name: vun_Latn data_files: - split: train path: vun_Latn/*_keep.jsonl - config_name: kus_Latn data_files: - split: train path: kus_Latn/*_keep.jsonl - config_name: lid_Latn data_files: - split: train path: lid_Latn/*_keep.jsonl - config_name: tos_Latn data_files: - split: train path: tos_Latn/*_keep.jsonl - config_name: bfd_Latn data_files: - split: train path: bfd_Latn/*_keep.jsonl - config_name: chd_Latn data_files: - split: train path: chd_Latn/*_keep.jsonl - config_name: cle_Latn data_files: - split: train path: cle_Latn/*_keep.jsonl - config_name: yon_Latn data_files: - split: train path: yon_Latn/*_keep.jsonl - config_name: bgs_Latn data_files: - split: train path: bgs_Latn/*_keep.jsonl - config_name: lsm_Latn data_files: - split: train path: lsm_Latn/*_keep.jsonl - config_name: msb_Latn data_files: - split: train path: msb_Latn/*_keep.jsonl - config_name: ota_Arab data_files: - split: train path: ota_Arab/*_keep.jsonl - config_name: guj_Latn data_files: - split: train path: guj_Latn/*_keep.jsonl - config_name: mxq_Latn data_files: - split: train path: mxq_Latn/*_keep.jsonl - config_name: lfn_Cyrl data_files: - split: train path: lfn_Cyrl/*_keep.jsonl - config_name: myw_Latn data_files: - split: train path: myw_Latn/*_keep.jsonl - config_name: aso_Latn data_files: - split: train path: aso_Latn/*_keep.jsonl - config_name: esu_Latn data_files: - split: train path: esu_Latn/*_keep.jsonl - config_name: kdi_Latn data_files: - split: train path: kdi_Latn/*_keep.jsonl - config_name: bhp_Latn data_files: - split: train path: bhp_Latn/*_keep.jsonl - config_name: mfz_Latn data_files: - split: train path: mfz_Latn/*_keep.jsonl - config_name: sgw_Ethi data_files: - split: train path: sgw_Ethi/*_keep.jsonl - config_name: xsi_Latn data_files: - split: train path: xsi_Latn/*_keep.jsonl - config_name: gun_Latn data_files: - split: train path: gun_Latn/*_keep.jsonl - config_name: kxc_Ethi data_files: - split: train path: kxc_Ethi/*_keep.jsonl - config_name: mux_Latn data_files: - split: train path: mux_Latn/*_keep.jsonl - config_name: otw_Latn data_files: - split: train path: otw_Latn/*_keep.jsonl - config_name: cjp_Latn data_files: - split: train path: cjp_Latn/*_keep.jsonl - config_name: nyo_Latn data_files: - split: train path: nyo_Latn/*_keep.jsonl - config_name: zia_Latn data_files: - split: train path: zia_Latn/*_keep.jsonl - config_name: cco_Latn data_files: - split: train path: cco_Latn/*_keep.jsonl - config_name: ojb_Cans data_files: - split: train path: ojb_Cans/*_keep.jsonl - config_name: ktu_Latn data_files: - split: train path: ktu_Latn/*_keep.jsonl - config_name: cpy_Latn data_files: - split: train path: cpy_Latn/*_keep.jsonl - config_name: txu_Latn data_files: - split: train path: txu_Latn/*_keep.jsonl - config_name: bjr_Latn data_files: - split: train path: bjr_Latn/*_keep.jsonl - config_name: bud_Latn data_files: - split: train path: bud_Latn/*_keep.jsonl - config_name: ken_Latn data_files: - split: train path: ken_Latn/*_keep.jsonl - config_name: bzh_Latn data_files: - split: train path: bzh_Latn/*_keep.jsonl - config_name: ipi_Latn data_files: - split: train path: ipi_Latn/*_keep.jsonl - config_name: crx_Latn data_files: - split: train path: crx_Latn/*_keep.jsonl - config_name: cko_Latn data_files: - split: train path: cko_Latn/*_keep.jsonl - config_name: gnd_Latn data_files: - split: train path: gnd_Latn/*_keep.jsonl - config_name: kix_Latn data_files: - split: train path: kix_Latn/*_keep.jsonl - config_name: mmx_Latn data_files: - split: train path: mmx_Latn/*_keep.jsonl - config_name: esk_Latn data_files: - split: train path: esk_Latn/*_keep.jsonl - config_name: kud_Latn data_files: - split: train path: kud_Latn/*_keep.jsonl - config_name: toh_Latn data_files: - split: train path: toh_Latn/*_keep.jsonl - config_name: byx_Latn data_files: - split: train path: byx_Latn/*_keep.jsonl - config_name: mtp_Latn data_files: - split: train path: mtp_Latn/*_keep.jsonl - config_name: kpv_Latn data_files: - split: train path: kpv_Latn/*_keep.jsonl - config_name: kyz_Latn data_files: - split: train path: kyz_Latn/*_keep.jsonl - config_name: lmp_Latn data_files: - split: train path: lmp_Latn/*_keep.jsonl - config_name: tiy_Latn data_files: - split: train path: tiy_Latn/*_keep.jsonl - config_name: ccp_Latn data_files: - split: train path: ccp_Latn/*_keep.jsonl - config_name: sbl_Latn data_files: - split: train path: sbl_Latn/*_keep.jsonl - config_name: tcs_Latn data_files: - split: train path: tcs_Latn/*_keep.jsonl - config_name: usp_Latn data_files: - split: train path: usp_Latn/*_keep.jsonl - config_name: buk_Latn data_files: - split: train path: buk_Latn/*_keep.jsonl - config_name: hvn_Latn data_files: - split: train path: hvn_Latn/*_keep.jsonl - config_name: amm_Latn data_files: - split: train path: amm_Latn/*_keep.jsonl - config_name: kzj_Latn data_files: - split: train path: kzj_Latn/*_keep.jsonl - config_name: gng_Latn data_files: - split: train path: gng_Latn/*_keep.jsonl - config_name: ter_Latn data_files: - split: train path: ter_Latn/*_keep.jsonl - config_name: kij_Latn data_files: - split: train path: kij_Latn/*_keep.jsonl - config_name: ngl_Latn data_files: - split: train path: ngl_Latn/*_keep.jsonl - config_name: pab_Latn data_files: - split: train path: pab_Latn/*_keep.jsonl - config_name: pad_Latn data_files: - split: train path: pad_Latn/*_keep.jsonl - config_name: kca_Cyrl data_files: - split: train path: kca_Cyrl/*_keep.jsonl - config_name: meq_Latn data_files: - split: train path: meq_Latn/*_keep.jsonl - config_name: kas_Cyrl data_files: - split: train path: kas_Cyrl/*_keep.jsonl - config_name: niq_Latn data_files: - split: train path: niq_Latn/*_keep.jsonl - config_name: dah_Latn data_files: - split: train path: dah_Latn/*_keep.jsonl - config_name: lia_Latn data_files: - split: train path: lia_Latn/*_keep.jsonl - config_name: kss_Latn data_files: - split: train path: kss_Latn/*_keep.jsonl - config_name: bch_Latn data_files: - split: train path: bch_Latn/*_keep.jsonl - config_name: khz_Latn data_files: - split: train path: khz_Latn/*_keep.jsonl - config_name: nop_Latn data_files: - split: train path: nop_Latn/*_keep.jsonl - config_name: yle_Latn data_files: - split: train path: yle_Latn/*_keep.jsonl - config_name: ain_Latn data_files: - split: train path: ain_Latn/*_keep.jsonl - config_name: pem_Latn data_files: - split: train path: pem_Latn/*_keep.jsonl - config_name: yml_Latn data_files: - split: train path: yml_Latn/*_keep.jsonl - config_name: taq_Tfng data_files: - split: train path: taq_Tfng/*_keep.jsonl - config_name: gaw_Latn data_files: - split: train path: gaw_Latn/*_keep.jsonl - config_name: kze_Latn data_files: - split: train path: kze_Latn/*_keep.jsonl - config_name: tby_Latn data_files: - split: train path: tby_Latn/*_keep.jsonl - config_name: cso_Latn data_files: - split: train path: cso_Latn/*_keep.jsonl - config_name: ifb_Latn data_files: - split: train path: ifb_Latn/*_keep.jsonl - config_name: rki_Mymr data_files: - split: train path: rki_Mymr/*_keep.jsonl - config_name: aly_Latn data_files: - split: train path: aly_Latn/*_keep.jsonl - config_name: kmu_Latn data_files: - split: train path: kmu_Latn/*_keep.jsonl - config_name: mhl_Latn data_files: - split: train path: mhl_Latn/*_keep.jsonl - config_name: kmo_Latn data_files: - split: train path: kmo_Latn/*_keep.jsonl - config_name: mva_Latn data_files: - split: train path: mva_Latn/*_keep.jsonl - config_name: opm_Latn data_files: - split: train path: opm_Latn/*_keep.jsonl - config_name: rtm_Latn data_files: - split: train path: rtm_Latn/*_keep.jsonl - config_name: xtn_Latn data_files: - split: train path: xtn_Latn/*_keep.jsonl - config_name: dgr_Latn data_files: - split: train path: dgr_Latn/*_keep.jsonl - config_name: ksr_Latn data_files: - split: train path: ksr_Latn/*_keep.jsonl - config_name: snp_Latn data_files: - split: train path: snp_Latn/*_keep.jsonl - config_name: tvk_Latn data_files: - split: train path: tvk_Latn/*_keep.jsonl - config_name: zpv_Latn data_files: - split: train path: zpv_Latn/*_keep.jsonl - config_name: hrx_Latn data_files: - split: train path: hrx_Latn/*_keep.jsonl - config_name: kwj_Latn data_files: - split: train path: kwj_Latn/*_keep.jsonl - config_name: muh_Latn data_files: - split: train path: muh_Latn/*_keep.jsonl - config_name: kak_Latn data_files: - split: train path: kak_Latn/*_keep.jsonl - config_name: kpw_Latn data_files: - split: train path: kpw_Latn/*_keep.jsonl - config_name: akb_Latn data_files: - split: train path: akb_Latn/*_keep.jsonl - config_name: ybb_Latn data_files: - split: train path: ybb_Latn/*_keep.jsonl - config_name: kjs_Latn data_files: - split: train path: kjs_Latn/*_keep.jsonl - config_name: wuv_Latn data_files: - split: train path: wuv_Latn/*_keep.jsonl - config_name: laj_Latn data_files: - split: train path: laj_Latn/*_keep.jsonl - config_name: ogo_Latn data_files: - split: train path: ogo_Latn/*_keep.jsonl - config_name: nim_Latn data_files: - split: train path: nim_Latn/*_keep.jsonl - config_name: czt_Latn data_files: - split: train path: czt_Latn/*_keep.jsonl - config_name: aoz_Latn data_files: - split: train path: aoz_Latn/*_keep.jsonl - config_name: rro_Latn data_files: - split: train path: rro_Latn/*_keep.jsonl - config_name: yuw_Latn data_files: - split: train path: yuw_Latn/*_keep.jsonl - config_name: heg_Latn data_files: - split: train path: heg_Latn/*_keep.jsonl - config_name: mrw_Latn data_files: - split: train path: mrw_Latn/*_keep.jsonl - config_name: zac_Latn data_files: - split: train path: zac_Latn/*_keep.jsonl - config_name: kpf_Latn data_files: - split: train path: kpf_Latn/*_keep.jsonl - config_name: leu_Latn data_files: - split: train path: leu_Latn/*_keep.jsonl - config_name: nwi_Latn data_files: - split: train path: nwi_Latn/*_keep.jsonl - config_name: awx_Latn data_files: - split: train path: awx_Latn/*_keep.jsonl - config_name: gso_Latn data_files: - split: train path: gso_Latn/*_keep.jsonl - config_name: keo_Latn data_files: - split: train path: keo_Latn/*_keep.jsonl - config_name: tte_Latn data_files: - split: train path: tte_Latn/*_keep.jsonl - config_name: ceg_Latn data_files: - split: train path: ceg_Latn/*_keep.jsonl - config_name: nhy_Latn data_files: - split: train path: nhy_Latn/*_keep.jsonl - config_name: bhw_Latn data_files: - split: train path: bhw_Latn/*_keep.jsonl - config_name: gnw_Latn data_files: - split: train path: gnw_Latn/*_keep.jsonl - config_name: nin_Latn data_files: - split: train path: nin_Latn/*_keep.jsonl - config_name: xmv_Latn data_files: - split: train path: xmv_Latn/*_keep.jsonl - config_name: crm_Cans data_files: - split: train path: crm_Cans/*_keep.jsonl - config_name: mxv_Latn data_files: - split: train path: mxv_Latn/*_keep.jsonl - config_name: ubr_Latn data_files: - split: train path: ubr_Latn/*_keep.jsonl - config_name: gld_Cyrl data_files: - split: train path: gld_Cyrl/*_keep.jsonl - config_name: bzi_Thai data_files: - split: train path: bzi_Thai/*_keep.jsonl - config_name: ann_Latn data_files: - split: train path: ann_Latn/*_keep.jsonl - config_name: lac_Latn data_files: - split: train path: lac_Latn/*_keep.jsonl - config_name: mej_Latn data_files: - split: train path: mej_Latn/*_keep.jsonl - config_name: zpc_Latn data_files: - split: train path: zpc_Latn/*_keep.jsonl - config_name: dje_Latn data_files: - split: train path: dje_Latn/*_keep.jsonl - config_name: caq_Latn data_files: - split: train path: caq_Latn/*_keep.jsonl - config_name: guk_Ethi data_files: - split: train path: guk_Ethi/*_keep.jsonl - config_name: wos_Latn data_files: - split: train path: wos_Latn/*_keep.jsonl - config_name: msm_Latn data_files: - split: train path: msm_Latn/*_keep.jsonl - config_name: zaw_Latn data_files: - split: train path: zaw_Latn/*_keep.jsonl - config_name: cap_Latn data_files: - split: train path: cap_Latn/*_keep.jsonl - config_name: mox_Latn data_files: - split: train path: mox_Latn/*_keep.jsonl - config_name: zab_Latn data_files: - split: train path: zab_Latn/*_keep.jsonl - config_name: mca_Latn data_files: - split: train path: mca_Latn/*_keep.jsonl - config_name: wrs_Latn data_files: - split: train path: wrs_Latn/*_keep.jsonl - config_name: hae_Latn data_files: - split: train path: hae_Latn/*_keep.jsonl - config_name: nss_Latn data_files: - split: train path: nss_Latn/*_keep.jsonl - config_name: rav_Deva data_files: - split: train path: rav_Deva/*_keep.jsonl - config_name: uvh_Latn data_files: - split: train path: uvh_Latn/*_keep.jsonl - config_name: dga_Latn data_files: - split: train path: dga_Latn/*_keep.jsonl - config_name: ppo_Latn data_files: - split: train path: ppo_Latn/*_keep.jsonl - config_name: nog_Latn data_files: - split: train path: nog_Latn/*_keep.jsonl - config_name: arq_Arab data_files: - split: train path: arq_Arab/*_keep.jsonl - config_name: bim_Latn data_files: - split: train path: bim_Latn/*_keep.jsonl - config_name: lwg_Latn data_files: - split: train path: lwg_Latn/*_keep.jsonl - config_name: kms_Latn data_files: - split: train path: kms_Latn/*_keep.jsonl - config_name: kne_Latn data_files: - split: train path: kne_Latn/*_keep.jsonl - config_name: tkl_Latn data_files: - split: train path: tkl_Latn/*_keep.jsonl - config_name: ady_Latn data_files: - split: train path: ady_Latn/*_keep.jsonl - config_name: caf_Latn data_files: - split: train path: caf_Latn/*_keep.jsonl - config_name: zat_Latn data_files: - split: train path: zat_Latn/*_keep.jsonl - config_name: aba_Latn data_files: - split: train path: aba_Latn/*_keep.jsonl - config_name: chf_Latn data_files: - split: train path: chf_Latn/*_keep.jsonl - config_name: lew_Latn data_files: - split: train path: lew_Latn/*_keep.jsonl - config_name: npl_Latn data_files: - split: train path: npl_Latn/*_keep.jsonl - config_name: uvl_Latn data_files: - split: train path: uvl_Latn/*_keep.jsonl - config_name: cdo_Hani data_files: - split: train path: cdo_Hani/*_keep.jsonl - config_name: rmq_Latn data_files: - split: train path: rmq_Latn/*_keep.jsonl - config_name: mek_Latn data_files: - split: train path: mek_Latn/*_keep.jsonl - config_name: snc_Latn data_files: - split: train path: snc_Latn/*_keep.jsonl - config_name: nsn_Latn data_files: - split: train path: nsn_Latn/*_keep.jsonl - config_name: amn_Latn data_files: - split: train path: amn_Latn/*_keep.jsonl - config_name: abz_Latn data_files: - split: train path: abz_Latn/*_keep.jsonl - config_name: cek_Latn data_files: - split: train path: cek_Latn/*_keep.jsonl - config_name: ong_Latn data_files: - split: train path: ong_Latn/*_keep.jsonl - config_name: txq_Latn data_files: - split: train path: txq_Latn/*_keep.jsonl - config_name: bjp_Latn data_files: - split: train path: bjp_Latn/*_keep.jsonl - config_name: gvf_Latn data_files: - split: train path: gvf_Latn/*_keep.jsonl - config_name: crk_Cans data_files: - split: train path: crk_Cans/*_keep.jsonl - config_name: snf_Latn data_files: - split: train path: snf_Latn/*_keep.jsonl - config_name: nhg_Latn data_files: - split: train path: nhg_Latn/*_keep.jsonl - config_name: kqw_Latn data_files: - split: train path: kqw_Latn/*_keep.jsonl - config_name: mic_Latn data_files: - split: train path: mic_Latn/*_keep.jsonl - config_name: mie_Latn data_files: - split: train path: mie_Latn/*_keep.jsonl - config_name: nus_Latn data_files: - split: train path: nus_Latn/*_keep.jsonl - config_name: plu_Latn data_files: - split: train path: plu_Latn/*_keep.jsonl - config_name: idu_Latn data_files: - split: train path: idu_Latn/*_keep.jsonl - config_name: sll_Latn data_files: - split: train path: sll_Latn/*_keep.jsonl - config_name: thl_Deva data_files: - split: train path: thl_Deva/*_keep.jsonl - config_name: bef_Latn data_files: - split: train path: bef_Latn/*_keep.jsonl - config_name: kwd_Latn data_files: - split: train path: kwd_Latn/*_keep.jsonl - config_name: mqy_Latn data_files: - split: train path: mqy_Latn/*_keep.jsonl - config_name: caa_Latn data_files: - split: train path: caa_Latn/*_keep.jsonl - config_name: aia_Latn data_files: - split: train path: aia_Latn/*_keep.jsonl - config_name: wer_Latn data_files: - split: train path: wer_Latn/*_keep.jsonl - config_name: agm_Latn data_files: - split: train path: agm_Latn/*_keep.jsonl - config_name: mbl_Latn data_files: - split: train path: mbl_Latn/*_keep.jsonl - config_name: mbs_Latn data_files: - split: train path: mbs_Latn/*_keep.jsonl - config_name: adh_Latn data_files: - split: train path: adh_Latn/*_keep.jsonl - config_name: hub_Latn data_files: - split: train path: hub_Latn/*_keep.jsonl - config_name: mav_Latn data_files: - split: train path: mav_Latn/*_keep.jsonl - config_name: nab_Latn data_files: - split: train path: nab_Latn/*_keep.jsonl - config_name: bqp_Latn data_files: - split: train path: bqp_Latn/*_keep.jsonl - config_name: guo_Latn data_files: - split: train path: guo_Latn/*_keep.jsonl - config_name: auy_Latn data_files: - split: train path: auy_Latn/*_keep.jsonl - config_name: big_Latn data_files: - split: train path: big_Latn/*_keep.jsonl - config_name: nii_Latn data_files: - split: train path: nii_Latn/*_keep.jsonl - config_name: row_Latn data_files: - split: train path: row_Latn/*_keep.jsonl - config_name: kim_Cyrl data_files: - split: train path: kim_Cyrl/*_keep.jsonl - config_name: mti_Latn data_files: - split: train path: mti_Latn/*_keep.jsonl - config_name: otm_Latn data_files: - split: train path: otm_Latn/*_keep.jsonl - config_name: prg_Latn data_files: - split: train path: prg_Latn/*_keep.jsonl - config_name: icr_Latn data_files: - split: train path: icr_Latn/*_keep.jsonl - config_name: mcp_Latn data_files: - split: train path: mcp_Latn/*_keep.jsonl - config_name: tbo_Latn data_files: - split: train path: tbo_Latn/*_keep.jsonl - config_name: chy_Latn data_files: - split: train path: chy_Latn/*_keep.jsonl - config_name: oji_Latn data_files: - split: train path: oji_Latn/*_keep.jsonl - config_name: kpx_Latn data_files: - split: train path: kpx_Latn/*_keep.jsonl - config_name: lbb_Latn data_files: - split: train path: lbb_Latn/*_keep.jsonl - config_name: pao_Latn data_files: - split: train path: pao_Latn/*_keep.jsonl - config_name: xuo_Latn data_files: - split: train path: xuo_Latn/*_keep.jsonl - config_name: zgh_Tfng data_files: - split: train path: zgh_Tfng/*_keep.jsonl - config_name: wls_Latn data_files: - split: train path: wls_Latn/*_keep.jsonl - config_name: aca_Latn data_files: - split: train path: aca_Latn/*_keep.jsonl - config_name: apy_Latn data_files: - split: train path: apy_Latn/*_keep.jsonl - config_name: wnc_Latn data_files: - split: train path: wnc_Latn/*_keep.jsonl - config_name: ssg_Latn data_files: - split: train path: ssg_Latn/*_keep.jsonl - config_name: eve_Cyrl data_files: - split: train path: eve_Cyrl/*_keep.jsonl - config_name: mee_Latn data_files: - split: train path: mee_Latn/*_keep.jsonl - config_name: yut_Latn data_files: - split: train path: yut_Latn/*_keep.jsonl - config_name: chr_Latn data_files: - split: train path: chr_Latn/*_keep.jsonl - config_name: kxm_Thai data_files: - split: train path: kxm_Thai/*_keep.jsonl - config_name: mur_Latn data_files: - split: train path: mur_Latn/*_keep.jsonl - config_name: lad_Hebr data_files: - split: train path: lad_Hebr/*_keep.jsonl - config_name: mcd_Latn data_files: - split: train path: mcd_Latn/*_keep.jsonl - config_name: cto_Latn data_files: - split: train path: cto_Latn/*_keep.jsonl - config_name: mqj_Latn data_files: - split: train path: mqj_Latn/*_keep.jsonl - config_name: usa_Latn data_files: - split: train path: usa_Latn/*_keep.jsonl - config_name: emi_Latn data_files: - split: train path: emi_Latn/*_keep.jsonl - config_name: liv_Latn data_files: - split: train path: liv_Latn/*_keep.jsonl - config_name: guz_Latn data_files: - split: train path: guz_Latn/*_keep.jsonl - config_name: tgp_Latn data_files: - split: train path: tgp_Latn/*_keep.jsonl - config_name: ncl_Latn data_files: - split: train path: ncl_Latn/*_keep.jsonl - config_name: azg_Latn data_files: - split: train path: azg_Latn/*_keep.jsonl - config_name: kck_Latn data_files: - split: train path: kck_Latn/*_keep.jsonl - config_name: apb_Latn data_files: - split: train path: apb_Latn/*_keep.jsonl - config_name: kbm_Latn data_files: - split: train path: kbm_Latn/*_keep.jsonl - config_name: sgz_Latn data_files: - split: train path: sgz_Latn/*_keep.jsonl - config_name: wsk_Latn data_files: - split: train path: wsk_Latn/*_keep.jsonl - config_name: gbm_Deva data_files: - split: train path: gbm_Deva/*_keep.jsonl - config_name: csw_Latn data_files: - split: train path: csw_Latn/*_keep.jsonl - config_name: ctp_Latn data_files: - split: train path: ctp_Latn/*_keep.jsonl - config_name: eri_Latn data_files: - split: train path: eri_Latn/*_keep.jsonl - config_name: vid_Latn data_files: - split: train path: vid_Latn/*_keep.jsonl - config_name: bsq_Latn data_files: - split: train path: bsq_Latn/*_keep.jsonl - config_name: dak_Latn data_files: - split: train path: dak_Latn/*_keep.jsonl - config_name: tif_Latn data_files: - split: train path: tif_Latn/*_keep.jsonl - config_name: xsr_Deva data_files: - split: train path: xsr_Deva/*_keep.jsonl - config_name: mwp_Latn data_files: - split: train path: mwp_Latn/*_keep.jsonl - config_name: roo_Latn data_files: - split: train path: roo_Latn/*_keep.jsonl - config_name: wbp_Latn data_files: - split: train path: wbp_Latn/*_keep.jsonl - config_name: gdn_Latn data_files: - split: train path: gdn_Latn/*_keep.jsonl - config_name: tgo_Latn data_files: - split: train path: tgo_Latn/*_keep.jsonl - config_name: zpm_Latn data_files: - split: train path: zpm_Latn/*_keep.jsonl - config_name: mih_Latn data_files: - split: train path: mih_Latn/*_keep.jsonl - config_name: qvc_Latn data_files: - split: train path: qvc_Latn/*_keep.jsonl - config_name: tod_Latn data_files: - split: train path: tod_Latn/*_keep.jsonl - config_name: abn_Latn data_files: - split: train path: abn_Latn/*_keep.jsonl - config_name: cao_Latn data_files: - split: train path: cao_Latn/*_keep.jsonl - config_name: kbc_Latn data_files: - split: train path: kbc_Latn/*_keep.jsonl - config_name: kog_Latn data_files: - split: train path: kog_Latn/*_keep.jsonl - config_name: moh_Latn data_files: - split: train path: moh_Latn/*_keep.jsonl - config_name: leh_Latn data_files: - split: train path: leh_Latn/*_keep.jsonl - config_name: nsu_Latn data_files: - split: train path: nsu_Latn/*_keep.jsonl - config_name: okv_Latn data_files: - split: train path: okv_Latn/*_keep.jsonl - config_name: tih_Latn data_files: - split: train path: tih_Latn/*_keep.jsonl - config_name: zos_Latn data_files: - split: train path: zos_Latn/*_keep.jsonl - config_name: llg_Latn data_files: - split: train path: llg_Latn/*_keep.jsonl - config_name: gmv_Ethi data_files: - split: train path: gmv_Ethi/*_keep.jsonl - config_name: kyf_Latn data_files: - split: train path: kyf_Latn/*_keep.jsonl - config_name: mhx_Latn data_files: - split: train path: mhx_Latn/*_keep.jsonl - config_name: mvp_Latn data_files: - split: train path: mvp_Latn/*_keep.jsonl - config_name: naf_Latn data_files: - split: train path: naf_Latn/*_keep.jsonl - config_name: ino_Latn data_files: - split: train path: ino_Latn/*_keep.jsonl - config_name: dng_Cyrl data_files: - split: train path: dng_Cyrl/*_keep.jsonl - config_name: mnk_Latn data_files: - split: train path: mnk_Latn/*_keep.jsonl - config_name: oke_Latn data_files: - split: train path: oke_Latn/*_keep.jsonl - config_name: omw_Latn data_files: - split: train path: omw_Latn/*_keep.jsonl - config_name: tnk_Latn data_files: - split: train path: tnk_Latn/*_keep.jsonl - config_name: xtd_Latn data_files: - split: train path: xtd_Latn/*_keep.jsonl - config_name: agt_Latn data_files: - split: train path: agt_Latn/*_keep.jsonl - config_name: cbr_Latn data_files: - split: train path: cbr_Latn/*_keep.jsonl - config_name: eko_Latn data_files: - split: train path: eko_Latn/*_keep.jsonl - config_name: nhk_Latn data_files: - split: train path: nhk_Latn/*_keep.jsonl - config_name: hot_Latn data_files: - split: train path: hot_Latn/*_keep.jsonl - config_name: iou_Latn data_files: - split: train path: iou_Latn/*_keep.jsonl - config_name: mpm_Latn data_files: - split: train path: mpm_Latn/*_keep.jsonl - config_name: myx_Latn data_files: - split: train path: myx_Latn/*_keep.jsonl - config_name: ndh_Latn data_files: - split: train path: ndh_Latn/*_keep.jsonl - config_name: pbb_Latn data_files: - split: train path: pbb_Latn/*_keep.jsonl - config_name: rng_Latn data_files: - split: train path: rng_Latn/*_keep.jsonl - config_name: cri_Latn data_files: - split: train path: cri_Latn/*_keep.jsonl - config_name: bvd_Latn data_files: - split: train path: bvd_Latn/*_keep.jsonl - config_name: kmz_Latn data_files: - split: train path: kmz_Latn/*_keep.jsonl - config_name: cta_Latn data_files: - split: train path: cta_Latn/*_keep.jsonl - config_name: blw_Latn data_files: - split: train path: blw_Latn/*_keep.jsonl - config_name: clu_Latn data_files: - split: train path: clu_Latn/*_keep.jsonl - config_name: cof_Latn data_files: - split: train path: cof_Latn/*_keep.jsonl - config_name: kje_Latn data_files: - split: train path: kje_Latn/*_keep.jsonl - config_name: nmf_Latn data_files: - split: train path: nmf_Latn/*_keep.jsonl - config_name: kbh_Latn data_files: - split: train path: kbh_Latn/*_keep.jsonl - config_name: qxn_Latn data_files: - split: train path: qxn_Latn/*_keep.jsonl - config_name: ria_Latn data_files: - split: train path: ria_Latn/*_keep.jsonl - config_name: wed_Latn data_files: - split: train path: wed_Latn/*_keep.jsonl - config_name: zar_Latn data_files: - split: train path: zar_Latn/*_keep.jsonl - config_name: huv_Latn data_files: - split: train path: huv_Latn/*_keep.jsonl - config_name: lsi_Latn data_files: - split: train path: lsi_Latn/*_keep.jsonl - config_name: msk_Latn data_files: - split: train path: msk_Latn/*_keep.jsonl - config_name: nbq_Latn data_files: - split: train path: nbq_Latn/*_keep.jsonl - config_name: ati_Latn data_files: - split: train path: ati_Latn/*_keep.jsonl - config_name: lww_Latn data_files: - split: train path: lww_Latn/*_keep.jsonl - config_name: yva_Latn data_files: - split: train path: yva_Latn/*_keep.jsonl - config_name: amr_Latn data_files: - split: train path: amr_Latn/*_keep.jsonl - config_name: lmk_Latn data_files: - split: train path: lmk_Latn/*_keep.jsonl - config_name: tim_Latn data_files: - split: train path: tim_Latn/*_keep.jsonl - config_name: bbb_Latn data_files: - split: train path: bbb_Latn/*_keep.jsonl - config_name: bzd_Latn data_files: - split: train path: bzd_Latn/*_keep.jsonl - config_name: djr_Latn data_files: - split: train path: djr_Latn/*_keep.jsonl - config_name: kwf_Latn data_files: - split: train path: kwf_Latn/*_keep.jsonl - config_name: nuy_Latn data_files: - split: train path: nuy_Latn/*_keep.jsonl - config_name: poi_Latn data_files: - split: train path: poi_Latn/*_keep.jsonl - config_name: ptp_Latn data_files: - split: train path: ptp_Latn/*_keep.jsonl - config_name: atd_Latn data_files: - split: train path: atd_Latn/*_keep.jsonl - config_name: bps_Latn data_files: - split: train path: bps_Latn/*_keep.jsonl - config_name: lcm_Latn data_files: - split: train path: lcm_Latn/*_keep.jsonl - config_name: mbh_Latn data_files: - split: train path: mbh_Latn/*_keep.jsonl - config_name: nuj_Latn data_files: - split: train path: nuj_Latn/*_keep.jsonl - config_name: ayp_Arab data_files: - split: train path: ayp_Arab/*_keep.jsonl - config_name: cwe_Latn data_files: - split: train path: cwe_Latn/*_keep.jsonl - config_name: geb_Latn data_files: - split: train path: geb_Latn/*_keep.jsonl - config_name: aoi_Latn data_files: - split: train path: aoi_Latn/*_keep.jsonl - config_name: mto_Latn data_files: - split: train path: mto_Latn/*_keep.jsonl - config_name: cbi_Latn data_files: - split: train path: cbi_Latn/*_keep.jsonl - config_name: gvn_Latn data_files: - split: train path: gvn_Latn/*_keep.jsonl - config_name: kqf_Latn data_files: - split: train path: kqf_Latn/*_keep.jsonl - config_name: rkb_Latn data_files: - split: train path: rkb_Latn/*_keep.jsonl - config_name: xed_Latn data_files: - split: train path: xed_Latn/*_keep.jsonl - config_name: zas_Latn data_files: - split: train path: zas_Latn/*_keep.jsonl - config_name: apz_Latn data_files: - split: train path: apz_Latn/*_keep.jsonl - config_name: cpb_Latn data_files: - split: train path: cpb_Latn/*_keep.jsonl - config_name: ese_Latn data_files: - split: train path: ese_Latn/*_keep.jsonl - config_name: gdg_Latn data_files: - split: train path: gdg_Latn/*_keep.jsonl - config_name: iws_Latn data_files: - split: train path: iws_Latn/*_keep.jsonl - config_name: apu_Latn data_files: - split: train path: apu_Latn/*_keep.jsonl - config_name: cag_Latn data_files: - split: train path: cag_Latn/*_keep.jsonl - config_name: kdc_Latn data_files: - split: train path: kdc_Latn/*_keep.jsonl - config_name: nou_Latn data_files: - split: train path: nou_Latn/*_keep.jsonl - config_name: too_Latn data_files: - split: train path: too_Latn/*_keep.jsonl - config_name: xmm_Latn data_files: - split: train path: xmm_Latn/*_keep.jsonl - config_name: beq_Latn data_files: - split: train path: beq_Latn/*_keep.jsonl - config_name: hnn_Latn data_files: - split: train path: hnn_Latn/*_keep.jsonl - config_name: myk_Latn data_files: - split: train path: myk_Latn/*_keep.jsonl - config_name: sby_Latn data_files: - split: train path: sby_Latn/*_keep.jsonl - config_name: arl_Latn data_files: - split: train path: arl_Latn/*_keep.jsonl - config_name: ncu_Latn data_files: - split: train path: ncu_Latn/*_keep.jsonl - config_name: rml_Latn data_files: - split: train path: rml_Latn/*_keep.jsonl - config_name: gam_Latn data_files: - split: train path: gam_Latn/*_keep.jsonl - config_name: kvn_Latn data_files: - split: train path: kvn_Latn/*_keep.jsonl - config_name: mbc_Latn data_files: - split: train path: mbc_Latn/*_keep.jsonl - config_name: mfy_Latn data_files: - split: train path: mfy_Latn/*_keep.jsonl - config_name: urt_Latn data_files: - split: train path: urt_Latn/*_keep.jsonl - config_name: luc_Latn data_files: - split: train path: luc_Latn/*_keep.jsonl - config_name: mio_Latn data_files: - split: train path: mio_Latn/*_keep.jsonl - config_name: snn_Latn data_files: - split: train path: snn_Latn/*_keep.jsonl - config_name: tar_Latn data_files: - split: train path: tar_Latn/*_keep.jsonl - config_name: tku_Latn data_files: - split: train path: tku_Latn/*_keep.jsonl - config_name: upv_Latn data_files: - split: train path: upv_Latn/*_keep.jsonl - config_name: kjg_Laoo data_files: - split: train path: kjg_Laoo/*_keep.jsonl - config_name: btd_Latn data_files: - split: train path: btd_Latn/*_keep.jsonl - config_name: cut_Latn data_files: - split: train path: cut_Latn/*_keep.jsonl - config_name: mwn_Latn data_files: - split: train path: mwn_Latn/*_keep.jsonl - config_name: tue_Latn data_files: - split: train path: tue_Latn/*_keep.jsonl - config_name: adz_Latn data_files: - split: train path: adz_Latn/*_keep.jsonl - config_name: kyg_Latn data_files: - split: train path: kyg_Latn/*_keep.jsonl - config_name: rel_Latn data_files: - split: train path: rel_Latn/*_keep.jsonl - config_name: tew_Latn data_files: - split: train path: tew_Latn/*_keep.jsonl - config_name: ttc_Latn data_files: - split: train path: ttc_Latn/*_keep.jsonl - config_name: nkf_Latn data_files: - split: train path: nkf_Latn/*_keep.jsonl - config_name: yrb_Latn data_files: - split: train path: yrb_Latn/*_keep.jsonl - config_name: fub_Latn data_files: - split: train path: fub_Latn/*_keep.jsonl - config_name: nsm_Latn data_files: - split: train path: nsm_Latn/*_keep.jsonl - config_name: nyf_Latn data_files: - split: train path: nyf_Latn/*_keep.jsonl - config_name: ava_Latn data_files: - split: train path: ava_Latn/*_keep.jsonl - config_name: bkd_Latn data_files: - split: train path: bkd_Latn/*_keep.jsonl - config_name: cpc_Latn data_files: - split: train path: cpc_Latn/*_keep.jsonl - config_name: lif_Limb data_files: - split: train path: lif_Limb/*_keep.jsonl - config_name: mwc_Latn data_files: - split: train path: mwc_Latn/*_keep.jsonl - config_name: gan_Latn data_files: - split: train path: gan_Latn/*_keep.jsonl - config_name: apw_Latn data_files: - split: train path: apw_Latn/*_keep.jsonl - config_name: azz_Latn data_files: - split: train path: azz_Latn/*_keep.jsonl - config_name: zpo_Latn data_files: - split: train path: zpo_Latn/*_keep.jsonl - config_name: ace_Arab data_files: - split: train path: ace_Arab/*_keep.jsonl - config_name: faa_Latn data_files: - split: train path: faa_Latn/*_keep.jsonl - config_name: ood_Latn data_files: - split: train path: ood_Latn/*_keep.jsonl - config_name: toc_Latn data_files: - split: train path: toc_Latn/*_keep.jsonl - config_name: wmt_Latn data_files: - split: train path: wmt_Latn/*_keep.jsonl - config_name: ajg_Latn data_files: - split: train path: ajg_Latn/*_keep.jsonl - config_name: nko_Latn data_files: - split: train path: nko_Latn/*_keep.jsonl - config_name: ssd_Latn data_files: - split: train path: ssd_Latn/*_keep.jsonl - config_name: sxb_Latn data_files: - split: train path: sxb_Latn/*_keep.jsonl - config_name: zxx_Latn data_files: - split: train path: zxx_Latn/*_keep.jsonl - config_name: not_Latn data_files: - split: train path: not_Latn/*_keep.jsonl - config_name: amk_Latn data_files: - split: train path: amk_Latn/*_keep.jsonl - config_name: hch_Latn data_files: - split: train path: hch_Latn/*_keep.jsonl - config_name: kqc_Latn data_files: - split: train path: kqc_Latn/*_keep.jsonl - config_name: aui_Latn data_files: - split: train path: aui_Latn/*_keep.jsonl - config_name: llb_Latn data_files: - split: train path: llb_Latn/*_keep.jsonl - config_name: avt_Latn data_files: - split: train path: avt_Latn/*_keep.jsonl - config_name: kaq_Latn data_files: - split: train path: kaq_Latn/*_keep.jsonl - config_name: tna_Latn data_files: - split: train path: tna_Latn/*_keep.jsonl - config_name: zpt_Latn data_files: - split: train path: zpt_Latn/*_keep.jsonl - config_name: mnw_Latn data_files: - split: train path: mnw_Latn/*_keep.jsonl - config_name: bwd_Latn data_files: - split: train path: bwd_Latn/*_keep.jsonl - config_name: lif_Deva data_files: - split: train path: lif_Deva/*_keep.jsonl - config_name: stn_Latn data_files: - split: train path: stn_Latn/*_keep.jsonl - config_name: crk_Latn data_files: - split: train path: crk_Latn/*_keep.jsonl - config_name: kgk_Latn data_files: - split: train path: kgk_Latn/*_keep.jsonl - config_name: mck_Latn data_files: - split: train path: mck_Latn/*_keep.jsonl - config_name: bhg_Latn data_files: - split: train path: bhg_Latn/*_keep.jsonl - config_name: ifu_Latn data_files: - split: train path: ifu_Latn/*_keep.jsonl - config_name: kkl_Latn data_files: - split: train path: kkl_Latn/*_keep.jsonl - config_name: zao_Latn data_files: - split: train path: zao_Latn/*_keep.jsonl - config_name: huu_Latn data_files: - split: train path: huu_Latn/*_keep.jsonl - config_name: sil_Latn data_files: - split: train path: sil_Latn/*_keep.jsonl - config_name: trq_Latn data_files: - split: train path: trq_Latn/*_keep.jsonl - config_name: tuf_Latn data_files: - split: train path: tuf_Latn/*_keep.jsonl - config_name: wnu_Latn data_files: - split: train path: wnu_Latn/*_keep.jsonl - config_name: amf_Latn data_files: - split: train path: amf_Latn/*_keep.jsonl - config_name: fan_Latn data_files: - split: train path: fan_Latn/*_keep.jsonl - config_name: zdj_Latn data_files: - split: train path: zdj_Latn/*_keep.jsonl - config_name: bco_Latn data_files: - split: train path: bco_Latn/*_keep.jsonl - config_name: kdl_Latn data_files: - split: train path: kdl_Latn/*_keep.jsonl - config_name: lln_Latn data_files: - split: train path: lln_Latn/*_keep.jsonl - config_name: mit_Latn data_files: - split: train path: mit_Latn/*_keep.jsonl - config_name: yaq_Latn data_files: - split: train path: yaq_Latn/*_keep.jsonl - config_name: ake_Latn data_files: - split: train path: ake_Latn/*_keep.jsonl - config_name: ige_Latn data_files: - split: train path: ige_Latn/*_keep.jsonl - config_name: mna_Latn data_files: - split: train path: mna_Latn/*_keep.jsonl - config_name: nhx_Latn data_files: - split: train path: nhx_Latn/*_keep.jsonl - config_name: njn_Latn data_files: - split: train path: njn_Latn/*_keep.jsonl - config_name: wba_Latn data_files: - split: train path: wba_Latn/*_keep.jsonl - config_name: zaa_Latn data_files: - split: train path: zaa_Latn/*_keep.jsonl - config_name: lez_Latn data_files: - split: train path: lez_Latn/*_keep.jsonl - config_name: syb_Latn data_files: - split: train path: syb_Latn/*_keep.jsonl - config_name: qxo_Latn data_files: - split: train path: qxo_Latn/*_keep.jsonl - config_name: rgu_Latn data_files: - split: train path: rgu_Latn/*_keep.jsonl - config_name: wiu_Latn data_files: - split: train path: wiu_Latn/*_keep.jsonl - config_name: bla_Latn data_files: - split: train path: bla_Latn/*_keep.jsonl - config_name: etr_Latn data_files: - split: train path: etr_Latn/*_keep.jsonl - config_name: miy_Latn data_files: - split: train path: miy_Latn/*_keep.jsonl - config_name: mjc_Latn data_files: - split: train path: mjc_Latn/*_keep.jsonl - config_name: nif_Latn data_files: - split: train path: nif_Latn/*_keep.jsonl - config_name: pov_Latn data_files: - split: train path: pov_Latn/*_keep.jsonl - config_name: qxl_Latn data_files: - split: train path: qxl_Latn/*_keep.jsonl - config_name: sey_Latn data_files: - split: train path: sey_Latn/*_keep.jsonl - config_name: bxh_Latn data_files: - split: train path: bxh_Latn/*_keep.jsonl - config_name: ddg_Latn data_files: - split: train path: ddg_Latn/*_keep.jsonl - config_name: mks_Latn data_files: - split: train path: mks_Latn/*_keep.jsonl - config_name: nki_Latn data_files: - split: train path: nki_Latn/*_keep.jsonl - config_name: pot_Latn data_files: - split: train path: pot_Latn/*_keep.jsonl - config_name: prf_Latn data_files: - split: train path: prf_Latn/*_keep.jsonl - config_name: hra_Latn data_files: - split: train path: hra_Latn/*_keep.jsonl - config_name: law_Latn data_files: - split: train path: law_Latn/*_keep.jsonl - config_name: plw_Latn data_files: - split: train path: plw_Latn/*_keep.jsonl - config_name: zpi_Latn data_files: - split: train path: zpi_Latn/*_keep.jsonl - config_name: atg_Latn data_files: - split: train path: atg_Latn/*_keep.jsonl - config_name: daf_Latn data_files: - split: train path: daf_Latn/*_keep.jsonl - config_name: drg_Latn data_files: - split: train path: drg_Latn/*_keep.jsonl - config_name: dru_Latn data_files: - split: train path: dru_Latn/*_keep.jsonl - config_name: ngp_Latn data_files: - split: train path: ngp_Latn/*_keep.jsonl - config_name: boa_Latn data_files: - split: train path: boa_Latn/*_keep.jsonl - config_name: cbt_Latn data_files: - split: train path: cbt_Latn/*_keep.jsonl - config_name: dhm_Latn data_files: - split: train path: dhm_Latn/*_keep.jsonl - config_name: ikw_Latn data_files: - split: train path: ikw_Latn/*_keep.jsonl - config_name: kqe_Latn data_files: - split: train path: kqe_Latn/*_keep.jsonl - config_name: lbj_Tibt data_files: - split: train path: lbj_Tibt/*_keep.jsonl - config_name: loq_Latn data_files: - split: train path: loq_Latn/*_keep.jsonl - config_name: xsb_Latn data_files: - split: train path: xsb_Latn/*_keep.jsonl - config_name: yad_Latn data_files: - split: train path: yad_Latn/*_keep.jsonl - config_name: kyu_Latn data_files: - split: train path: kyu_Latn/*_keep.jsonl - config_name: mcb_Latn data_files: - split: train path: mcb_Latn/*_keep.jsonl - config_name: tks_Arab data_files: - split: train path: tks_Arab/*_keep.jsonl - config_name: cnl_Latn data_files: - split: train path: cnl_Latn/*_keep.jsonl - config_name: far_Latn data_files: - split: train path: far_Latn/*_keep.jsonl - config_name: miz_Latn data_files: - split: train path: miz_Latn/*_keep.jsonl - config_name: maj_Latn data_files: - split: train path: maj_Latn/*_keep.jsonl - config_name: mgm_Latn data_files: - split: train path: mgm_Latn/*_keep.jsonl - config_name: mib_Latn data_files: - split: train path: mib_Latn/*_keep.jsonl - config_name: mza_Latn data_files: - split: train path: mza_Latn/*_keep.jsonl - config_name: nhr_Latn data_files: - split: train path: nhr_Latn/*_keep.jsonl - config_name: smt_Latn data_files: - split: train path: smt_Latn/*_keep.jsonl - config_name: ish_Latn data_files: - split: train path: ish_Latn/*_keep.jsonl - config_name: mlu_Latn data_files: - split: train path: mlu_Latn/*_keep.jsonl - config_name: yka_Latn data_files: - split: train path: yka_Latn/*_keep.jsonl - config_name: anv_Latn data_files: - split: train path: anv_Latn/*_keep.jsonl - config_name: ign_Latn data_files: - split: train path: ign_Latn/*_keep.jsonl - config_name: mir_Latn data_files: - split: train path: mir_Latn/*_keep.jsonl - config_name: tav_Latn data_files: - split: train path: tav_Latn/*_keep.jsonl - config_name: gyr_Latn data_files: - split: train path: gyr_Latn/*_keep.jsonl - config_name: klt_Latn data_files: - split: train path: klt_Latn/*_keep.jsonl - config_name: apn_Latn data_files: - split: train path: apn_Latn/*_keep.jsonl - config_name: wbm_Latn data_files: - split: train path: wbm_Latn/*_keep.jsonl - config_name: cjk_Latn data_files: - split: train path: cjk_Latn/*_keep.jsonl - config_name: dln_Latn data_files: - split: train path: dln_Latn/*_keep.jsonl - config_name: mcf_Latn data_files: - split: train path: mcf_Latn/*_keep.jsonl - config_name: twx_Latn data_files: - split: train path: twx_Latn/*_keep.jsonl - config_name: ldi_Latn data_files: - split: train path: ldi_Latn/*_keep.jsonl - config_name: poy_Latn data_files: - split: train path: poy_Latn/*_keep.jsonl - config_name: yaa_Latn data_files: - split: train path: yaa_Latn/*_keep.jsonl - config_name: zae_Latn data_files: - split: train path: zae_Latn/*_keep.jsonl - config_name: bdq_Latn data_files: - split: train path: bdq_Latn/*_keep.jsonl - config_name: con_Latn data_files: - split: train path: con_Latn/*_keep.jsonl - config_name: dnw_Latn data_files: - split: train path: dnw_Latn/*_keep.jsonl - config_name: gah_Latn data_files: - split: train path: gah_Latn/*_keep.jsonl - config_name: lcp_Thai data_files: - split: train path: lcp_Thai/*_keep.jsonl - config_name: mbj_Latn data_files: - split: train path: mbj_Latn/*_keep.jsonl - config_name: xog_Latn data_files: - split: train path: xog_Latn/*_keep.jsonl - config_name: yan_Latn data_files: - split: train path: yan_Latn/*_keep.jsonl - config_name: sdq_Latn data_files: - split: train path: sdq_Latn/*_keep.jsonl - config_name: sgh_Cyrl data_files: - split: train path: sgh_Cyrl/*_keep.jsonl - config_name: gwi_Latn data_files: - split: train path: gwi_Latn/*_keep.jsonl - config_name: lbk_Latn data_files: - split: train path: lbk_Latn/*_keep.jsonl - config_name: ses_Latn data_files: - split: train path: ses_Latn/*_keep.jsonl - config_name: ycn_Latn data_files: - split: train path: ycn_Latn/*_keep.jsonl - config_name: kau_Latn data_files: - split: train path: kau_Latn/*_keep.jsonl - config_name: hix_Latn data_files: - split: train path: hix_Latn/*_keep.jsonl - config_name: mig_Latn data_files: - split: train path: mig_Latn/*_keep.jsonl - config_name: mlh_Latn data_files: - split: train path: mlh_Latn/*_keep.jsonl - config_name: aer_Latn data_files: - split: train path: aer_Latn/*_keep.jsonl - config_name: amx_Latn data_files: - split: train path: amx_Latn/*_keep.jsonl - config_name: auc_Latn data_files: - split: train path: auc_Latn/*_keep.jsonl - config_name: cly_Latn data_files: - split: train path: cly_Latn/*_keep.jsonl - config_name: dsh_Latn data_files: - split: train path: dsh_Latn/*_keep.jsonl - config_name: gnb_Latn data_files: - split: train path: gnb_Latn/*_keep.jsonl - config_name: neb_Latn data_files: - split: train path: neb_Latn/*_keep.jsonl - config_name: ttt_Cyrl data_files: - split: train path: ttt_Cyrl/*_keep.jsonl - config_name: jic_Latn data_files: - split: train path: jic_Latn/*_keep.jsonl - config_name: xtm_Latn data_files: - split: train path: xtm_Latn/*_keep.jsonl - config_name: tll_Latn data_files: - split: train path: tll_Latn/*_keep.jsonl - config_name: apt_Latn data_files: - split: train path: apt_Latn/*_keep.jsonl - config_name: kgr_Latn data_files: - split: train path: kgr_Latn/*_keep.jsonl - config_name: pio_Latn data_files: - split: train path: pio_Latn/*_keep.jsonl - config_name: pmf_Latn data_files: - split: train path: pmf_Latn/*_keep.jsonl - config_name: yrk_Latn data_files: - split: train path: yrk_Latn/*_keep.jsonl - config_name: akh_Latn data_files: - split: train path: akh_Latn/*_keep.jsonl - config_name: box_Latn data_files: - split: train path: box_Latn/*_keep.jsonl - config_name: cub_Latn data_files: - split: train path: cub_Latn/*_keep.jsonl - config_name: cux_Latn data_files: - split: train path: cux_Latn/*_keep.jsonl - config_name: mrq_Latn data_files: - split: train path: mrq_Latn/*_keep.jsonl - config_name: inh_Latn data_files: - split: train path: inh_Latn/*_keep.jsonl - config_name: bsp_Latn data_files: - split: train path: bsp_Latn/*_keep.jsonl - config_name: for_Latn data_files: - split: train path: for_Latn/*_keep.jsonl - config_name: kny_Latn data_files: - split: train path: kny_Latn/*_keep.jsonl - config_name: uri_Latn data_files: - split: train path: uri_Latn/*_keep.jsonl - config_name: zsr_Latn data_files: - split: train path: zsr_Latn/*_keep.jsonl - config_name: pce_Mymr data_files: - split: train path: pce_Mymr/*_keep.jsonl - config_name: cme_Latn data_files: - split: train path: cme_Latn/*_keep.jsonl - config_name: cot_Latn data_files: - split: train path: cot_Latn/*_keep.jsonl - config_name: kxw_Latn data_files: - split: train path: kxw_Latn/*_keep.jsonl - config_name: omb_Latn data_files: - split: train path: omb_Latn/*_keep.jsonl - config_name: srq_Latn data_files: - split: train path: srq_Latn/*_keep.jsonl - config_name: vag_Latn data_files: - split: train path: vag_Latn/*_keep.jsonl - config_name: cpu_Latn data_files: - split: train path: cpu_Latn/*_keep.jsonl - config_name: kmy_Latn data_files: - split: train path: kmy_Latn/*_keep.jsonl - config_name: ksc_Latn data_files: - split: train path: ksc_Latn/*_keep.jsonl - config_name: lai_Latn data_files: - split: train path: lai_Latn/*_keep.jsonl - config_name: nnp_Latn data_files: - split: train path: nnp_Latn/*_keep.jsonl - config_name: ruf_Latn data_files: - split: train path: ruf_Latn/*_keep.jsonl - config_name: spm_Latn data_files: - split: train path: spm_Latn/*_keep.jsonl - config_name: tro_Latn data_files: - split: train path: tro_Latn/*_keep.jsonl - config_name: ttj_Latn data_files: - split: train path: ttj_Latn/*_keep.jsonl - config_name: waj_Latn data_files: - split: train path: waj_Latn/*_keep.jsonl - config_name: raj_Deva data_files: - split: train path: raj_Deva/*_keep.jsonl - config_name: ian_Latn data_files: - split: train path: ian_Latn/*_keep.jsonl - config_name: ivb_Latn data_files: - split: train path: ivb_Latn/*_keep.jsonl - config_name: kmm_Latn data_files: - split: train path: kmm_Latn/*_keep.jsonl - config_name: kzf_Latn data_files: - split: train path: kzf_Latn/*_keep.jsonl - config_name: maw_Latn data_files: - split: train path: maw_Latn/*_keep.jsonl - config_name: tuv_Latn data_files: - split: train path: tuv_Latn/*_keep.jsonl - config_name: whk_Latn data_files: - split: train path: whk_Latn/*_keep.jsonl - config_name: zsm_Arab data_files: - split: train path: zsm_Arab/*_keep.jsonl - config_name: aph_Deva data_files: - split: train path: aph_Deva/*_keep.jsonl - config_name: anm_Latn data_files: - split: train path: anm_Latn/*_keep.jsonl - config_name: mny_Latn data_files: - split: train path: mny_Latn/*_keep.jsonl - config_name: bug_Bugi data_files: - split: train path: bug_Bugi/*_keep.jsonl - config_name: trp_Latn data_files: - split: train path: trp_Latn/*_keep.jsonl - config_name: are_Latn data_files: - split: train path: are_Latn/*_keep.jsonl - config_name: esi_Latn data_files: - split: train path: esi_Latn/*_keep.jsonl - config_name: mhi_Latn data_files: - split: train path: mhi_Latn/*_keep.jsonl - config_name: obo_Latn data_files: - split: train path: obo_Latn/*_keep.jsonl - config_name: bwu_Latn data_files: - split: train path: bwu_Latn/*_keep.jsonl - config_name: lwo_Latn data_files: - split: train path: lwo_Latn/*_keep.jsonl - config_name: mrg_Latn data_files: - split: train path: mrg_Latn/*_keep.jsonl - config_name: old_Latn data_files: - split: train path: old_Latn/*_keep.jsonl - config_name: zav_Latn data_files: - split: train path: zav_Latn/*_keep.jsonl - config_name: snk_Latn data_files: - split: train path: snk_Latn/*_keep.jsonl - config_name: daa_Latn data_files: - split: train path: daa_Latn/*_keep.jsonl - config_name: fuq_Latn data_files: - split: train path: fuq_Latn/*_keep.jsonl - config_name: lud_Latn data_files: - split: train path: lud_Latn/*_keep.jsonl - config_name: nlg_Latn data_files: - split: train path: nlg_Latn/*_keep.jsonl - config_name: sck_Deva data_files: - split: train path: sck_Deva/*_keep.jsonl - config_name: tbl_Latn data_files: - split: train path: tbl_Latn/*_keep.jsonl - config_name: khb_Talu data_files: - split: train path: khb_Talu/*_keep.jsonl - config_name: tpu_Khmr data_files: - split: train path: tpu_Khmr/*_keep.jsonl - config_name: fue_Latn data_files: - split: train path: fue_Latn/*_keep.jsonl - config_name: tmd_Latn data_files: - split: train path: tmd_Latn/*_keep.jsonl - config_name: whg_Latn data_files: - split: train path: whg_Latn/*_keep.jsonl - config_name: blt_Latn data_files: - split: train path: blt_Latn/*_keep.jsonl - config_name: gqr_Latn data_files: - split: train path: gqr_Latn/*_keep.jsonl - config_name: kub_Latn data_files: - split: train path: kub_Latn/*_keep.jsonl - config_name: ots_Latn data_files: - split: train path: ots_Latn/*_keep.jsonl - config_name: tpp_Latn data_files: - split: train path: tpp_Latn/*_keep.jsonl - config_name: var_Latn data_files: - split: train path: var_Latn/*_keep.jsonl - config_name: hbb_Latn data_files: - split: train path: hbb_Latn/*_keep.jsonl - config_name: krr_Khmr data_files: - split: train path: krr_Khmr/*_keep.jsonl - config_name: zxx_Zyyy data_files: - split: train path: zxx_Zyyy/*_keep.jsonl - config_name: alj_Latn data_files: - split: train path: alj_Latn/*_keep.jsonl - config_name: ebk_Latn data_files: - split: train path: ebk_Latn/*_keep.jsonl - config_name: goa_Latn data_files: - split: train path: goa_Latn/*_keep.jsonl - config_name: hav_Latn data_files: - split: train path: hav_Latn/*_keep.jsonl - config_name: kmk_Latn data_files: - split: train path: kmk_Latn/*_keep.jsonl - config_name: kqo_Latn data_files: - split: train path: kqo_Latn/*_keep.jsonl - config_name: muy_Latn data_files: - split: train path: muy_Latn/*_keep.jsonl - config_name: njb_Latn data_files: - split: train path: njb_Latn/*_keep.jsonl - config_name: snw_Latn data_files: - split: train path: snw_Latn/*_keep.jsonl - config_name: wib_Latn data_files: - split: train path: wib_Latn/*_keep.jsonl - config_name: shn_Latn data_files: - split: train path: shn_Latn/*_keep.jsonl - config_name: tkr_Latn data_files: - split: train path: tkr_Latn/*_keep.jsonl - config_name: ksp_Latn data_files: - split: train path: ksp_Latn/*_keep.jsonl - config_name: lip_Latn data_files: - split: train path: lip_Latn/*_keep.jsonl - config_name: mog_Latn data_files: - split: train path: mog_Latn/*_keep.jsonl - config_name: nla_Latn data_files: - split: train path: nla_Latn/*_keep.jsonl - config_name: pss_Latn data_files: - split: train path: pss_Latn/*_keep.jsonl - config_name: zad_Latn data_files: - split: train path: zad_Latn/*_keep.jsonl - config_name: awi_Latn data_files: - split: train path: awi_Latn/*_keep.jsonl - config_name: frd_Latn data_files: - split: train path: frd_Latn/*_keep.jsonl - config_name: kei_Latn data_files: - split: train path: kei_Latn/*_keep.jsonl - config_name: kmd_Latn data_files: - split: train path: kmd_Latn/*_keep.jsonl - config_name: mim_Latn data_files: - split: train path: mim_Latn/*_keep.jsonl - config_name: got_Latn data_files: - split: train path: got_Latn/*_keep.jsonl - config_name: lbe_Latn data_files: - split: train path: lbe_Latn/*_keep.jsonl - config_name: adi_Latn data_files: - split: train path: adi_Latn/*_keep.jsonl - config_name: any_Latn data_files: - split: train path: any_Latn/*_keep.jsonl - config_name: arp_Latn data_files: - split: train path: arp_Latn/*_keep.jsonl - config_name: biu_Latn data_files: - split: train path: biu_Latn/*_keep.jsonl - config_name: bvc_Latn data_files: - split: train path: bvc_Latn/*_keep.jsonl - config_name: ghs_Latn data_files: - split: train path: ghs_Latn/*_keep.jsonl - config_name: ttq_Latn data_files: - split: train path: ttq_Latn/*_keep.jsonl - config_name: vmk_Latn data_files: - split: train path: vmk_Latn/*_keep.jsonl - config_name: zpj_Latn data_files: - split: train path: zpj_Latn/*_keep.jsonl - config_name: crl_Cans data_files: - split: train path: crl_Cans/*_keep.jsonl - config_name: dtb_Latn data_files: - split: train path: dtb_Latn/*_keep.jsonl - config_name: dug_Latn data_files: - split: train path: dug_Latn/*_keep.jsonl - config_name: kam_Latn data_files: - split: train path: kam_Latn/*_keep.jsonl - config_name: nmo_Latn data_files: - split: train path: nmo_Latn/*_keep.jsonl - config_name: qva_Latn data_files: - split: train path: qva_Latn/*_keep.jsonl - config_name: rhg_Latn data_files: - split: train path: rhg_Latn/*_keep.jsonl - config_name: taw_Latn data_files: - split: train path: taw_Latn/*_keep.jsonl - config_name: tui_Latn data_files: - split: train path: tui_Latn/*_keep.jsonl - config_name: uth_Latn data_files: - split: train path: uth_Latn/*_keep.jsonl - config_name: wap_Latn data_files: - split: train path: wap_Latn/*_keep.jsonl - config_name: zpg_Latn data_files: - split: train path: zpg_Latn/*_keep.jsonl - config_name: brb_Khmr data_files: - split: train path: brb_Khmr/*_keep.jsonl - config_name: dty_Latn data_files: - split: train path: dty_Latn/*_keep.jsonl - config_name: syr_Latn data_files: - split: train path: syr_Latn/*_keep.jsonl - config_name: bih_Arab data_files: - split: train path: bih_Arab/*_keep.jsonl - config_name: bqj_Latn data_files: - split: train path: bqj_Latn/*_keep.jsonl - config_name: cjv_Latn data_files: - split: train path: cjv_Latn/*_keep.jsonl - config_name: cnw_Latn data_files: - split: train path: cnw_Latn/*_keep.jsonl - config_name: kgf_Latn data_files: - split: train path: kgf_Latn/*_keep.jsonl - config_name: mfh_Latn data_files: - split: train path: mfh_Latn/*_keep.jsonl - config_name: mns_Cyrl data_files: - split: train path: mns_Cyrl/*_keep.jsonl - config_name: nnw_Latn data_files: - split: train path: nnw_Latn/*_keep.jsonl - config_name: ntp_Latn data_files: - split: train path: ntp_Latn/*_keep.jsonl - config_name: oto_Latn data_files: - split: train path: oto_Latn/*_keep.jsonl - config_name: dks_Latn data_files: - split: train path: dks_Latn/*_keep.jsonl - config_name: mpt_Latn data_files: - split: train path: mpt_Latn/*_keep.jsonl - config_name: nmw_Latn data_files: - split: train path: nmw_Latn/*_keep.jsonl - config_name: sba_Latn data_files: - split: train path: sba_Latn/*_keep.jsonl - config_name: sfw_Latn data_files: - split: train path: sfw_Latn/*_keep.jsonl - config_name: shu_Arab data_files: - split: train path: shu_Arab/*_keep.jsonl - config_name: ury_Latn data_files: - split: train path: ury_Latn/*_keep.jsonl - config_name: yrl_Latn data_files: - split: train path: yrl_Latn/*_keep.jsonl - config_name: arc_Latn data_files: - split: train path: arc_Latn/*_keep.jsonl - config_name: cmo_Khmr data_files: - split: train path: cmo_Khmr/*_keep.jsonl - config_name: xkg_Latn data_files: - split: train path: xkg_Latn/*_keep.jsonl - config_name: iqw_Latn data_files: - split: train path: iqw_Latn/*_keep.jsonl - config_name: kpj_Latn data_files: - split: train path: kpj_Latn/*_keep.jsonl - config_name: nfa_Latn data_files: - split: train path: nfa_Latn/*_keep.jsonl - config_name: nph_Latn data_files: - split: train path: nph_Latn/*_keep.jsonl - config_name: nre_Latn data_files: - split: train path: nre_Latn/*_keep.jsonl - config_name: wsg_Telu data_files: - split: train path: wsg_Telu/*_keep.jsonl - config_name: xsu_Latn data_files: - split: train path: xsu_Latn/*_keep.jsonl - config_name: nut_Latn data_files: - split: train path: nut_Latn/*_keep.jsonl - config_name: bmk_Latn data_files: - split: train path: bmk_Latn/*_keep.jsonl - config_name: cdf_Latn data_files: - split: train path: cdf_Latn/*_keep.jsonl - config_name: enl_Latn data_files: - split: train path: enl_Latn/*_keep.jsonl - config_name: fuv_Arab data_files: - split: train path: fuv_Arab/*_keep.jsonl - config_name: hop_Latn data_files: - split: train path: hop_Latn/*_keep.jsonl - config_name: ife_Latn data_files: - split: train path: ife_Latn/*_keep.jsonl - config_name: lnd_Latn data_files: - split: train path: lnd_Latn/*_keep.jsonl - config_name: mrv_Latn data_files: - split: train path: mrv_Latn/*_keep.jsonl - config_name: nzm_Latn data_files: - split: train path: nzm_Latn/*_keep.jsonl - config_name: tem_Latn data_files: - split: train path: tem_Latn/*_keep.jsonl - config_name: dwr_Ethi data_files: - split: train path: dwr_Ethi/*_keep.jsonl - config_name: gwc_Arab data_files: - split: train path: gwc_Arab/*_keep.jsonl - config_name: udi_Cyrl data_files: - split: train path: udi_Cyrl/*_keep.jsonl - config_name: zha_Hani data_files: - split: train path: zha_Hani/*_keep.jsonl - config_name: ajz_Latn data_files: - split: train path: ajz_Latn/*_keep.jsonl - config_name: kru_Deva data_files: - split: train path: kru_Deva/*_keep.jsonl - config_name: qvo_Latn data_files: - split: train path: qvo_Latn/*_keep.jsonl - config_name: sld_Latn data_files: - split: train path: sld_Latn/*_keep.jsonl - config_name: yup_Latn data_files: - split: train path: yup_Latn/*_keep.jsonl - config_name: anp_Latn data_files: - split: train path: anp_Latn/*_keep.jsonl - config_name: kwu_Latn data_files: - split: train path: kwu_Latn/*_keep.jsonl - config_name: szy_Hani data_files: - split: train path: szy_Hani/*_keep.jsonl - config_name: tdg_Deva data_files: - split: train path: tdg_Deva/*_keep.jsonl - config_name: ade_Latn data_files: - split: train path: ade_Latn/*_keep.jsonl - config_name: bcw_Latn data_files: - split: train path: bcw_Latn/*_keep.jsonl - config_name: bgz_Latn data_files: - split: train path: bgz_Latn/*_keep.jsonl - config_name: cul_Latn data_files: - split: train path: cul_Latn/*_keep.jsonl - config_name: fmu_Deva data_files: - split: train path: fmu_Deva/*_keep.jsonl - config_name: gvc_Latn data_files: - split: train path: gvc_Latn/*_keep.jsonl - config_name: ktj_Latn data_files: - split: train path: ktj_Latn/*_keep.jsonl - config_name: lis_Lisu data_files: - split: train path: lis_Lisu/*_keep.jsonl - config_name: mev_Latn data_files: - split: train path: mev_Latn/*_keep.jsonl - config_name: msc_Latn data_files: - split: train path: msc_Latn/*_keep.jsonl - config_name: mta_Latn data_files: - split: train path: mta_Latn/*_keep.jsonl - config_name: nbc_Latn data_files: - split: train path: nbc_Latn/*_keep.jsonl - config_name: ncq_Laoo data_files: - split: train path: ncq_Laoo/*_keep.jsonl - config_name: way_Latn data_files: - split: train path: way_Latn/*_keep.jsonl - config_name: wlv_Latn data_files: - split: train path: wlv_Latn/*_keep.jsonl - config_name: wlx_Latn data_files: - split: train path: wlx_Latn/*_keep.jsonl - config_name: jmx_Latn data_files: - split: train path: jmx_Latn/*_keep.jsonl - config_name: pli_Latn data_files: - split: train path: pli_Latn/*_keep.jsonl - config_name: tkr_Cyrl data_files: - split: train path: tkr_Cyrl/*_keep.jsonl - config_name: wni_Latn data_files: - split: train path: wni_Latn/*_keep.jsonl - config_name: aim_Latn data_files: - split: train path: aim_Latn/*_keep.jsonl - config_name: byv_Latn data_files: - split: train path: byv_Latn/*_keep.jsonl - config_name: cgg_Latn data_files: - split: train path: cgg_Latn/*_keep.jsonl - config_name: fud_Latn data_files: - split: train path: fud_Latn/*_keep.jsonl - config_name: jmc_Latn data_files: - split: train path: jmc_Latn/*_keep.jsonl - config_name: ker_Latn data_files: - split: train path: ker_Latn/*_keep.jsonl - config_name: kia_Latn data_files: - split: train path: kia_Latn/*_keep.jsonl - config_name: lom_Latn data_files: - split: train path: lom_Latn/*_keep.jsonl - config_name: ojb_Latn data_files: - split: train path: ojb_Latn/*_keep.jsonl - config_name: tnc_Latn data_files: - split: train path: tnc_Latn/*_keep.jsonl - config_name: bwx_Latn data_files: - split: train path: bwx_Latn/*_keep.jsonl - config_name: cre_Cans data_files: - split: train path: cre_Cans/*_keep.jsonl - config_name: skr_Latn data_files: - split: train path: skr_Latn/*_keep.jsonl - config_name: xal_Latn data_files: - split: train path: xal_Latn/*_keep.jsonl - config_name: gjn_Latn data_files: - split: train path: gjn_Latn/*_keep.jsonl - config_name: guq_Latn data_files: - split: train path: guq_Latn/*_keep.jsonl - config_name: lap_Latn data_files: - split: train path: lap_Latn/*_keep.jsonl - config_name: mip_Latn data_files: - split: train path: mip_Latn/*_keep.jsonl - config_name: mkl_Latn data_files: - split: train path: mkl_Latn/*_keep.jsonl - config_name: mtg_Latn data_files: - split: train path: mtg_Latn/*_keep.jsonl - config_name: mzk_Latn data_files: - split: train path: mzk_Latn/*_keep.jsonl - config_name: njm_Latn data_files: - split: train path: njm_Latn/*_keep.jsonl - config_name: nse_Latn data_files: - split: train path: nse_Latn/*_keep.jsonl - config_name: pne_Latn data_files: - split: train path: pne_Latn/*_keep.jsonl - config_name: pww_Thai data_files: - split: train path: pww_Thai/*_keep.jsonl - config_name: zam_Latn data_files: - split: train path: zam_Latn/*_keep.jsonl - config_name: zca_Latn data_files: - split: train path: zca_Latn/*_keep.jsonl - config_name: the_Deva data_files: - split: train path: the_Deva/*_keep.jsonl - config_name: dis_Latn data_files: - split: train path: dis_Latn/*_keep.jsonl - config_name: lgl_Latn data_files: - split: train path: lgl_Latn/*_keep.jsonl - config_name: mbd_Latn data_files: - split: train path: mbd_Latn/*_keep.jsonl - config_name: mda_Latn data_files: - split: train path: mda_Latn/*_keep.jsonl - config_name: mhy_Latn data_files: - split: train path: mhy_Latn/*_keep.jsonl - config_name: nst_Latn data_files: - split: train path: nst_Latn/*_keep.jsonl - config_name: pkb_Latn data_files: - split: train path: pkb_Latn/*_keep.jsonl - config_name: pmq_Latn data_files: - split: train path: pmq_Latn/*_keep.jsonl - config_name: poe_Latn data_files: - split: train path: poe_Latn/*_keep.jsonl - config_name: swk_Latn data_files: - split: train path: swk_Latn/*_keep.jsonl - config_name: trs_Latn data_files: - split: train path: trs_Latn/*_keep.jsonl - config_name: vot_Latn data_files: - split: train path: vot_Latn/*_keep.jsonl - config_name: yam_Latn data_files: - split: train path: yam_Latn/*_keep.jsonl - config_name: zpq_Latn data_files: - split: train path: zpq_Latn/*_keep.jsonl - config_name: atq_Latn data_files: - split: train path: atq_Latn/*_keep.jsonl - config_name: bav_Latn data_files: - split: train path: bav_Latn/*_keep.jsonl - config_name: cho_Latn data_files: - split: train path: cho_Latn/*_keep.jsonl - config_name: chq_Latn data_files: - split: train path: chq_Latn/*_keep.jsonl - config_name: cjo_Latn data_files: - split: train path: cjo_Latn/*_keep.jsonl - config_name: due_Latn data_files: - split: train path: due_Latn/*_keep.jsonl - config_name: duo_Latn data_files: - split: train path: duo_Latn/*_keep.jsonl - config_name: etu_Latn data_files: - split: train path: etu_Latn/*_keep.jsonl - config_name: ifa_Latn data_files: - split: train path: ifa_Latn/*_keep.jsonl - config_name: kby_Latn data_files: - split: train path: kby_Latn/*_keep.jsonl - config_name: khq_Latn data_files: - split: train path: khq_Latn/*_keep.jsonl - config_name: kno_Latn data_files: - split: train path: kno_Latn/*_keep.jsonl - config_name: lem_Latn data_files: - split: train path: lem_Latn/*_keep.jsonl - config_name: mcn_Latn data_files: - split: train path: mcn_Latn/*_keep.jsonl - config_name: mkz_Latn data_files: - split: train path: mkz_Latn/*_keep.jsonl - config_name: mnb_Latn data_files: - split: train path: mnb_Latn/*_keep.jsonl - config_name: myb_Latn data_files: - split: train path: myb_Latn/*_keep.jsonl - config_name: niy_Latn data_files: - split: train path: niy_Latn/*_keep.jsonl - config_name: pxm_Latn data_files: - split: train path: pxm_Latn/*_keep.jsonl - config_name: rub_Latn data_files: - split: train path: rub_Latn/*_keep.jsonl - config_name: sju_Latn data_files: - split: train path: sju_Latn/*_keep.jsonl - config_name: tmc_Latn data_files: - split: train path: tmc_Latn/*_keep.jsonl - config_name: tpm_Latn data_files: - split: train path: tpm_Latn/*_keep.jsonl - config_name: wob_Latn data_files: - split: train path: wob_Latn/*_keep.jsonl - config_name: nxa_Latn data_files: - split: train path: nxa_Latn/*_keep.jsonl - config_name: pnt_Latn data_files: - split: train path: pnt_Latn/*_keep.jsonl - config_name: sdk_Latn data_files: - split: train path: sdk_Latn/*_keep.jsonl - config_name: tcy_Latn data_files: - split: train path: tcy_Latn/*_keep.jsonl - config_name: bhz_Latn data_files: - split: train path: bhz_Latn/*_keep.jsonl - config_name: bth_Latn data_files: - split: train path: bth_Latn/*_keep.jsonl - config_name: crj_Cans data_files: - split: train path: crj_Cans/*_keep.jsonl - config_name: eka_Latn data_files: - split: train path: eka_Latn/*_keep.jsonl - config_name: khy_Latn data_files: - split: train path: khy_Latn/*_keep.jsonl - config_name: led_Latn data_files: - split: train path: led_Latn/*_keep.jsonl - config_name: met_Latn data_files: - split: train path: met_Latn/*_keep.jsonl - config_name: mgo_Latn data_files: - split: train path: mgo_Latn/*_keep.jsonl - config_name: mus_Latn data_files: - split: train path: mus_Latn/*_keep.jsonl - config_name: mzm_Latn data_files: - split: train path: mzm_Latn/*_keep.jsonl - config_name: naw_Latn data_files: - split: train path: naw_Latn/*_keep.jsonl - config_name: sri_Latn data_files: - split: train path: sri_Latn/*_keep.jsonl - config_name: tbk_Latn data_files: - split: train path: tbk_Latn/*_keep.jsonl - config_name: xbr_Latn data_files: - split: train path: xbr_Latn/*_keep.jsonl - config_name: awa_Latn data_files: - split: train path: awa_Latn/*_keep.jsonl - config_name: tnl_Latn data_files: - split: train path: tnl_Latn/*_keep.jsonl - config_name: tnn_Latn data_files: - split: train path: tnn_Latn/*_keep.jsonl - config_name: awb_Latn data_files: - split: train path: awb_Latn/*_keep.jsonl - config_name: bsc_Latn data_files: - split: train path: bsc_Latn/*_keep.jsonl - config_name: iri_Latn data_files: - split: train path: iri_Latn/*_keep.jsonl - config_name: kpq_Latn data_files: - split: train path: kpq_Latn/*_keep.jsonl - config_name: ktm_Latn data_files: - split: train path: ktm_Latn/*_keep.jsonl - config_name: loe_Latn data_files: - split: train path: loe_Latn/*_keep.jsonl - config_name: lun_Latn data_files: - split: train path: lun_Latn/*_keep.jsonl - config_name: mfg_Latn data_files: - split: train path: mfg_Latn/*_keep.jsonl - config_name: moa_Latn data_files: - split: train path: moa_Latn/*_keep.jsonl - config_name: ndj_Latn data_files: - split: train path: ndj_Latn/*_keep.jsonl - config_name: otn_Latn data_files: - split: train path: otn_Latn/*_keep.jsonl - config_name: sjo_Mong data_files: - split: train path: sjo_Mong/*_keep.jsonl - config_name: wat_Latn data_files: - split: train path: wat_Latn/*_keep.jsonl - config_name: bkm_Latn data_files: - split: train path: bkm_Latn/*_keep.jsonl - config_name: tuz_Latn data_files: - split: train path: tuz_Latn/*_keep.jsonl - config_name: ybi_Deva data_files: - split: train path: ybi_Deva/*_keep.jsonl - config_name: gbr_Latn data_files: - split: train path: gbr_Latn/*_keep.jsonl - config_name: gej_Latn data_files: - split: train path: gej_Latn/*_keep.jsonl - config_name: giz_Latn data_files: - split: train path: giz_Latn/*_keep.jsonl - config_name: gna_Latn data_files: - split: train path: gna_Latn/*_keep.jsonl - config_name: gwr_Latn data_files: - split: train path: gwr_Latn/*_keep.jsonl - config_name: kex_Deva data_files: - split: train path: kex_Deva/*_keep.jsonl - config_name: kle_Deva data_files: - split: train path: kle_Deva/*_keep.jsonl - config_name: knx_Latn data_files: - split: train path: knx_Latn/*_keep.jsonl - config_name: ktz_Latn data_files: - split: train path: ktz_Latn/*_keep.jsonl - config_name: kvj_Latn data_files: - split: train path: kvj_Latn/*_keep.jsonl - config_name: lob_Latn data_files: - split: train path: lob_Latn/*_keep.jsonl - config_name: mhw_Latn data_files: - split: train path: mhw_Latn/*_keep.jsonl - config_name: mph_Latn data_files: - split: train path: mph_Latn/*_keep.jsonl - config_name: pmx_Latn data_files: - split: train path: pmx_Latn/*_keep.jsonl - config_name: qus_Latn data_files: - split: train path: qus_Latn/*_keep.jsonl - config_name: tcc_Latn data_files: - split: train path: tcc_Latn/*_keep.jsonl - config_name: ang_Runr data_files: - split: train path: ang_Runr/*_keep.jsonl - config_name: azn_Latn data_files: - split: train path: azn_Latn/*_keep.jsonl - config_name: bra_Deva data_files: - split: train path: bra_Deva/*_keep.jsonl - config_name: gal_Latn data_files: - split: train path: gal_Latn/*_keep.jsonl - config_name: jra_Khmr data_files: - split: train path: jra_Khmr/*_keep.jsonl - config_name: nlv_Latn data_files: - split: train path: nlv_Latn/*_keep.jsonl - config_name: rki_Latn data_files: - split: train path: rki_Latn/*_keep.jsonl - config_name: stk_Latn data_files: - split: train path: stk_Latn/*_keep.jsonl - config_name: yux_Cyrl data_files: - split: train path: yux_Cyrl/*_keep.jsonl - config_name: dip_Latn data_files: - split: train path: dip_Latn/*_keep.jsonl - config_name: ivv_Latn data_files: - split: train path: ivv_Latn/*_keep.jsonl - config_name: kdj_Latn data_files: - split: train path: kdj_Latn/*_keep.jsonl - config_name: kff_Telu data_files: - split: train path: kff_Telu/*_keep.jsonl - config_name: kyu_Kali data_files: - split: train path: kyu_Kali/*_keep.jsonl - config_name: mnf_Latn data_files: - split: train path: mnf_Latn/*_keep.jsonl - config_name: moc_Latn data_files: - split: train path: moc_Latn/*_keep.jsonl - config_name: mpg_Latn data_files: - split: train path: mpg_Latn/*_keep.jsonl - config_name: mua_Latn data_files: - split: train path: mua_Latn/*_keep.jsonl - config_name: nma_Latn data_files: - split: train path: nma_Latn/*_keep.jsonl - config_name: rim_Latn data_files: - split: train path: rim_Latn/*_keep.jsonl - config_name: rjs_Deva data_files: - split: train path: rjs_Deva/*_keep.jsonl - config_name: rnl_Latn data_files: - split: train path: rnl_Latn/*_keep.jsonl - config_name: ssx_Latn data_files: - split: train path: ssx_Latn/*_keep.jsonl - config_name: tig_Ethi data_files: - split: train path: tig_Ethi/*_keep.jsonl - config_name: urw_Latn data_files: - split: train path: urw_Latn/*_keep.jsonl - config_name: idt_Latn data_files: - split: train path: idt_Latn/*_keep.jsonl - config_name: mrn_Latn data_files: - split: train path: mrn_Latn/*_keep.jsonl - config_name: oki_Latn data_files: - split: train path: oki_Latn/*_keep.jsonl - config_name: bbk_Latn data_files: - split: train path: bbk_Latn/*_keep.jsonl - config_name: bea_Latn data_files: - split: train path: bea_Latn/*_keep.jsonl - config_name: bkq_Latn data_files: - split: train path: bkq_Latn/*_keep.jsonl - config_name: btt_Latn data_files: - split: train path: btt_Latn/*_keep.jsonl - config_name: cou_Latn data_files: - split: train path: cou_Latn/*_keep.jsonl - config_name: ddn_Latn data_files: - split: train path: ddn_Latn/*_keep.jsonl - config_name: did_Latn data_files: - split: train path: did_Latn/*_keep.jsonl - config_name: diu_Latn data_files: - split: train path: diu_Latn/*_keep.jsonl - config_name: ilb_Latn data_files: - split: train path: ilb_Latn/*_keep.jsonl - config_name: ksj_Latn data_files: - split: train path: ksj_Latn/*_keep.jsonl - config_name: lhi_Latn data_files: - split: train path: lhi_Latn/*_keep.jsonl - config_name: ndi_Latn data_files: - split: train path: ndi_Latn/*_keep.jsonl - config_name: ngb_Latn data_files: - split: train path: ngb_Latn/*_keep.jsonl - config_name: njz_Latn data_files: - split: train path: njz_Latn/*_keep.jsonl - config_name: nmz_Latn data_files: - split: train path: nmz_Latn/*_keep.jsonl - config_name: npo_Latn data_files: - split: train path: npo_Latn/*_keep.jsonl - config_name: nwb_Latn data_files: - split: train path: nwb_Latn/*_keep.jsonl - config_name: pbi_Latn data_files: - split: train path: pbi_Latn/*_keep.jsonl - config_name: sbd_Latn data_files: - split: train path: sbd_Latn/*_keep.jsonl - config_name: soe_Latn data_files: - split: train path: soe_Latn/*_keep.jsonl - config_name: tpw_Latn data_files: - split: train path: tpw_Latn/*_keep.jsonl - config_name: twb_Latn data_files: - split: train path: twb_Latn/*_keep.jsonl - config_name: bfn_Latn data_files: - split: train path: bfn_Latn/*_keep.jsonl - config_name: boz_Latn data_files: - split: train path: boz_Latn/*_keep.jsonl - config_name: lwl_Thai data_files: - split: train path: lwl_Thai/*_keep.jsonl - config_name: psp_Latn data_files: - split: train path: psp_Latn/*_keep.jsonl - config_name: sgd_Latn data_files: - split: train path: sgd_Latn/*_keep.jsonl - config_name: ymp_Latn data_files: - split: train path: ymp_Latn/*_keep.jsonl - config_name: bkl_Latn data_files: - split: train path: bkl_Latn/*_keep.jsonl - config_name: bkv_Latn data_files: - split: train path: bkv_Latn/*_keep.jsonl - config_name: csk_Latn data_files: - split: train path: csk_Latn/*_keep.jsonl - config_name: enx_Latn data_files: - split: train path: enx_Latn/*_keep.jsonl - config_name: ess_Latn data_files: - split: train path: ess_Latn/*_keep.jsonl - config_name: gof_Ethi data_files: - split: train path: gof_Ethi/*_keep.jsonl - config_name: gud_Latn data_files: - split: train path: gud_Latn/*_keep.jsonl - config_name: guu_Latn data_files: - split: train path: guu_Latn/*_keep.jsonl - config_name: kdh_Latn data_files: - split: train path: kdh_Latn/*_keep.jsonl - config_name: krx_Latn data_files: - split: train path: krx_Latn/*_keep.jsonl - config_name: kzn_Latn data_files: - split: train path: kzn_Latn/*_keep.jsonl - config_name: maf_Latn data_files: - split: train path: maf_Latn/*_keep.jsonl - config_name: max_Latn data_files: - split: train path: max_Latn/*_keep.jsonl - config_name: mgc_Latn data_files: - split: train path: mgc_Latn/*_keep.jsonl - config_name: mvn_Latn data_files: - split: train path: mvn_Latn/*_keep.jsonl - config_name: mwm_Latn data_files: - split: train path: mwm_Latn/*_keep.jsonl - config_name: nbe_Latn data_files: - split: train path: nbe_Latn/*_keep.jsonl - config_name: nlc_Latn data_files: - split: train path: nlc_Latn/*_keep.jsonl - config_name: nxd_Latn data_files: - split: train path: nxd_Latn/*_keep.jsonl - config_name: pse_Latn data_files: - split: train path: pse_Latn/*_keep.jsonl - config_name: sbs_Latn data_files: - split: train path: sbs_Latn/*_keep.jsonl - config_name: tlb_Latn data_files: - split: train path: tlb_Latn/*_keep.jsonl - config_name: wwa_Latn data_files: - split: train path: wwa_Latn/*_keep.jsonl - config_name: yim_Latn data_files: - split: train path: yim_Latn/*_keep.jsonl - config_name: bkx_Latn data_files: - split: train path: bkx_Latn/*_keep.jsonl - config_name: bze_Latn data_files: - split: train path: bze_Latn/*_keep.jsonl - config_name: chu_Latn data_files: - split: train path: chu_Latn/*_keep.jsonl - config_name: kbq_Latn data_files: - split: train path: kbq_Latn/*_keep.jsonl - config_name: kpy_Armn data_files: - split: train path: kpy_Armn/*_keep.jsonl - config_name: mry_Latn data_files: - split: train path: mry_Latn/*_keep.jsonl - config_name: tkd_Latn data_files: - split: train path: tkd_Latn/*_keep.jsonl - config_name: ybh_Deva data_files: - split: train path: ybh_Deva/*_keep.jsonl - config_name: abi_Latn data_files: - split: train path: abi_Latn/*_keep.jsonl - config_name: ayo_Latn data_files: - split: train path: ayo_Latn/*_keep.jsonl - config_name: bex_Latn data_files: - split: train path: bex_Latn/*_keep.jsonl - config_name: bom_Latn data_files: - split: train path: bom_Latn/*_keep.jsonl - config_name: bov_Latn data_files: - split: train path: bov_Latn/*_keep.jsonl - config_name: dhg_Latn data_files: - split: train path: dhg_Latn/*_keep.jsonl - config_name: jaa_Latn data_files: - split: train path: jaa_Latn/*_keep.jsonl - config_name: kqs_Latn data_files: - split: train path: kqs_Latn/*_keep.jsonl - config_name: kqy_Ethi data_files: - split: train path: kqy_Ethi/*_keep.jsonl - config_name: ksb_Latn data_files: - split: train path: ksb_Latn/*_keep.jsonl - config_name: ldn_Latn data_files: - split: train path: ldn_Latn/*_keep.jsonl - config_name: log_Latn data_files: - split: train path: log_Latn/*_keep.jsonl - config_name: lol_Latn data_files: - split: train path: lol_Latn/*_keep.jsonl - config_name: mfk_Latn data_files: - split: train path: mfk_Latn/*_keep.jsonl - config_name: mtj_Latn data_files: - split: train path: mtj_Latn/*_keep.jsonl - config_name: ndz_Latn data_files: - split: train path: ndz_Latn/*_keep.jsonl - config_name: ngc_Latn data_files: - split: train path: ngc_Latn/*_keep.jsonl - config_name: nio_Cyrl data_files: - split: train path: nio_Cyrl/*_keep.jsonl - config_name: nri_Latn data_files: - split: train path: nri_Latn/*_keep.jsonl - config_name: nuz_Latn data_files: - split: train path: nuz_Latn/*_keep.jsonl - config_name: pps_Latn data_files: - split: train path: pps_Latn/*_keep.jsonl - config_name: shk_Latn data_files: - split: train path: shk_Latn/*_keep.jsonl - config_name: tlj_Latn data_files: - split: train path: tlj_Latn/*_keep.jsonl - config_name: vut_Latn data_files: - split: train path: vut_Latn/*_keep.jsonl - config_name: xnn_Latn data_files: - split: train path: xnn_Latn/*_keep.jsonl - config_name: bcc_Arab data_files: - split: train path: bcc_Arab/*_keep.jsonl - config_name: cuh_Latn data_files: - split: train path: cuh_Latn/*_keep.jsonl - config_name: emp_Cyrl data_files: - split: train path: emp_Cyrl/*_keep.jsonl - config_name: hro_Latn data_files: - split: train path: hro_Latn/*_keep.jsonl - config_name: nco_Latn data_files: - split: train path: nco_Latn/*_keep.jsonl - config_name: nxl_Latn data_files: - split: train path: nxl_Latn/*_keep.jsonl - config_name: pex_Latn data_files: - split: train path: pex_Latn/*_keep.jsonl - config_name: tnp_Latn data_files: - split: train path: tnp_Latn/*_keep.jsonl - config_name: trv_Hani data_files: - split: train path: trv_Hani/*_keep.jsonl - config_name: vif_Latn data_files: - split: train path: vif_Latn/*_keep.jsonl - config_name: aha_Latn data_files: - split: train path: aha_Latn/*_keep.jsonl - config_name: avn_Latn data_files: - split: train path: avn_Latn/*_keep.jsonl - config_name: bmv_Latn data_files: - split: train path: bmv_Latn/*_keep.jsonl - config_name: chj_Latn data_files: - split: train path: chj_Latn/*_keep.jsonl - config_name: crt_Latn data_files: - split: train path: crt_Latn/*_keep.jsonl - config_name: dos_Latn data_files: - split: train path: dos_Latn/*_keep.jsonl - config_name: eto_Latn data_files: - split: train path: eto_Latn/*_keep.jsonl - config_name: gya_Latn data_files: - split: train path: gya_Latn/*_keep.jsonl - config_name: hlt_Latn data_files: - split: train path: hlt_Latn/*_keep.jsonl - config_name: jun_Orya data_files: - split: train path: jun_Orya/*_keep.jsonl - config_name: ktb_Ethi data_files: - split: train path: ktb_Ethi/*_keep.jsonl - config_name: lgm_Latn data_files: - split: train path: lgm_Latn/*_keep.jsonl - config_name: mnx_Latn data_files: - split: train path: mnx_Latn/*_keep.jsonl - config_name: mor_Latn data_files: - split: train path: mor_Latn/*_keep.jsonl - config_name: mug_Latn data_files: - split: train path: mug_Latn/*_keep.jsonl - config_name: nng_Latn data_files: - split: train path: nng_Latn/*_keep.jsonl - config_name: nnh_Latn data_files: - split: train path: nnh_Latn/*_keep.jsonl - config_name: nsa_Latn data_files: - split: train path: nsa_Latn/*_keep.jsonl - config_name: nyk_Latn data_files: - split: train path: nyk_Latn/*_keep.jsonl - config_name: otd_Latn data_files: - split: train path: otd_Latn/*_keep.jsonl - config_name: oym_Latn data_files: - split: train path: oym_Latn/*_keep.jsonl - config_name: phm_Latn data_files: - split: train path: phm_Latn/*_keep.jsonl - config_name: prq_Latn data_files: - split: train path: prq_Latn/*_keep.jsonl - config_name: saj_Latn data_files: - split: train path: saj_Latn/*_keep.jsonl - config_name: szb_Latn data_files: - split: train path: szb_Latn/*_keep.jsonl - config_name: tap_Latn data_files: - split: train path: tap_Latn/*_keep.jsonl - config_name: tnr_Latn data_files: - split: train path: tnr_Latn/*_keep.jsonl - config_name: tzl_Latn data_files: - split: train path: tzl_Latn/*_keep.jsonl - config_name: wew_Latn data_files: - split: train path: wew_Latn/*_keep.jsonl - config_name: yas_Latn data_files: - split: train path: yas_Latn/*_keep.jsonl - config_name: yuz_Latn data_files: - split: train path: yuz_Latn/*_keep.jsonl - config_name: avk_Cyrl data_files: - split: train path: avk_Cyrl/*_keep.jsonl - config_name: bat_Cyrl data_files: - split: train path: bat_Cyrl/*_keep.jsonl - config_name: baw_Latn data_files: - split: train path: baw_Latn/*_keep.jsonl - config_name: bwt_Latn data_files: - split: train path: bwt_Latn/*_keep.jsonl - config_name: bxa_Latn data_files: - split: train path: bxa_Latn/*_keep.jsonl - config_name: cjs_Latn data_files: - split: train path: cjs_Latn/*_keep.jsonl - config_name: csw_Cans data_files: - split: train path: csw_Cans/*_keep.jsonl - config_name: fli_Latn data_files: - split: train path: fli_Latn/*_keep.jsonl - config_name: kqr_Latn data_files: - split: train path: kqr_Latn/*_keep.jsonl - config_name: lan_Latn data_files: - split: train path: lan_Latn/*_keep.jsonl - config_name: lgr_Latn data_files: - split: train path: lgr_Latn/*_keep.jsonl - config_name: lhm_Deva data_files: - split: train path: lhm_Deva/*_keep.jsonl - config_name: mlk_Latn data_files: - split: train path: mlk_Latn/*_keep.jsonl - config_name: mve_Arab data_files: - split: train path: mve_Arab/*_keep.jsonl - config_name: nqo_Latn data_files: - split: train path: nqo_Latn/*_keep.jsonl - config_name: odk_Arab data_files: - split: train path: odk_Arab/*_keep.jsonl - config_name: olo_Cyrl data_files: - split: train path: olo_Cyrl/*_keep.jsonl - config_name: otq_Arab data_files: - split: train path: otq_Arab/*_keep.jsonl - config_name: pea_Latn data_files: - split: train path: pea_Latn/*_keep.jsonl - config_name: saq_Latn data_files: - split: train path: saq_Latn/*_keep.jsonl - config_name: sea_Latn data_files: - split: train path: sea_Latn/*_keep.jsonl - config_name: sps_Latn data_files: - split: train path: sps_Latn/*_keep.jsonl - config_name: tio_Latn data_files: - split: train path: tio_Latn/*_keep.jsonl - config_name: yin_Latn data_files: - split: train path: yin_Latn/*_keep.jsonl - config_name: adl_Latn data_files: - split: train path: adl_Latn/*_keep.jsonl - config_name: agw_Latn data_files: - split: train path: agw_Latn/*_keep.jsonl - config_name: ald_Latn data_files: - split: train path: ald_Latn/*_keep.jsonl - config_name: asg_Latn data_files: - split: train path: asg_Latn/*_keep.jsonl - config_name: bnj_Latn data_files: - split: train path: bnj_Latn/*_keep.jsonl - config_name: brx_Latn data_files: - split: train path: brx_Latn/*_keep.jsonl - config_name: bwi_Latn data_files: - split: train path: bwi_Latn/*_keep.jsonl - config_name: bwq_Latn data_files: - split: train path: bwq_Latn/*_keep.jsonl - config_name: dbq_Latn data_files: - split: train path: dbq_Latn/*_keep.jsonl - config_name: dow_Latn data_files: - split: train path: dow_Latn/*_keep.jsonl - config_name: fad_Latn data_files: - split: train path: fad_Latn/*_keep.jsonl - config_name: hoc_Latn data_files: - split: train path: hoc_Latn/*_keep.jsonl - config_name: kql_Latn data_files: - split: train path: kql_Latn/*_keep.jsonl - config_name: ksf_Latn data_files: - split: train path: ksf_Latn/*_keep.jsonl - config_name: kyu_Mymr data_files: - split: train path: kyu_Mymr/*_keep.jsonl - config_name: lea_Latn data_files: - split: train path: lea_Latn/*_keep.jsonl - config_name: mse_Latn data_files: - split: train path: mse_Latn/*_keep.jsonl - config_name: mzl_Latn data_files: - split: train path: mzl_Latn/*_keep.jsonl - config_name: nhd_Latn data_files: - split: train path: nhd_Latn/*_keep.jsonl - config_name: nnl_Latn data_files: - split: train path: nnl_Latn/*_keep.jsonl - config_name: nwx_Deva data_files: - split: train path: nwx_Deva/*_keep.jsonl - config_name: pbc_Latn data_files: - split: train path: pbc_Latn/*_keep.jsonl - config_name: pny_Latn data_files: - split: train path: pny_Latn/*_keep.jsonl - config_name: tul_Latn data_files: - split: train path: tul_Latn/*_keep.jsonl - config_name: aaa_Latn data_files: - split: train path: aaa_Latn/*_keep.jsonl - config_name: abc_Latn data_files: - split: train path: abc_Latn/*_keep.jsonl - config_name: agq_Latn data_files: - split: train path: agq_Latn/*_keep.jsonl - config_name: ags_Latn data_files: - split: train path: ags_Latn/*_keep.jsonl - config_name: azo_Latn data_files: - split: train path: azo_Latn/*_keep.jsonl - config_name: bag_Latn data_files: - split: train path: bag_Latn/*_keep.jsonl - config_name: bax_Latn data_files: - split: train path: bax_Latn/*_keep.jsonl - config_name: bce_Latn data_files: - split: train path: bce_Latn/*_keep.jsonl - config_name: bfm_Latn data_files: - split: train path: bfm_Latn/*_keep.jsonl - config_name: bgf_Latn data_files: - split: train path: bgf_Latn/*_keep.jsonl - config_name: bhs_Latn data_files: - split: train path: bhs_Latn/*_keep.jsonl - config_name: bkc_Latn data_files: - split: train path: bkc_Latn/*_keep.jsonl - config_name: bkh_Latn data_files: - split: train path: bkh_Latn/*_keep.jsonl - config_name: blk_Latn data_files: - split: train path: blk_Latn/*_keep.jsonl - config_name: bob_Latn data_files: - split: train path: bob_Latn/*_keep.jsonl - config_name: bqm_Latn data_files: - split: train path: bqm_Latn/*_keep.jsonl - config_name: bri_Latn data_files: - split: train path: bri_Latn/*_keep.jsonl - config_name: brv_Laoo data_files: - split: train path: brv_Laoo/*_keep.jsonl - config_name: buo_Latn data_files: - split: train path: buo_Latn/*_keep.jsonl - config_name: bya_Latn data_files: - split: train path: bya_Latn/*_keep.jsonl - config_name: chp_Cans data_files: - split: train path: chp_Cans/*_keep.jsonl - config_name: cim_Latn data_files: - split: train path: cim_Latn/*_keep.jsonl - config_name: clo_Latn data_files: - split: train path: clo_Latn/*_keep.jsonl - config_name: cuv_Latn data_files: - split: train path: cuv_Latn/*_keep.jsonl - config_name: dag_Arab data_files: - split: train path: dag_Arab/*_keep.jsonl - config_name: dmg_Latn data_files: - split: train path: dmg_Latn/*_keep.jsonl - config_name: dtr_Latn data_files: - split: train path: dtr_Latn/*_keep.jsonl - config_name: eee_Thai data_files: - split: train path: eee_Thai/*_keep.jsonl - config_name: ekm_Latn data_files: - split: train path: ekm_Latn/*_keep.jsonl - config_name: enc_Latn data_files: - split: train path: enc_Latn/*_keep.jsonl - config_name: fiu_Cyrl data_files: - split: train path: fiu_Cyrl/*_keep.jsonl - config_name: gbj_Orya data_files: - split: train path: gbj_Orya/*_keep.jsonl - config_name: gou_Latn data_files: - split: train path: gou_Latn/*_keep.jsonl - config_name: hao_Latn data_files: - split: train path: hao_Latn/*_keep.jsonl - config_name: hna_Latn data_files: - split: train path: hna_Latn/*_keep.jsonl - config_name: hre_Latn data_files: - split: train path: hre_Latn/*_keep.jsonl - config_name: isu_Latn data_files: - split: train path: isu_Latn/*_keep.jsonl - config_name: jgo_Latn data_files: - split: train path: jgo_Latn/*_keep.jsonl - config_name: kbx_Latn data_files: - split: train path: kbx_Latn/*_keep.jsonl - config_name: kvt_Latn data_files: - split: train path: kvt_Latn/*_keep.jsonl - config_name: kxp_Arab data_files: - split: train path: kxp_Arab/*_keep.jsonl - config_name: lfa_Latn data_files: - split: train path: lfa_Latn/*_keep.jsonl - config_name: lkb_Latn data_files: - split: train path: lkb_Latn/*_keep.jsonl - config_name: lns_Latn data_files: - split: train path: lns_Latn/*_keep.jsonl - config_name: loh_Latn data_files: - split: train path: loh_Latn/*_keep.jsonl - config_name: lrc_Latn data_files: - split: train path: lrc_Latn/*_keep.jsonl - config_name: lts_Latn data_files: - split: train path: lts_Latn/*_keep.jsonl - config_name: luy_Latn data_files: - split: train path: luy_Latn/*_keep.jsonl - config_name: mdr_Latn data_files: - split: train path: mdr_Latn/*_keep.jsonl - config_name: mfj_Latn data_files: - split: train path: mfj_Latn/*_keep.jsonl - config_name: mgg_Latn data_files: - split: train path: mgg_Latn/*_keep.jsonl - config_name: mgq_Latn data_files: - split: train path: mgq_Latn/*_keep.jsonl - config_name: mle_Latn data_files: - split: train path: mle_Latn/*_keep.jsonl - config_name: mlw_Latn data_files: - split: train path: mlw_Latn/*_keep.jsonl - config_name: mmu_Latn data_files: - split: train path: mmu_Latn/*_keep.jsonl - config_name: mne_Latn data_files: - split: train path: mne_Latn/*_keep.jsonl - config_name: muv_Mlym data_files: - split: train path: muv_Mlym/*_keep.jsonl - config_name: mxu_Latn data_files: - split: train path: mxu_Latn/*_keep.jsonl - config_name: nge_Latn data_files: - split: train path: nge_Latn/*_keep.jsonl - config_name: ngn_Latn data_files: - split: train path: ngn_Latn/*_keep.jsonl - config_name: njy_Latn data_files: - split: train path: njy_Latn/*_keep.jsonl - config_name: nsk_Cans data_files: - split: train path: nsk_Cans/*_keep.jsonl - config_name: nsk_Latn data_files: - split: train path: nsk_Latn/*_keep.jsonl - config_name: nwe_Latn data_files: - split: train path: nwe_Latn/*_keep.jsonl - config_name: nza_Latn data_files: - split: train path: nza_Latn/*_keep.jsonl - config_name: pcg_Mlym data_files: - split: train path: pcg_Mlym/*_keep.jsonl - config_name: pdu_Latn data_files: - split: train path: pdu_Latn/*_keep.jsonl - config_name: pnz_Latn data_files: - split: train path: pnz_Latn/*_keep.jsonl - config_name: pwg_Latn data_files: - split: train path: pwg_Latn/*_keep.jsonl - config_name: qaa_Latn data_files: - split: train path: qaa_Latn/*_keep.jsonl - config_name: shi_Arab data_files: - split: train path: shi_Arab/*_keep.jsonl - config_name: smn_Cyrl data_files: - split: train path: smn_Cyrl/*_keep.jsonl - config_name: snk_Arab data_files: - split: train path: snk_Arab/*_keep.jsonl - config_name: snl_Latn data_files: - split: train path: snl_Latn/*_keep.jsonl - config_name: sox_Latn data_files: - split: train path: sox_Latn/*_keep.jsonl - config_name: ssn_Latn data_files: - split: train path: ssn_Latn/*_keep.jsonl - config_name: syw_Deva data_files: - split: train path: syw_Deva/*_keep.jsonl - config_name: tay_Hani data_files: - split: train path: tay_Hani/*_keep.jsonl - config_name: tbj_Latn data_files: - split: train path: tbj_Latn/*_keep.jsonl - config_name: tdb_Deva data_files: - split: train path: tdb_Deva/*_keep.jsonl - config_name: thy_Thai data_files: - split: train path: thy_Thai/*_keep.jsonl - config_name: tnt_Latn data_files: - split: train path: tnt_Latn/*_keep.jsonl - config_name: tom_Latn data_files: - split: train path: tom_Latn/*_keep.jsonl - config_name: tpl_Latn data_files: - split: train path: tpl_Latn/*_keep.jsonl - config_name: tsb_Latn data_files: - split: train path: tsb_Latn/*_keep.jsonl - config_name: tvs_Latn data_files: - split: train path: tvs_Latn/*_keep.jsonl - config_name: udg_Mlym data_files: - split: train path: udg_Mlym/*_keep.jsonl - config_name: unr_Orya data_files: - split: train path: unr_Orya/*_keep.jsonl - config_name: wbr_Deva data_files: - split: train path: wbr_Deva/*_keep.jsonl - config_name: wms_Latn data_files: - split: train path: wms_Latn/*_keep.jsonl - config_name: wnk_Latn data_files: - split: train path: wnk_Latn/*_keep.jsonl - config_name: wtk_Latn data_files: - split: train path: wtk_Latn/*_keep.jsonl - config_name: xmd_Latn data_files: - split: train path: xmd_Latn/*_keep.jsonl - config_name: xmg_Latn data_files: - split: train path: xmg_Latn/*_keep.jsonl - config_name: xty_Latn data_files: - split: train path: xty_Latn/*_keep.jsonl - config_name: yav_Latn data_files: - split: train path: yav_Latn/*_keep.jsonl - config_name: yea_Mlym data_files: - split: train path: yea_Mlym/*_keep.jsonl - config_name: zuh_Latn data_files: - split: train path: zuh_Latn/*_keep.jsonl language: - eng - rus - cmn - deu - spa - fra - jpn - ita - por - pol - nld - ind - tur - vie - fas - kor - swe - hun - ell - ukr - tha - aze - arb - slv - cat - fin - hbs - ces - fil - guj - nob - mal - bul - kan - hin - tam - ara - kaz - sqi - pan - est - srp - heb - isl - mlt - mkd - bos - lit - kat - hrv - ben - glg - ceb - ron - msa - hye - tgk - mar - bel - nep - urd - slk - mon - swa - dan - eus - azj - sin - lat - als - tel - afr - ekk - ltz - zsm - som - cym - und - kir - nor - uzb - mya - epo - hau - ary - gle - lvs - nno - und - ory - amh - tat - khm - und - und - und - arz - pus - lav - hbs - und - war - und - mlg - uzn - hat - zul - kur - tgl - uzb - div - und - fry - sna - und - fao - sun - und - und - snd - cos - bak - ckb - asm - und - jpn - ast - ibo - mri - und - ars - und - anp - khk - und - lao - ori - und - yid - hmn - jav - nya - und - und - und - tir - uig - wln - und - yor - swh - gla - xho - uzn - bre - sot - che - nan - tel - bew - glk - smo - orm - zho - haw - pnb - und - oci - chv - kin - und - srp - und - und - pcm - kaa - lug - pbt - aze - gsw - min - tuk - lim - kmr - und - roh - und - und - vec - san - und - gmh - nds - sco - und - und - azb - tsn - rus - und - mon - und - tgk - sah - pri - pap - plt - lmo - bod - und - yue - und - und - und - bar - und - hif - und - arg - pms - kat - nrm - vol - aeb - und - und - ido - pam - kal - und - und - und - lus - und - und - und - new - sme - und - und - nso - lld - ina - scn - und - und - und - hyw - abk - bew - und - und - bpy - tgk - lin - oss - que - szl - sdh - mww - mhr - und - und - und - rmy - diq - srd - und - und - ydd - und - run - und - hsb - und - wol - und - urd - und - kiu - ilo - und - cak - und - acm - und - und - grc - xmf - vls - und - und - tso - crh - nav - mwl - und - tat - grn - mui - hin - mvf - udm - mzn - und - und - und - bcl - und - und - ban - und - afb - und - cnh - und - cbk - kaa - tyv - kur - ful - und - zea - frp - frr - pfl - lij - apc - mai - und - und - pon - bak - eml - uzs - nde - hil - mam - gom - dag - nap - bjn - und - hbo - tet - inh - ven - gaz - tpi - und - ajp - sat - wuu - bam - vep - glv - tzo - bik - und - acr - twi - myv - ewe - poh - und - ile - rue - und - und - ace - kha - und - und - und - und - ksh - hui - gor - krc - lfn - tls - fur - und - gag - chk - hmo - kek - fon - ssw - quh - meu - csb - ksd - ext - rop - und - aln - kab - shn - tbz - knv - bqc - und - und - npi - rug - und - kom - kpg - kbd - dzo - wal - zlm - und - mzh - pan - hac - und - tum - sgs - fij - tuc - und - und - jbo - iba - pcd - kjh - ixl - und - und - und - ndo - suz - und - und - mfe - bxr - ava - und - bho - brh - und - ctd - aym - ady - nbl - gom - hus - gug - und - und - bat - guj - hne - srn - ctu - san - ton - bug - aoj - jam - und - lez - xav - luo - ltg - bih - uig - mrj - avk - kos - kbp - alt - cfm - goh - lad - und - cor - quc - und - kpv - und - aka - und - hak - rmn - pls - sag - min - und - rcf - som - gym - und - kik - pag - arn - und - ngu - dsb - tca - mni - naq - pdc - mps - und - olo - fro - fit - crh - cdo - kac - mdf - mad - cab - srm - toj - zai - guc - smn - ote - nch - und - prs - tuk - bis - cuk - bzj - map - djk - ncj - und - mco - shp - und - ang - seh - ikk - qvi - yom - top - awa - ike - mau - kum - mos - tly - und - ayr - tdt - yap - evn - tah - xal - szy - quw - stq - tlh - otq - und - nov - skr - yua - raw - und - fiu - enm - bbc - und - non - und - ber - kea - uig - bua - kua - zza - csy - mnw - dtp - nah - yao - azj - hau - nog - abt - meo - ame - mbf - chm - arb - kas - tam - crs - tcy - lbe - cni - ben - rom - zom - blk - efi - ada - und - koi - und - bbj - trv - ach - mgh - kas - gcr - krl - iso - lki - atj - cmo - chu - gur - mni - iku - sma - lrc - gos - dty - nzi - btx - brx - bts - nyu - ckt - guw - pck - quy - gcf - ksw - nia - bal - nhe - hwc - mup - dyu - ami - tay - gaa - loz - abq - pnt - snd - ium - abs - cmr - shi - tzm - gil - ewo - kon - sms - ape - tzh - bci - acd - tab - fuv - swc - tcz - und - sgc - aaz - tly - tvl - zha - pib - pli - bru - quz - cha - aeu - bjn - nqo - mer - acf - rmc - msi - smj - kng - dhv - doi - zap - hla - cac - pdt - mbt - taq - bgp - tyz - aau - mah - nak - kmb - mjw - fuf - bba - ron - amu - alz - cop - rar - emp - arc - nyn - rut - lub - tzj - fat - lzh - aak - nnb - lhu - bjv - bum - maq - roa - bvr - kcg - tok - yrk - khs - rup - tuk - qub - jac - hmr - sid - chr - amp - qug - mas - fkv - mal - bem - cav - her - kwn - ify - asm - gpe - zpa - agu - ppk - tiv - npi - ahk - pis - hns - sus - hak - bon - sja - kas - mar - kri - dik - wrk - got - dar - gui - mak - jiv - kjb - maz - bsn - dov - cok - rwo - mag - hnj - krj - teo - enq - aom - ffm - din - ubu - pwn - gum - sny - twu - med - acn - rme - cbs - abx - ndc - ibb - pih - zty - rad - aby - zne - cui - lua - yby - bno - niu - agd - nij - agg - yre - fip - qve - tsg - skg - adj - mfq - agx - kmg - umb - cnk - nhw - maa - kwy - jra - syr - inb - pau - xsm - vap - alp - des - syl - kmr - mkn - gan - qwh - jvn - bib - ckt - mpx - bin - klv - xon - jbu - bdh - knj - ptu - mmn - mwq - sop - cgc - rmy - dop - mgr - rmo - tbc - kyq - zpu - kkc - acu - ata - gag - kan - mif - sus - tsz - mbi - imo - fuh - zyp - apr - att - bus - kqp - koo - bas - urh - bbr - msy - mdy - nas - lee - mcu - mrj - dig - izr - nfr - hto - mzw - qxh - chz - guh - ded - bvz - kkj - gux - ikt - bnp - bgt - quf - dwr - nod - yal - bmr - ljp - xla - zyb - gof - niv - nrf - npy - ura - dob - gfk - gdr - sdc - pjt - spp - irk - cpa - knc - gvl - agr - njo - xrb - kao - zpz - bgr - rnd - ntu - aai - gai - dgi - kez - dad - kmh - aii - ifk - aji - noa - bhl - ztq - rmn - gde - dnj - men - miq - mdf - isd - lgg - ncx - gub - itv - tac - cce - kwi - nhu - snd - sml - pah - sas - cwt - spy - enb - fai - cas - sue - yss - ozm - bku - biv - akp - dts - kdr - fal - mmo - byr - cbv - cbu - eza - kgp - sda - gbo - mfi - bdd - boj - blh - ibg - agn - vmy - sua - gul - rap - bmh - sxn - dyi - tdx - car - heh - dgc - sgb - bpr - gbi - avu - udu - yli - cjs - gnn - nhi - urk - kpy - qup - qvh - pir - tsc - bxr - thk - grt - kqn - hay - mqb - tbg - bss - trn - jae - myy - ipk - bao - qvz - dua - mwv - nct - kyc - tuo - tee - mop - mxt - qvm - gkn - lam - ntr - sbe - dyo - lex - smk - coe - kpe - mni - xbi - atb - tcf - bfo - cbc - swg - niv - cnt - izz - knf - mpp - kki - nho - sat - kbr - bmu - hig - qxr - orv - pma - zpl - kpr - sig - ory - mxp - lef - mlp - soq - cre - aey - qvs - sur - knc - suk - cax - alq - chw - dww - gog - viv - qvw - ted - yuj - ziw - kto - mcq - sim - koi - lue - cya - knk - tpt - taj - blz - mil - kde - kpz - hag - vun - kus - lid - tos - bfd - chd - cle - yon - bgs - lsm - msb - ota - guj - mxq - lfn - myw - aso - esu - kdi - bhp - mfz - sgw - xsi - gun - kxc - mux - otw - cjp - nyo - zia - cco - ojb - ktu - cpy - txu - bjr - bud - ken - bzh - ipi - crx - cko - gnd - kix - mmx - esk - kud - toh - byx - mtp - kpv - kyz - lmp - tiy - ccp - sbl - tcs - usp - buk - hvn - amm - kzj - gng - ter - kij - ngl - pab - pad - kca - meq - kas - niq - dah - lia - kss - bch - khz - nop - yle - ain - pem - yml - taq - gaw - kze - tby - cso - ifb - rki - aly - kmu - mhl - kmo - mva - opm - rtm - xtn - dgr - ksr - snp - tvk - zpv - hrx - kwj - muh - kak - kpw - akb - ybb - kjs - wuv - laj - ogo - nim - czt - aoz - rro - yuw - heg - mrw - zac - kpf - leu - nwi - awx - gso - keo - tte - ceg - nhy - bhw - gnw - nin - xmv - crm - mxv - ubr - gld - bzi - ann - lac - mej - zpc - dje - caq - guk - wos - msm - zaw - cap - mox - zab - mca - wrs - hae - nss - rav - uvh - dga - ppo - nog - arq - bim - lwg - kms - kne - tkl - ady - caf - zat - aba - chf - lew - npl - uvl - cdo - rmq - mek - snc - nsn - amn - abz - cek - ong - txq - bjp - gvf - crk - snf - nhg - kqw - mic - mie - nus - plu - idu - sll - thl - bef - kwd - mqy - caa - aia - wer - agm - mbl - mbs - adh - hub - mav - nab - bqp - guo - auy - big - nii - row - kim - mti - otm - prg - icr - mcp - tbo - chy - oji - kpx - lbb - pao - xuo - zgh - wls - aca - apy - wnc - ssg - eve - mee - yut - chr - kxm - mur - lad - mcd - cto - mqj - usa - emi - liv - guz - tgp - ncl - azg - kck - apb - kbm - sgz - wsk - gbm - csw - ctp - eri - vid - bsq - dak - tif - xsr - mwp - roo - wbp - gdn - tgo - zpm - mih - qvc - tod - abn - cao - kbc - kog - moh - leh - nsu - okv - tih - zos - llg - gmv - kyf - mhx - mvp - naf - ino - dng - mnk - oke - omw - tnk - xtd - agt - cbr - eko - nhk - hot - iou - mpm - myx - ndh - pbb - rng - cri - bvd - kmz - cta - blw - clu - cof - kje - nmf - kbh - qxn - ria - wed - zar - huv - lsi - msk - nbq - ati - lww - yva - amr - lmk - tim - bbb - bzd - djr - kwf - nuy - poi - ptp - atd - bps - lcm - mbh - nuj - ayp - cwe - geb - aoi - mto - cbi - gvn - kqf - rkb - xed - zas - apz - cpb - ese - gdg - iws - apu - cag - kdc - nou - too - xmm - beq - hnn - myk - sby - arl - ncu - rml - gam - kvn - mbc - mfy - urt - luc - mio - snn - tar - tku - upv - kjg - btd - cut - mwn - tue - adz - kyg - rel - tew - ttc - nkf - yrb - fub - nsm - nyf - ava - bkd - cpc - lif - mwc - gan - apw - azz - zpo - ace - faa - ood - toc - wmt - ajg - nko - ssd - sxb - zxx - not - amk - hch - kqc - aui - llb - avt - kaq - tna - zpt - mnw - bwd - lif - stn - crk - kgk - mck - bhg - ifu - kkl - zao - huu - sil - trq - tuf - wnu - amf - fan - zdj - bco - kdl - lln - mit - yaq - ake - ige - mna - nhx - njn - wba - zaa - lez - syb - qxo - rgu - wiu - bla - etr - miy - mjc - nif - pov - qxl - sey - bxh - ddg - mks - nki - pot - prf - hra - law - plw - zpi - atg - daf - drg - dru - ngp - boa - cbt - dhm - ikw - kqe - lbj - loq - xsb - yad - kyu - mcb - tks - cnl - far - miz - maj - mgm - mib - mza - nhr - smt - ish - mlu - yka - anv - ign - mir - tav - gyr - klt - apn - wbm - cjk - dln - mcf - twx - ldi - poy - yaa - zae - bdq - con - dnw - gah - lcp - mbj - xog - yan - sdq - sgh - gwi - lbk - ses - ycn - kau - hix - mig - mlh - aer - amx - auc - cly - dsh - gnb - neb - ttt - jic - xtm - tll - apt - kgr - pio - pmf - yrk - akh - box - cub - cux - mrq - inh - bsp - for - kny - uri - zsr - pce - cme - cot - kxw - omb - srq - vag - cpu - kmy - ksc - lai - nnp - ruf - spm - tro - ttj - waj - raj - ian - ivb - kmm - kzf - maw - tuv - whk - zsm - aph - anm - mny - bug - trp - are - esi - mhi - obo - bwu - lwo - mrg - old - zav - snk - daa - fuq - lud - nlg - sck - tbl - khb - tpu - fue - tmd - whg - blt - gqr - kub - ots - tpp - var - hbb - krr - zxx - alj - ebk - goa - hav - kmk - kqo - muy - njb - snw - wib - shn - tkr - ksp - lip - mog - nla - pss - zad - awi - frd - kei - kmd - mim - got - lbe - adi - any - arp - biu - bvc - ghs - ttq - vmk - zpj - crl - dtb - dug - kam - nmo - qva - rhg - taw - tui - uth - wap - zpg - brb - dty - syr - bih - bqj - cjv - cnw - kgf - mfh - mns - nnw - ntp - oto - dks - mpt - nmw - sba - sfw - shu - ury - yrl - arc - cmo - xkg - iqw - kpj - nfa - nph - nre - wsg - xsu - nut - bmk - cdf - enl - fuv - hop - ife - lnd - mrv - nzm - tem - dwr - gwc - udi - zha - ajz - kru - qvo - sld - yup - anp - kwu - szy - tdg - ade - bcw - bgz - cul - fmu - gvc - ktj - lis - mev - msc - mta - nbc - ncq - way - wlv - wlx - jmx - pli - tkr - wni - aim - byv - cgg - fud - jmc - ker - kia - lom - ojb - tnc - bwx - cre - skr - xal - gjn - guq - lap - mip - mkl - mtg - mzk - njm - nse - pne - pww - zam - zca - the - dis - lgl - mbd - mda - mhy - nst - pkb - pmq - poe - swk - trs - vot - yam - zpq - atq - bav - cho - chq - cjo - due - duo - etu - ifa - kby - khq - kno - lem - mcn - mkz - mnb - myb - niy - pxm - rub - sju - tmc - tpm - wob - nxa - pnt - sdk - tcy - bhz - bth - crj - eka - khy - led - met - mgo - mus - mzm - naw - sri - tbk - xbr - awa - tnl - tnn - awb - bsc - iri - kpq - ktm - loe - lun - mfg - moa - ndj - otn - sjo - wat - bkm - tuz - ybi - gbr - gej - giz - gna - gwr - kex - kle - knx - ktz - kvj - lob - mhw - mph - pmx - qus - tcc - ang - azn - bra - gal - jra - nlv - rki - stk - yux - dip - ivv - kdj - kff - kyu - mnf - moc - mpg - mua - nma - rim - rjs - rnl - ssx - tig - urw - idt - mrn - oki - bbk - bea - bkq - btt - cou - ddn - did - diu - ilb - ksj - lhi - ndi - ngb - njz - nmz - npo - nwb - pbi - sbd - soe - tpw - twb - bfn - boz - lwl - psp - sgd - ymp - bkl - bkv - csk - enx - ess - gof - gud - guu - kdh - krx - kzn - maf - max - mgc - mvn - mwm - nbe - nlc - nxd - pse - sbs - tlb - wwa - yim - bkx - bze - chu - kbq - kpy - mry - tkd - ybh - abi - ayo - bex - bom - bov - dhg - jaa - kqs - kqy - ksb - ldn - log - lol - mfk - mtj - ndz - ngc - nio - nri - nuz - pps - shk - tlj - vut - xnn - bcc - cuh - emp - hro - nco - nxl - pex - tnp - trv - vif - aha - avn - bmv - chj - crt - dos - eto - gya - hlt - jun - ktb - lgm - mnx - mor - mug - nng - nnh - nsa - nyk - otd - oym - phm - prq - saj - szb - tap - tnr - tzl - wew - yas - yuz - avk - bat - baw - bwt - bxa - cjs - csw - fli - kqr - lan - lgr - lhm - mlk - mve - nqo - odk - olo - otq - pea - saq - sea - sps - tio - yin - adl - agw - ald - asg - bnj - brx - bwi - bwq - dbq - dow - fad - hoc - kql - ksf - kyu - lea - mse - mzl - nhd - nnl - nwx - pbc - pny - tul - aaa - abc - agq - ags - azo - bag - bax - bce - bfm - bgf - bhs - bkc - bkh - blk - bob - bqm - bri - brv - buo - bya - chp - cim - clo - cuv - dag - dmg - dtr - eee - ekm - enc - fiu - gbj - gou - hao - hna - hre - isu - jgo - kbx - kvt - kxp - lfa - lkb - lns - loh - lrc - lts - luy - mdr - mfj - mgg - mgq - mle - mlw - mmu - mne - muv - mxu - nge - ngn - njy - nsk - nsk - nwe - nza - pcg - pdu - pnz - pwg - qaa - shi - smn - snk - snl - sox - ssn - syw - tay - tbj - tdb - thy - tnt - tom - tpl - tsb - tvs - udg - unr - wbr - wms - wnk - wtk - xmd - xmg - xty - yav - yea - zuh multilinguality: - multilingual pinned: true tags: - multilingual --- ## Dataset Summary DCAD-2000 is a large-scale multilingual corpus built using newly extracted Common Crawl data (CC-MAIN-2024-46) and existing multilingual datasets. It includes over 2,282 languages, 46.72TB of data, and 8.63 billion documents, spanning 155 highand medium-resource languages and 159 writing scripts. We propose reframing data cleaning as an anomaly detection task. This dynamic filtering approach significantly enhances data quality by identifying and removing noisy or anomalous content. + Paper: [A Multilingual Dataset across 2000+ Languages with Data Cleaning as Anomaly Detection](https://www.arxiv.org/abs/2502.11546) + Github: [https://github.com/yl-shen/DCAD-2000](https://github.com/yl-shen/DCAD-2000) + Dataset (HuggingFace): [openbmb/DCAD-2000](https://huggingface.co/datasets/openbmb/DCAD-2000) ## Dataset Overview Comparison of multilingual datasets constructed from Common Crawl (CC) and our constructed DCAD-2000, focusing on the latest CC version used, the total number of languages supported, distribution across resource categories (high, medium, low, very low), and training readiness. The CC version marked with **bold** indicates an inferred version due to the lack of explicit specification in the original paper. The ``Training-Ready'' column indicates whether the dataset is ready for training LLMs without requiring further data cleaning. | **Dataset** | **CC Version** | **#Langs (total)** | **#Langs (high)** | **#Langs (medium)** | **#Langs (low)** | **#Langs (very low)** | **Training-Ready** | |---------------------------|--------------------|--------------------|-------------------|---------------------|------------------|-----------------------|--------------------| | mC4 (Raffel et al., 2020) | CC-MAIN-2020-34 | 101 | 0 | 43 | 52 | 6 | ✘ | | OSCAR 23.01 (Abadji et al., 2022) | CC-MAIN-2022-49 | 153 | 6 | 42 | 25 | 80 | ✘ | | Glot500 (Imani et al., 2023) | **CC-MAIN-2020-34** | 511 | 0 | 108 | 79 | 324 | ✘ | | CulturaX (Nguyen et al., 2024) | **CC-MAIN-2022-49** | 167 | 11 | 47 | 27 | 82 | ✘ | | Madlad-400 (Kudugunta et al., 2024) | CC-MAIN-2022-33 | 419 | 7 | 46 | 39 | 327 | ✘ | | MaLA (Ji et al., 2024) | **CC-MAIN-2022-49** | 939 | 1 | 125 | 78 | 735 | ✘ | | Glotcc (Kargaran et al., 2024) | CC-MAIN-2023-50 | 1331 | 0 | 10 | 52 | 1269 | ✘ | | HPLT-v1.2 (de Gilbert et al., 2024) | **CC-MAIN-2022-40** | 191 | 12 | 53 | 38 | 88 | ✘ | | Fineweb-2 (Penedo et al., 2024) | CC-MAIN-2024-18 | 1915 | 10 | 62 | 49 | 1794 | ✘ | | **DCAD-2000** | CC-MAIN-2024-46 | 2282 | 13 | 142 | 124 | 2003 | ✓ | ## Dataset Creation + **Data Collection:** DCAD-2000 integrates data from four main sources: MaLA, Fineweb, Fineweb-2, and newly extracted Common Crawl data. + **Data Cleaning as Anomaly Detection:** Traditional data cleaning methods rely on fixed thresholds for document-level features, making them less adaptable to the diversity of multilingual data. To address this, we propose a novel framework that formulates data cleaning as an anomaly detection task, which involves the feature extraction and anomaly detection. - **Feature Extraction:** For each document, we consider the following eight features: (1) Number of Words; (2) Character Repetition Ratio; (3) Word Repetition Ratio; (4) Special Characters Ratio; (5) Stop- words Ratio; (6) Flagged Words Ratio; (7) Language Identification (LID) Score; (8) Perplexity Score. - **Anomaly Detection:** We evaluate several classical anomaly detection algorithms including (1) Isolation Forest; (2) One Class SVM; (3) Local Outlier Factor and (4) K-Means. - Visualization<br> ![ad_overview](https://github.com/yl-shen/DCAD-2000/raw/master/images/ad_visual.png) ## Data Statistics + [Geographical Distribution](https://github.com/yl-shen/DCAD-2000/blob/master/statistics/geo_group.tsv) + [Script Distribution](https://github.com/yl-shen/DCAD-2000/blob/master/statistics/script_group_detail.tsv) + [Statistical Details](https://github.com/yl-shen/DCAD-2000/blob/master/statistics/statistic_detail.tsv) + [language list](https://github.com/yl-shen/DCAD-2000/blob/master/statistics/statistic_lang_num.tsv) + [language mapping](https://github.com/yl-shen/DCAD-2000/blob/master/lang_mapping/all_mapping.csv) ## Usage (Dataset) ``` from datasets import load_dataset data = load_dataset("openbmb/DCAD-2000") ``` You can also specifiy the language you wanted ``` from datasets import load_dataset data = load_dataset("openbmb/DCAD-2000", name="eng_Latn", split="train") ``` ## Citation Information ``` @article{shen2025dcad, title={DCAD-2000: A Multilingual Dataset across 2000+ Languages with Data Cleaning as Anomaly Detection}, author={Shen, Yingli and Lai, Wen and Wang, Shuo and Zhang, Xueren and Luo, Kangyang and Fraser, Alexander and Sun, Maosong}, journal={arXiv preprint arXiv:2502.11546}, year={2025} } ``` ## Acknowledgements We introduce DCAD-2000, a large- scale multilingual dataset designed to address the increasing demand for high-quality and diverse training data for multilingual LLMs. This work is done by researchers at [Tsinghua NLP group](https://nlp.csai.tsinghua.edu.cn) in collaboration with partners from [TUM](https://wenlai-lavine.github.io/) and [Modelbest Inc.](https://huggingface.co/openbmb) ## Contact Information Yingli Shen ([email protected]) Wen Lai ([email protected])

stanfordnlp/sst2

stanfordnlp

"2024-01-04T16:31:07Z"

15,748

114

[ "task_categories:text-classification", "task_ids:sentiment-classification", "annotations_creators:crowdsourced", "language_creators:found", "multilinguality:monolingual", "source_datasets:original", "language:en", "license:unknown", "size_categories:10K<n<100K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]

[ "text-classification" ]

"2022-06-13T14:01:47Z"

--- annotations_creators: - crowdsourced language_creators: - found language: - en license: - unknown multilinguality: - monolingual size_categories: - 10K<n<100K source_datasets: - original task_categories: - text-classification task_ids: - sentiment-classification paperswithcode_id: sst pretty_name: Stanford Sentiment Treebank v2 dataset_info: features: - name: idx dtype: int32 - name: sentence dtype: string - name: label dtype: class_label: names: '0': negative '1': positive splits: - name: train num_bytes: 4681603 num_examples: 67349 - name: validation num_bytes: 106252 num_examples: 872 - name: test num_bytes: 216640 num_examples: 1821 download_size: 3331058 dataset_size: 5004495 configs: - config_name: default data_files: - split: train path: data/train-* - split: validation path: data/validation-* - split: test path: data/test-* --- # Dataset Card for [Dataset Name] ## Table of Contents - [Table of Contents](#table-of-contents) - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Homepage:** https://nlp.stanford.edu/sentiment/ - **Repository:** - **Paper:** [Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank](https://www.aclweb.org/anthology/D13-1170/) - **Leaderboard:** - **Point of Contact:** ### Dataset Summary The Stanford Sentiment Treebank is a corpus with fully labeled parse trees that allows for a complete analysis of the compositional effects of sentiment in language. The corpus is based on the dataset introduced by Pang and Lee (2005) and consists of 11,855 single sentences extracted from movie reviews. It was parsed with the Stanford parser and includes a total of 215,154 unique phrases from those parse trees, each annotated by 3 human judges. Binary classification experiments on full sentences (negative or somewhat negative vs somewhat positive or positive with neutral sentences discarded) refer to the dataset as SST-2 or SST binary. ### Supported Tasks and Leaderboards - `sentiment-classification` ### Languages The text in the dataset is in English (`en`). ## Dataset Structure ### Data Instances ``` {'idx': 0, 'sentence': 'hide new secretions from the parental units ', 'label': 0} ``` ### Data Fields - `idx`: Monotonically increasing index ID. - `sentence`: Complete sentence expressing an opinion about a film. - `label`: Sentiment of the opinion, either "negative" (0) or positive (1). The test set labels are hidden (-1). ### Data Splits | | train | validation | test | |--------------------|---------:|-----------:|-----:| | Number of examples | 67349 | 872 | 1821 | ## Dataset Creation ### Curation Rationale [More Information Needed] ### Source Data #### Initial Data Collection and Normalization [More Information Needed] #### Who are the source language producers? Rotten Tomatoes reviewers. ### Annotations #### Annotation process [More Information Needed] #### Who are the annotators? [More Information Needed] ### Personal and Sensitive Information [More Information Needed] ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed] ### Discussion of Biases [More Information Needed] ### Other Known Limitations [More Information Needed] ## Additional Information ### Dataset Curators [More Information Needed] ### Licensing Information Unknown. ### Citation Information ```bibtex @inproceedings{socher-etal-2013-recursive, title = "Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank", author = "Socher, Richard and Perelygin, Alex and Wu, Jean and Chuang, Jason and Manning, Christopher D. and Ng, Andrew and Potts, Christopher", booktitle = "Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing", month = oct, year = "2013", address = "Seattle, Washington, USA", publisher = "Association for Computational Linguistics", url = "https://www.aclweb.org/anthology/D13-1170", pages = "1631--1642", } ``` ### Contributions Thanks to [@albertvillanova](https://github.com/albertvillanova) for adding this dataset.

bigcode/bigcodebench-hard

bigcode

"2025-02-23T16:42:46Z"

15,726

3

[ "size_categories:n<1K", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]

null

"2024-09-14T14:50:33Z"

--- dataset_info: features: - name: task_id dtype: string - name: complete_prompt dtype: string - name: instruct_prompt dtype: string - name: canonical_solution dtype: string - name: code_prompt dtype: string - name: test dtype: string - name: entry_point dtype: string - name: doc_struct dtype: string - name: libs dtype: string - name: q_idx dtype: int64 - name: question dtype: string - name: score dtype: float64 - name: _id dtype: string splits: - name: v0.1.0_hf num_bytes: 1271624 num_examples: 148 - name: v0.1.1 num_bytes: 1271607 num_examples: 148 - name: v0.1.2 num_bytes: 1271812 num_examples: 148 - name: v0.1.3 num_bytes: 1271812 num_examples: 148 - name: v0.1.4 num_bytes: 1272012 num_examples: 148 download_size: 2758366 dataset_size: 6358867 configs: - config_name: default data_files: - split: v0.1.0_hf path: data/v0.1.0_hf-* - split: v0.1.1 path: data/v0.1.1-* - split: v0.1.2 path: data/v0.1.2-* - split: v0.1.3 path: data/v0.1.3-* - split: v0.1.4 path: data/v0.1.4-* ---

andstor/methods2test

andstor

"2023-12-23T03:01:51Z"

15,658

0

[ "task_categories:text-generation", "language:en", "license:mit", "size_categories:10M<n<100M", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "arxiv:2203.12776", "region:us", "unit test", "java", "code" ]

[ "text-generation" ]

"2023-12-07T13:37:44Z"

--- language: - en license: mit task_categories: - text-generation configs: - config_name: fm data_files: - split: train path: data/fm/train-* - split: test path: data/fm/test-* - split: validation path: data/fm/validation-* - config_name: fm_indented data_files: - split: train path: data/fm_indented/train-* - split: test path: data/fm_indented/test-* - split: validation path: data/fm_indented/validation-* - config_name: fm+t data_files: - split: train path: data/fm+t/train-* - split: test path: data/fm+t/test-* - split: validation path: data/fm+t/validation-* - config_name: fm+fc data_files: - split: train path: data/fm+fc/train-* - split: test path: data/fm+fc/test-* - split: validation path: data/fm+fc/validation-* - config_name: fm+fc+t+tc data_files: - split: train path: data/fm+fc+t+tc/train-* - split: test path: data/fm+fc+t+tc/test-* - split: validation path: data/fm+fc+t+tc/validation-* - config_name: fm+fc+c data_files: - split: train path: data/fm+fc+c/train-* - split: test path: data/fm+fc+c/test-* - split: validation path: data/fm+fc+c/validation-* - config_name: fm+fc+c+t+tc data_files: - split: train path: data/fm+fc+c+t+tc/train-* - split: test path: data/fm+fc+c+t+tc/test-* - split: validation path: data/fm+fc+c+t+tc/validation-* - config_name: fm+fc+c+m data_files: - split: train path: data/fm+fc+c+m/train-* - split: test path: data/fm+fc+c+m/test-* - split: validation path: data/fm+fc+c+m/validation-* - config_name: fm+fc+c+m+t+tc data_files: - split: train path: data/fm+fc+c+m+t+tc/train-* - split: test path: data/fm+fc+c+m+t+tc/test-* - split: validation path: data/fm+fc+c+m+t+tc/validation-* - config_name: fm+fc+c+m+f data_files: - split: train path: data/fm+fc+c+m+f/train-* - split: test path: data/fm+fc+c+m+f/test-* - split: validation path: data/fm+fc+c+m+f/validation-* - config_name: fm+fc+c+m+f+t+tc data_files: - split: train path: data/fm+fc+c+m+f+t+tc/train-* - split: test path: data/fm+fc+c+m+f+t+tc/test-* - split: validation path: data/fm+fc+c+m+f+t+tc/validation-* - config_name: t data_files: - split: train path: data/t/train-* - split: test path: data/t/test-* - split: validation path: data/t/validation-* - config_name: t_indented data_files: - split: train path: data/t_indented/train-* - split: test path: data/t_indented/test-* - split: validation path: data/t_indented/validation-* - config_name: t+tc data_files: - split: train path: data/t+tc/train-* - split: test path: data/t+tc/test-* - split: validation path: data/t+tc/validation-* dataset_info: - config_name: fm features: - name: id dtype: string - name: text dtype: string splits: - name: train num_bytes: 440444124 num_examples: 624022 - name: test num_bytes: 59407291 num_examples: 78388 - name: validation num_bytes: 57170315 num_examples: 78534 download_size: 99172217 dataset_size: 557021730 - config_name: fm+fc features: - name: id dtype: string - name: text dtype: string splits: - name: train num_bytes: 506130678 num_examples: 624022 - name: test num_bytes: 68407490 num_examples: 78388 - name: validation num_bytes: 65318956 num_examples: 78534 download_size: 109141139 dataset_size: 639857124 - config_name: fm+fc+c features: - name: id dtype: string - name: text dtype: string splits: - name: train num_bytes: 569209100 num_examples: 624022 - name: test num_bytes: 75552573 num_examples: 78388 - name: validation num_bytes: 73101169 num_examples: 78534 download_size: 117996353 dataset_size: 717862842 - config_name: fm+fc+c+m features: - name: id dtype: string - name: text dtype: string splits: - name: train num_bytes: 1354004338 num_examples: 624022 - name: test num_bytes: 187724929 num_examples: 78388 - name: validation num_bytes: 184349299 num_examples: 78534 download_size: 222922572 dataset_size: 1726078566 - config_name: fm+fc+c+m+f features: - name: id dtype: string - name: text dtype: string splits: - name: train num_bytes: 1476073209 num_examples: 624022 - name: test num_bytes: 201686811 num_examples: 78388 - name: validation num_bytes: 201259950 num_examples: 78534 download_size: 240405885 dataset_size: 1879019970 - config_name: fm+fc+c+m+f+t+tc features: - name: id dtype: string - name: source dtype: string - name: target dtype: string splits: - name: train num_bytes: 2019918359 num_examples: 624022 - name: test num_bytes: 269021331 num_examples: 78388 - name: validation num_bytes: 272958781 num_examples: 78534 download_size: 371500476 dataset_size: 2561898471 - config_name: fm+fc+c+m+t+tc features: - name: id dtype: string - name: source dtype: string - name: target dtype: string splits: - name: train num_bytes: 1897682665 num_examples: 624022 - name: test num_bytes: 255053799 num_examples: 78388 - name: validation num_bytes: 256030595 num_examples: 78534 download_size: 360175965 dataset_size: 2408767059 - config_name: fm+fc+c+t+tc features: - name: id dtype: string - name: source dtype: string - name: target dtype: string splits: - name: train num_bytes: 1109827485 num_examples: 624022 - name: test num_bytes: 142558255 num_examples: 78388 - name: validation num_bytes: 144523616 num_examples: 78534 download_size: 251861137 dataset_size: 1396909356 - config_name: fm+fc+t+tc features: - name: id dtype: string - name: source dtype: string - name: target dtype: string splits: - name: train num_bytes: 1046592848 num_examples: 624022 - name: test num_bytes: 135403379 num_examples: 78388 - name: validation num_bytes: 136729952 num_examples: 78534 download_size: 243052074 dataset_size: 1318726179 - config_name: fm+t features: - name: id dtype: string - name: source dtype: string - name: target dtype: string splits: - name: train num_bytes: 868034154 num_examples: 624022 - name: test num_bytes: 114371187 num_examples: 78388 - name: validation num_bytes: 112688219 num_examples: 78534 download_size: 217267853 dataset_size: 1095093560 - config_name: fm_indented features: - name: id dtype: string - name: text dtype: string splits: - name: train num_bytes: 473170158 num_examples: 624022 - name: test num_bytes: 64280367 num_examples: 78388 - name: validation num_bytes: 61093848 num_examples: 78534 download_size: 103174190 dataset_size: 598544373 - config_name: t features: - name: id dtype: string - name: source dtype: string - name: target dtype: string splits: - name: train num_bytes: 380207303 num_examples: 624022 - name: test num_bytes: 47993188 num_examples: 78388 - name: validation num_bytes: 49808813 num_examples: 78534 download_size: 113820250 dataset_size: 478009304 - config_name: t+tc features: - name: id dtype: string - name: source dtype: string - name: target dtype: string splits: - name: train num_bytes: 550955294 num_examples: 624022 - name: test num_bytes: 68323462 num_examples: 78388 - name: validation num_bytes: 72740770 num_examples: 78534 download_size: 136767271 dataset_size: 692019526 - config_name: t_indented features: - name: id dtype: string - name: source dtype: string - name: target dtype: string splits: - name: train num_bytes: 405853738 num_examples: 624022 - name: test num_bytes: 51457514 num_examples: 78388 - name: validation num_bytes: 52970428 num_examples: 78534 download_size: 117732776 dataset_size: 510281680 tags: - unit test - java - code --- ## Dataset Description Microsoft created the methods2test dataset, consisting of Java Junit test cases with its corresponding focal methods. It contains 780k pairs of JUnit test cases and focal methods which were extracted from a total of 91K Java open source project hosted on GitHub. This is an assembled version of the methods2test dataset. It provides convenient access to the different context levels based on the raw source code (e.g. newlines are preserved). The test cases and associated classes are also made available. The mapping between test case and focal methods are based heuristics rules and Java developer's best practice. More information could be found here: - [methods2test Github repo](https://github.com/microsoft/methods2test) - [Methods2Test: A dataset of focal methods mapped to test cases](https://arxiv.org/pdf/2203.12776.pdf) ## Dataset Schema ``` t: <TEST_CASE> t_tc: <TEST_CASE> <TEST_CLASS_NAME> fm: <FOCAL_METHOD> fm_fc: <FOCAL_CLASS_NAME> <FOCAL_METHOD> fm_fc_c: <FOCAL_CLASS_NAME> <FOCAL_METHOD> <CONTRSUCTORS> fm_fc_c_m: <FOCAL_CLASS_NAME> <FOCAL_METHOD> <CONTRSUCTORS> <METHOD_SIGNATURES> fm_fc_c_m_f: <FOCAL_CLASS_NAME> <FOCAL_METHOD> <CONTRSUCTORS> <METHOD_SIGNATURES> <FIELDS> ``` ## Focal Context - fm: this representation incorporates exclusively the source code of the focal method. Intuitively, this contains the most important information for generating accurate test cases for the given method. - fm+fc: this representations adds the focal class name, which can provide meaningful semantic information to the model. - fm+fc+c: this representation adds the signatures of the constructor methods of the focal class. The idea behind this augmentation is that the test case may require instantiating an object of the focal class in order to properly test the focal method. - fm+fc+c+m: this representation adds the signatures of the other public methods in the focal class. The rationale which motivated this inclusion is that the test case may need to invoke other auxiliary methods within the class (e.g., getters, setters) to set up or tear down the testing environment. - fm+fc+c+m+f : this representation adds the public fields of the focal class. The motivation is that test cases may need to inspect the status of the public fields to properly test a focal method. ![image/png](https://huggingface.co/datasets/andstor/methods2test/resolve/main/figure-1-focal-context.png) The different levels of focal contexts are the following: ``` T: test case T_TC: test case + test class name FM: focal method FM_FC: focal method + focal class name FM_FC_C: focal method + focal class name + constructor signatures FM_FC_C_M: focal method + focal class name + constructor signatures + public method signatures FM_FC_C_M_F: focal method + focal class name + constructor signatures + public method signatures + public fields ``` ## Limitations The original authors validate the heuristics by inspecting a statistically significant sample (confidence level of 95% within 10% margin of error) of 97 samples from the training set. Two authors independently evaluated the sample, then met to discuss the disagreements. We found that 90.72% of the samples have a correct link between the test case and the corresponding focal method ## Contribution All thanks to the original authors.

zh-plus/tiny-imagenet

zh-plus

"2022-07-12T09:04:30Z"

15,447

72

[ "task_categories:image-classification", "task_ids:multi-class-image-classification", "annotations_creators:crowdsourced", "language_creators:crowdsourced", "multilinguality:monolingual", "source_datasets:extended|imagenet-1k", "language:en", "size_categories:100K<n<1M", "format:parquet", "modality:image", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]

[ "image-classification" ]

"2022-07-01T03:33:16Z"

--- annotations_creators: - crowdsourced extra_gated_prompt: "By clicking on \u201CAccess repository\u201D below, you also\ \ agree to ImageNet Terms of Access:\n[RESEARCHER_FULLNAME] (the \"Researcher\"\ ) has requested permission to use the ImageNet database (the \"Database\") at Princeton\ \ University and Stanford University. In exchange for such permission, Researcher\ \ hereby agrees to the following terms and conditions:\n1. Researcher shall use\ \ the Database only for non-commercial research and educational purposes.\n2. Princeton\ \ University, Stanford University and Hugging Face make no representations or warranties\ \ regarding the Database, including but not limited to warranties of non-infringement\ \ or fitness for a particular purpose.\n3. Researcher accepts full responsibility\ \ for his or her use of the Database and shall defend and indemnify the ImageNet\ \ team, Princeton University, Stanford University and Hugging Face, including their\ \ employees, Trustees, officers and agents, against any and all claims arising from\ \ Researcher's use of the Database, including but not limited to Researcher's use\ \ of any copies of copyrighted images that he or she may create from the Database.\n\ 4. Researcher may provide research associates and colleagues with access to the\ \ Database provided that they first agree to be bound by these terms and conditions.\n\ 5. Princeton University, Stanford University and Hugging Face reserve the right\ \ to terminate Researcher's access to the Database at any time.\n6. If Researcher\ \ is employed by a for-profit, commercial entity, Researcher's employer shall also\ \ be bound by these terms and conditions, and Researcher hereby represents that\ \ he or she is fully authorized to enter into this agreement on behalf of such employer.\n\ 7. The law of the State of New Jersey shall apply to all disputes under this agreement." language: - en language_creators: - crowdsourced license: [] multilinguality: - monolingual paperswithcode_id: imagenet pretty_name: Tiny-ImageNet size_categories: - 100K<n<1M source_datasets: - extended|imagenet-1k task_categories: - image-classification task_ids: - multi-class-image-classification --- # Dataset Card for tiny-imagenet ## Dataset Description - **Homepage:** https://www.kaggle.com/c/tiny-imagenet - **Repository:** [Needs More Information] - **Paper:** http://cs231n.stanford.edu/reports/2017/pdfs/930.pdf - **Leaderboard:** https://paperswithcode.com/sota/image-classification-on-tiny-imagenet-1 ### Dataset Summary Tiny ImageNet contains 100000 images of 200 classes (500 for each class) downsized to 64×64 colored images. Each class has 500 training images, 50 validation images, and 50 test images. ### Languages The class labels in the dataset are in English. ## Dataset Structure ### Data Instances ```json { 'image': <PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=64x64 at 0x1A800E8E190, 'label': 15 } ``` ### Data Fields - image: A PIL.Image.Image object containing the image. Note that when accessing the image column: dataset[0]["image"] the image file is automatically decoded. Decoding of a large number of image files might take a significant amount of time. Thus it is important to first query the sample index before the "image" column, i.e. dataset[0]["image"] should always be preferred over dataset["image"][0]. - label: an int classification label. -1 for test set as the labels are missing. Check `classes.py` for the map of numbers & labels. ### Data Splits | | Train | Valid | | ------------ | ------ | ----- | | # of samples | 100000 | 10000 | ## Usage ### Example #### Load Dataset ```python def example_usage(): tiny_imagenet = load_dataset('Maysee/tiny-imagenet', split='train') print(tiny_imagenet[0]) if __name__ == '__main__': example_usage() ```

Multimodal-Fatima/SNLI-VE_train

Multimodal-Fatima

"2023-02-07T23:21:35Z"

15,368

1

[ "size_categories:100K<n<1M", "format:parquet", "modality:image", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]

null

"2023-02-07T00:32:32Z"

--- dataset_info: features: - name: image dtype: image - name: filename dtype: string - name: premise dtype: string - name: hypothesis dtype: string - name: label dtype: class_label: names: '0': entailment '1': neutral '2': contradiction - name: id dtype: int64 - name: id_image dtype: int64 - name: clip_tags_ViT_L_14 sequence: string - name: blip_caption dtype: string - name: LLM_Description_gpt3_downstream_tasks_visual_genome_ViT_L_14 sequence: string splits: - name: train num_bytes: 73634118251.385 num_examples: 529527 download_size: 27853612384 dataset_size: 73634118251.385 --- # Dataset Card for "SNLI-VE_train" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

Avelina/smollm-corpus-cleaned

Avelina

"2025-02-26T23:03:34Z"

15,329

0

[ "task_categories:text-generation", "language:en", "license:odc-by", "size_categories:100M<n<1B", "format:json", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "region:us" ]

[ "text-generation" ]

"2025-02-26T20:55:01Z"

--- license: odc-by dataset_info: - config_name: default features: - name: text dtype: string configs: - config_name: default data_files: - split: train path: data*/train-* task_categories: - text-generation language: - en size_categories: - 100M<n<1B --- # SmolLM-Corpus: Now shuffled and sharded (and Cleaned)! This is a version of the SmolLM-Corpus where the 3 subsets have been interleved, shuffled and sharded as 23698 `jsonl.zst` files for easy streaming! The dataset is comprised of the `cosmopedia-v2` and `fineweb-edu-dedup` subsets from the original [SmolLM-Corpus repo](https://huggingface.co/datasets/HuggingFaceTB/smollm-corpus), with the `python-edu` subset being pulled from my [python-edu-cleaned repo](https://huggingface.co/datasets/Avelina/python-edu-cleaned). ## Dataset Structure The dataset is split into 24 subdirectories, with the first 23 containing 1000 shards and the 24th containing the final 698. The repository is structured as follows: ``` data00/ ├── train-00000-of-23698.jsonl.zst ├── ... └── train-00999-of-23698.jsonl.zst data01/ ├── train-01000-of-23698.jsonl.zst ├── ... └── train-01999-of-23698.jsonl.zst ... data22/ ├── train-22000-of-23698.jsonl.zst ├── ... └── train-22999-of-23698.jsonl.zst data23/ ├── train-23000-of-23698.jsonl.zst ├── ... └── train-23697-of-23698.jsonl.zst ``` In general, you can obtain the exact download URL for all shards using the following python function: ```py def get_url_from_shard( index: int ) -> str: if index >= 23_698: raise ValueError( f'Shard index must be less than 23,698 but received {index}' ) group = index // 1000 return f'https://huggingface.co/datasets/Avelina/smollm-corpus/resolve/main/data{group:02d}/train-{index:05d}-of-23698.jsonl.zst' ``` ## Generation Code Here is the code which was used to generate the shuffled shards. Note the use of non-contiguous interleaving in attempt to uniformly pull documents from across entire subsets to loosely decouple shard index from original document position. Please make sure you `pip install zstandard`!!! ```py import tqdm import datasets from datasets import load_dataset # Output directory and file format. Note that the file extension enforces zst compression is used. OUTPUT_FMT = '/YOUR/FILE/PATH/HERE/data/train-{index:05d}-of-{num_shards:05d}.jsonl.zst' # Total number of shards giving approximately 10,000 documents per shard OUTPUT_NUM_SHARDS = 23698 # Grab the three datasets ds_python = load_dataset( 'Avelina/python-edu-cleaned' ) ds_cosmo = load_dataset( 'HuggingFaceTB/smollm-corpus', 'cosmopedia-v2' ) ds_edu = load_dataset( 'HuggingFaceTB/smollm-corpus', 'fineweb-edu-dedup' ) # Retain only the text columns and the train splits ds_python = ds_python.select_columns( 'text' )[ 'train' ] ds_cosmo = ds_cosmo.select_columns( 'text' )[ 'train' ] ds_edu = ds_edu.select_columns( 'text' )[ 'train' ] # Iterate over all shards with a nice progbar for index in tqdm.tqdm( range( OUTPUT_NUM_SHARDS ) ): # Get non-contiguous in-memory sub-shards for the three datasets curr_python = ds_python.shard( num_shards=OUTPUT_NUM_SHARDS, index=index, contiguous=False, keep_in_memory=True ) curr_cosmo = ds_cosmo.shard( num_shards=OUTPUT_NUM_SHARDS, index=index, contiguous=False, keep_in_memory=True ) curr_edu = ds_edu.shard( num_shards=OUTPUT_NUM_SHARDS, index=index, contiguous=False, keep_in_memory=True ) # Concatenate the sub-shards curr_shard = datasets.concatenate_datasets( [ curr_python, curr_cosmo, curr_edu ] ) # Deterministically shuffle using the current shard index for reproducibility curr_shard = curr_shard.shuffle( seed=index, keep_in_memory=True ) # Dump the shards to .jsonl.zst curr_shard.to_json( OUTPUT_FMT.format( index=index, num_shards=OUTPUT_NUM_SHARDS ) ) ``` ## In-Memory Decompression Zstandard was chosen as it enables trivial in-memory decompression to minimise the storage impact of the dataset. Here is some example code which creates a python generator that yields each json line from a compressed shard stored at `file_name`, and a second function which creates a python generator that parses and yields the compressed shard. ```py import json from json import JSONDecodeError import zstandard def read_lines_zst( file_name ): # Open the file for reading in binary mode with open( file_name, 'rb' ) as file_handle: # Initialise an empty buffer buffer = '' # Create a reader for the opened file reader = zstandard.ZstdDecompressor( max_window_size=2**31 ).stream_reader( file_handle ) while True: # Read a chunk of up to 128MB chunk = reader.read( 2**27 ).decode() # If chunk is empty we've reached the end of the file and can break out if not chunk: break # Combine any prior buffer with the current chunk and split by newline lines = ( buffer + chunk ).split( '\n' ) # Yield the full lines so far for line in lines[ : -1 ]: yield line # The last 'line' is incomplete, so place in buffer for next chunk buffer = lines[ -1 ] # Always remember to close your reader! reader.close() def parse_jsonl_zst( file_name ): # Iterate over the yielded lines of the compressed shard for i, line in enumerate( read_lines_zst( file_name ) ): try: # Convert the line into a python dict and yield the text field yield json.loads( line )[ 'text' ] except ( KeyError, JSONDecodeError ): # Catch KeyError for 'text' not present in dict # Catch JSONDecodeError for malformed line print( f'JSON error @ shard={file_name}, line={i}' ) ``` Of course you *could* use HuggingFace's in-built streaming mechanics to handle things for you, but in my experience that approach is less reliable, doesn't handle `JSONDecodeError`s if there are malformed lines, can cause memory leaks, and has forced sharding behaviour when used inside a multi-worker PyTorch `DataLoader` which I've not yet found a way to disable!

fixie-ai/librispeech_asr

fixie-ai

"2024-08-05T18:38:33Z"

15,326

3

[ "language:en", "size_categories:100K<n<1M", "format:parquet", "modality:audio", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]

null

"2024-07-19T02:34:30Z"

--- language: - en dataset_info: - config_name: clean features: - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: text dtype: string - name: speaker_id dtype: int64 - name: chapter_id dtype: int64 - name: id dtype: string - name: continuation dtype: string splits: - name: test num_bytes: 623948478.48 num_examples: 2620 - name: validation num_bytes: 622190064.956 num_examples: 2703 - name: train.360 num_bytes: 41953890926.124 num_examples: 104014 - name: train.100 num_bytes: 11606313661.774 num_examples: 28539 download_size: 53886816833 dataset_size: 54806343131.334 - config_name: other features: - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: text dtype: string - name: speaker_id dtype: int64 - name: chapter_id dtype: int64 - name: id dtype: string - name: continuation dtype: string splits: - name: train.500 num_bytes: 57330687390.808 num_examples: 148688 - name: validation num_bytes: 591511495.496 num_examples: 2864 - name: test num_bytes: 616939198.113 num_examples: 2939 download_size: 57019309170 dataset_size: 58539138084.417 configs: - config_name: clean data_files: - split: test path: clean/test-* - split: validation path: clean/validation-* - split: train.360 path: clean/train.360-* - split: train.100 path: clean/train.100-* - config_name: other data_files: - split: train.500 path: other/train.500-* - split: validation path: other/validation-* - split: test path: other/test-* ---

parrotzone/sdxl-1.0

parrotzone

"2023-09-20T12:27:51Z"

15,274

12

[ "license:openrail++", "size_categories:1K<n<10K", "format:imagefolder", "modality:image", "library:datasets", "library:mlcroissant", "region:us" ]

null

"2023-07-31T07:18:18Z"

--- license: openrail++ --- # check [sdxl.parrotzone.art](https://sdxl.parrotzone.art) for easy viewing ⋆｡°✩ --- ## all images were made with SDXL 1.0 + the 0.9 VAE - steps: 20 - cfg scale: 7 - no refiner - random seeds

emozilla/Long-Data-Collections-Pretrain-Without-Books

emozilla

"2023-10-09T14:32:21Z"

15,251

1

[ "size_categories:1M<n<10M", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]

null

"2023-10-07T05:31:23Z"

--- configs: - config_name: default data_files: - split: train path: data/train-* dataset_info: features: - name: text dtype: string splits: - name: train num_bytes: 236565210292 num_examples: 9383848 download_size: 25749677954 dataset_size: 236565210292 --- # Dataset Card for "Long-Data-Collections-Pretrain-Without-Books" Paraquet version of the pretrain split of [togethercomputer/Long-Data-Collections](https://huggingface.co/datasets/togethercomputer/Long-Data-Collections) WITHOUT books Statistics (in # of characters): `total_len: 236088622215, average_len: 25159.041601590307`

Helsinki-NLP/opus_infopankki

Helsinki-NLP

"2024-02-22T15:10:55Z"

15,247

4

[ "task_categories:translation", "annotations_creators:found", "language_creators:found", "multilinguality:multilingual", "source_datasets:original", "language:ar", "language:en", "language:es", "language:et", "language:fa", "language:fi", "language:fr", "language:ru", "language:so", "language:sv", "language:tr", "language:zh", "license:cc-by-4.0", "size_categories:1M<n<10M", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]

[ "translation" ]

"2022-03-02T23:29:22Z"

--- annotations_creators: - found language_creators: - found language: - ar - en - es - et - fa - fi - fr - ru - so - sv - tr - zh license: cc-by-4.0 multilinguality: - multilingual size_categories: - 10K<n<100K source_datasets: - original task_categories: - translation task_ids: [] pretty_name: OpusInfopankki config_names: - ar-en - ar-es - ar-et - ar-fa - ar-fi - ar-fr - ar-ru - ar-so - ar-sv - ar-tr - ar-zh - en-es - en-et - en-fa - en-fi - en-fr - en-ru - en-so - en-sv - en-tr - en-zh - es-et - es-fa - es-fi - es-fr - es-ru - es-so - es-sv - es-tr - es-zh - et-fa - et-fi - et-fr - et-ru - et-so - et-sv - et-tr - et-zh - fa-fi - fa-fr - fa-ru - fa-so - fa-sv - fa-tr - fa-zh - fi-fr - fi-ru - fi-so - fi-sv - fi-tr - fi-zh - fr-ru - fr-so - fr-sv - fr-tr - fr-zh - ru-so - ru-sv - ru-tr - ru-zh - so-sv - so-tr - so-zh - sv-tr - sv-zh - tr-zh dataset_info: - config_name: ar-en features: - name: translation dtype: translation: languages: - ar - en splits: - name: train num_bytes: 10133337 num_examples: 50769 download_size: 2775475 dataset_size: 10133337 - config_name: ar-es features: - name: translation dtype: translation: languages: - ar - es splits: - name: train num_bytes: 8665355 num_examples: 40514 download_size: 2366264 dataset_size: 8665355 - config_name: ar-et features: - name: translation dtype: translation: languages: - ar - et splits: - name: train num_bytes: 9087555 num_examples: 46573 download_size: 2475165 dataset_size: 9087555 - config_name: ar-fa features: - name: translation dtype: translation: languages: - ar - fa splits: - name: train num_bytes: 12220196 num_examples: 47007 download_size: 3017006 dataset_size: 12220196 - config_name: ar-fi features: - name: translation dtype: translation: languages: - ar - fi splits: - name: train num_bytes: 9524265 num_examples: 49608 download_size: 2704144 dataset_size: 9524265 - config_name: ar-fr features: - name: translation dtype: translation: languages: - ar - fr splits: - name: train num_bytes: 8877629 num_examples: 41061 download_size: 2434048 dataset_size: 8877629 - config_name: ar-ru features: - name: translation dtype: translation: languages: - ar - ru splits: - name: train num_bytes: 13648194 num_examples: 50286 download_size: 3393441 dataset_size: 13648194 - config_name: ar-so features: - name: translation dtype: translation: languages: - ar - so splits: - name: train num_bytes: 9555548 num_examples: 44736 download_size: 2614055 dataset_size: 9555548 - config_name: ar-sv features: - name: translation dtype: translation: languages: - ar - sv splits: - name: train num_bytes: 8585135 num_examples: 43085 download_size: 2312217 dataset_size: 8585135 - config_name: ar-tr features: - name: translation dtype: translation: languages: - ar - tr splits: - name: train num_bytes: 8691077 num_examples: 41710 download_size: 2417172 dataset_size: 8691077 - config_name: ar-zh features: - name: translation dtype: translation: languages: - ar - zh splits: - name: train num_bytes: 5973634 num_examples: 29943 download_size: 1523722 dataset_size: 5973634 - config_name: en-es features: - name: translation dtype: translation: languages: - en - es splits: - name: train num_bytes: 6933983 num_examples: 42657 download_size: 2108422 dataset_size: 6933983 - config_name: en-et features: - name: translation dtype: translation: languages: - en - et splits: - name: train num_bytes: 8211562 num_examples: 58410 download_size: 2473732 dataset_size: 8211562 - config_name: en-fa features: - name: translation dtype: translation: languages: - en - fa splits: - name: train num_bytes: 10166305 num_examples: 48277 download_size: 2696051 dataset_size: 10166305 - config_name: en-fi features: - name: translation dtype: translation: languages: - en - fi splits: - name: train num_bytes: 10913601 num_examples: 84645 download_size: 3183398 dataset_size: 10913601 - config_name: en-fr features: - name: translation dtype: translation: languages: - en - fr splits: - name: train num_bytes: 8903183 num_examples: 56120 download_size: 2522185 dataset_size: 8903183 - config_name: en-ru features: - name: translation dtype: translation: languages: - en - ru splits: - name: train num_bytes: 15918195 num_examples: 75305 download_size: 3834067 dataset_size: 15918195 - config_name: en-so features: - name: translation dtype: translation: languages: - en - so splits: - name: train num_bytes: 7602290 num_examples: 47220 download_size: 2317274 dataset_size: 7602290 - config_name: en-sv features: - name: translation dtype: translation: languages: - en - sv splits: - name: train num_bytes: 7410975 num_examples: 51749 download_size: 2214196 dataset_size: 7410975 - config_name: en-tr features: - name: translation dtype: translation: languages: - en - tr splits: - name: train num_bytes: 6929154 num_examples: 44030 download_size: 2158897 dataset_size: 6929154 - config_name: en-zh features: - name: translation dtype: translation: languages: - en - zh splits: - name: train num_bytes: 4666963 num_examples: 29907 download_size: 1313255 dataset_size: 4666963 - config_name: es-et features: - name: translation dtype: translation: languages: - es - et splits: - name: train num_bytes: 6611956 num_examples: 42342 download_size: 2109076 dataset_size: 6611956 - config_name: es-fa features: - name: translation dtype: translation: languages: - es - fa splits: - name: train num_bytes: 9338210 num_examples: 41218 download_size: 2535729 dataset_size: 9338210 - config_name: es-fi features: - name: translation dtype: translation: languages: - es - fi splits: - name: train num_bytes: 6436298 num_examples: 41479 download_size: 2052254 dataset_size: 6436298 - config_name: es-fr features: - name: translation dtype: translation: languages: - es - fr splits: - name: train num_bytes: 7368724 num_examples: 41940 download_size: 2234633 dataset_size: 7368724 - config_name: es-ru features: - name: translation dtype: translation: languages: - es - ru splits: - name: train num_bytes: 9844937 num_examples: 41061 download_size: 2638368 dataset_size: 9844937 - config_name: es-so features: - name: translation dtype: translation: languages: - es - so splits: - name: train num_bytes: 7257038 num_examples: 41752 download_size: 2261851 dataset_size: 7257038 - config_name: es-sv features: - name: translation dtype: translation: languages: - es - sv splits: - name: train num_bytes: 6650652 num_examples: 41256 download_size: 2027874 dataset_size: 6650652 - config_name: es-tr features: - name: translation dtype: translation: languages: - es - tr splits: - name: train num_bytes: 7144065 num_examples: 42191 download_size: 2206245 dataset_size: 7144065 - config_name: es-zh features: - name: translation dtype: translation: languages: - es - zh splits: - name: train num_bytes: 4358751 num_examples: 26004 download_size: 1176333 dataset_size: 4358751 - config_name: et-fa features: - name: translation dtype: translation: languages: - et - fa splits: - name: train num_bytes: 9795996 num_examples: 47633 download_size: 2680445 dataset_size: 9795996 - config_name: et-fi features: - name: translation dtype: translation: languages: - et - fi splits: - name: train num_bytes: 7656989 num_examples: 57353 download_size: 2419554 dataset_size: 7656989 - config_name: et-fr features: - name: translation dtype: translation: languages: - et - fr splits: - name: train num_bytes: 7012430 num_examples: 44753 download_size: 2193006 dataset_size: 7012430 - config_name: et-ru features: - name: translation dtype: translation: languages: - et - ru splits: - name: train num_bytes: 12001391 num_examples: 55901 download_size: 3160673 dataset_size: 12001391 - config_name: et-so features: - name: translation dtype: translation: languages: - et - so splits: - name: train num_bytes: 7260797 num_examples: 46933 download_size: 2319211 dataset_size: 7260797 - config_name: et-sv features: - name: translation dtype: translation: languages: - et - sv splits: - name: train num_bytes: 6523041 num_examples: 46775 download_size: 2074448 dataset_size: 6523041 - config_name: et-tr features: - name: translation dtype: translation: languages: - et - tr splits: - name: train num_bytes: 6621665 num_examples: 43729 download_size: 2123880 dataset_size: 6621665 - config_name: et-zh features: - name: translation dtype: translation: languages: - et - zh splits: - name: train num_bytes: 4305273 num_examples: 27826 download_size: 1201275 dataset_size: 4305273 - config_name: fa-fi features: - name: translation dtype: translation: languages: - fa - fi splits: - name: train num_bytes: 9579257 num_examples: 46924 download_size: 2618699 dataset_size: 9579257 - config_name: fa-fr features: - name: translation dtype: translation: languages: - fa - fr splits: - name: train num_bytes: 9574254 num_examples: 41975 download_size: 2588917 dataset_size: 9574254 - config_name: fa-ru features: - name: translation dtype: translation: languages: - fa - ru splits: - name: train num_bytes: 13544451 num_examples: 47814 download_size: 3351553 dataset_size: 13544451 - config_name: fa-so features: - name: translation dtype: translation: languages: - fa - so splits: - name: train num_bytes: 10254723 num_examples: 45571 download_size: 2813443 dataset_size: 10254723 - config_name: fa-sv features: - name: translation dtype: translation: languages: - fa - sv splits: - name: train num_bytes: 9153752 num_examples: 43510 download_size: 2512908 dataset_size: 9153752 - config_name: fa-tr features: - name: translation dtype: translation: languages: - fa - tr splits: - name: train num_bytes: 9393209 num_examples: 42708 download_size: 2599794 dataset_size: 9393209 - config_name: fa-zh features: - name: translation dtype: translation: languages: - fa - zh splits: - name: train num_bytes: 5792439 num_examples: 27748 download_size: 1413779 dataset_size: 5792439 - config_name: fi-fr features: - name: translation dtype: translation: languages: - fi - fr splits: - name: train num_bytes: 8310851 num_examples: 55087 download_size: 2455971 dataset_size: 8310851 - config_name: fi-ru features: - name: translation dtype: translation: languages: - fi - ru splits: - name: train num_bytes: 15188168 num_examples: 74699 download_size: 3842831 dataset_size: 15188168 - config_name: fi-so features: - name: translation dtype: translation: languages: - fi - so splits: - name: train num_bytes: 7076221 num_examples: 46032 download_size: 2219872 dataset_size: 7076221 - config_name: fi-sv features: - name: translation dtype: translation: languages: - fi - sv splits: - name: train num_bytes: 6947224 num_examples: 51506 download_size: 2137629 dataset_size: 6947224 - config_name: fi-tr features: - name: translation dtype: translation: languages: - fi - tr splits: - name: train num_bytes: 6438716 num_examples: 42781 download_size: 2081615 dataset_size: 6438716 - config_name: fi-zh features: - name: translation dtype: translation: languages: - fi - zh splits: - name: train num_bytes: 4434168 num_examples: 29503 download_size: 1312557 dataset_size: 4434168 - config_name: fr-ru features: - name: translation dtype: translation: languages: - fr - ru splits: - name: train num_bytes: 12564196 num_examples: 54213 download_size: 3159587 dataset_size: 12564196 - config_name: fr-so features: - name: translation dtype: translation: languages: - fr - so splits: - name: train num_bytes: 7473559 num_examples: 42652 download_size: 2344399 dataset_size: 7473559 - config_name: fr-sv features: - name: translation dtype: translation: languages: - fr - sv splits: - name: train num_bytes: 7027563 num_examples: 43524 download_size: 2107653 dataset_size: 7027563 - config_name: fr-tr features: - name: translation dtype: translation: languages: - fr - tr splits: - name: train num_bytes: 7341078 num_examples: 43036 download_size: 2279611 dataset_size: 7341078 - config_name: fr-zh features: - name: translation dtype: translation: languages: - fr - zh splits: - name: train num_bytes: 4525109 num_examples: 26654 download_size: 1211652 dataset_size: 4525109 - config_name: ru-so features: - name: translation dtype: translation: languages: - ru - so splits: - name: train num_bytes: 10809193 num_examples: 45430 download_size: 2932790 dataset_size: 10809193 - config_name: ru-sv features: - name: translation dtype: translation: languages: - ru - sv splits: - name: train num_bytes: 10517433 num_examples: 47672 download_size: 2724280 dataset_size: 10517433 - config_name: ru-tr features: - name: translation dtype: translation: languages: - ru - tr splits: - name: train num_bytes: 9930592 num_examples: 42587 download_size: 2727600 dataset_size: 9930592 - config_name: ru-zh features: - name: translation dtype: translation: languages: - ru - zh splits: - name: train num_bytes: 6417808 num_examples: 29523 download_size: 1582749 dataset_size: 6417808 - config_name: so-sv features: - name: translation dtype: translation: languages: - so - sv splits: - name: train num_bytes: 6763754 num_examples: 42384 download_size: 2098877 dataset_size: 6763754 - config_name: so-tr features: - name: translation dtype: translation: languages: - so - tr splits: - name: train num_bytes: 7272349 num_examples: 43242 download_size: 2279999 dataset_size: 7272349 - config_name: so-zh features: - name: translation dtype: translation: languages: - so - zh splits: - name: train num_bytes: 4535955 num_examples: 27090 download_size: 1267321 dataset_size: 4535955 - config_name: sv-tr features: - name: translation dtype: translation: languages: - sv - tr splits: - name: train num_bytes: 6637744 num_examples: 42555 download_size: 2045078 dataset_size: 6637744 - config_name: sv-zh features: - name: translation dtype: translation: languages: - sv - zh splits: - name: train num_bytes: 4216405 num_examples: 26898 download_size: 1149609 dataset_size: 4216405 - config_name: tr-zh features: - name: translation dtype: translation: languages: - tr - zh splits: - name: train num_bytes: 4494071 num_examples: 27323 download_size: 1221951 dataset_size: 4494071 configs: - config_name: ar-en data_files: - split: train path: ar-en/train-* - config_name: ar-es data_files: - split: train path: ar-es/train-* - config_name: ar-et data_files: - split: train path: ar-et/train-* - config_name: ar-fa data_files: - split: train path: ar-fa/train-* - config_name: ar-fi data_files: - split: train path: ar-fi/train-* - config_name: ar-fr data_files: - split: train path: ar-fr/train-* - config_name: ar-ru data_files: - split: train path: ar-ru/train-* - config_name: ar-so data_files: - split: train path: ar-so/train-* - config_name: ar-sv data_files: - split: train path: ar-sv/train-* - config_name: ar-tr data_files: - split: train path: ar-tr/train-* - config_name: ar-zh data_files: - split: train path: ar-zh/train-* - config_name: en-es data_files: - split: train path: en-es/train-* - config_name: en-et data_files: - split: train path: en-et/train-* - config_name: en-fa data_files: - split: train path: en-fa/train-* - config_name: en-fi data_files: - split: train path: en-fi/train-* - config_name: en-fr data_files: - split: train path: en-fr/train-* - config_name: en-ru data_files: - split: train path: en-ru/train-* - config_name: en-so data_files: - split: train path: en-so/train-* - config_name: en-sv data_files: - split: train path: en-sv/train-* - config_name: en-tr data_files: - split: train path: en-tr/train-* - config_name: en-zh data_files: - split: train path: en-zh/train-* - config_name: es-et data_files: - split: train path: es-et/train-* - config_name: es-fa data_files: - split: train path: es-fa/train-* - config_name: es-fi data_files: - split: train path: es-fi/train-* - config_name: es-fr data_files: - split: train path: es-fr/train-* - config_name: es-ru data_files: - split: train path: es-ru/train-* - config_name: es-so data_files: - split: train path: es-so/train-* - config_name: es-sv data_files: - split: train path: es-sv/train-* - config_name: es-tr data_files: - split: train path: es-tr/train-* - config_name: es-zh data_files: - split: train path: es-zh/train-* - config_name: et-fa data_files: - split: train path: et-fa/train-* - config_name: et-fi data_files: - split: train path: et-fi/train-* - config_name: et-fr data_files: - split: train path: et-fr/train-* - config_name: et-ru data_files: - split: train path: et-ru/train-* - config_name: et-so data_files: - split: train path: et-so/train-* - config_name: et-sv data_files: - split: train path: et-sv/train-* - config_name: et-tr data_files: - split: train path: et-tr/train-* - config_name: et-zh data_files: - split: train path: et-zh/train-* - config_name: fa-fi data_files: - split: train path: fa-fi/train-* - config_name: fa-fr data_files: - split: train path: fa-fr/train-* - config_name: fa-ru data_files: - split: train path: fa-ru/train-* - config_name: fa-so data_files: - split: train path: fa-so/train-* - config_name: fa-sv data_files: - split: train path: fa-sv/train-* - config_name: fa-tr data_files: - split: train path: fa-tr/train-* - config_name: fa-zh data_files: - split: train path: fa-zh/train-* - config_name: fi-fr data_files: - split: train path: fi-fr/train-* - config_name: fi-ru data_files: - split: train path: fi-ru/train-* - config_name: fi-so data_files: - split: train path: fi-so/train-* - config_name: fi-sv data_files: - split: train path: fi-sv/train-* - config_name: fi-tr data_files: - split: train path: fi-tr/train-* - config_name: fi-zh data_files: - split: train path: fi-zh/train-* - config_name: fr-ru data_files: - split: train path: fr-ru/train-* - config_name: fr-so data_files: - split: train path: fr-so/train-* - config_name: fr-sv data_files: - split: train path: fr-sv/train-* - config_name: fr-tr data_files: - split: train path: fr-tr/train-* - config_name: fr-zh data_files: - split: train path: fr-zh/train-* - config_name: ru-so data_files: - split: train path: ru-so/train-* - config_name: ru-sv data_files: - split: train path: ru-sv/train-* - config_name: ru-tr data_files: - split: train path: ru-tr/train-* - config_name: ru-zh data_files: - split: train path: ru-zh/train-* - config_name: so-sv data_files: - split: train path: so-sv/train-* - config_name: so-tr data_files: - split: train path: so-tr/train-* - config_name: so-zh data_files: - split: train path: so-zh/train-* - config_name: sv-tr data_files: - split: train path: sv-tr/train-* - config_name: sv-zh data_files: - split: train path: sv-zh/train-* - config_name: tr-zh data_files: - split: train path: tr-zh/train-* --- # Dataset Card for infopankki ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Homepage:** https://opus.nlpl.eu/infopankki/corpus/version/infopankki - **Repository:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - **Paper:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - **Leaderboard:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - **Point of Contact:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Dataset Summary A parallel corpus of 12 languages, 66 bitexts. ### Supported Tasks and Leaderboards The underlying task is machine translation. ### Languages [More Information Needed] ## Dataset Structure ### Data Instances [More Information Needed] ### Data Fields [More Information Needed] ### Data Splits [More Information Needed] ## Dataset Creation ### Curation Rationale [More Information Needed] ### Source Data #### Initial Data Collection and Normalization Source: http://www.infopankki.fi via the Open Data API #### Who are the source language producers? [More Information Needed] ### Annotations #### Annotation process [More Information Needed] #### Who are the annotators? [More Information Needed] ### Personal and Sensitive Information [More Information Needed] ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed] ### Discussion of Biases [More Information Needed] ### Other Known Limitations [More Information Needed] ## Additional Information ### Dataset Curators [More Information Needed] ### Licensing Information Licensed under [CC-BY 4.0](https://creativecommons.org/licenses/by/4.0/). ### Citation Information If you use any part of the corpus in your own work, please cite the following article: ``` @inproceedings{tiedemann-2012-parallel, title = "Parallel Data, Tools and Interfaces in {OPUS}", author = {Tiedemann, J{\"o}rg}, editor = "Calzolari, Nicoletta and Choukri, Khalid and Declerck, Thierry and Do{\u{g}}an, Mehmet U{\u{g}}ur and Maegaard, Bente and Mariani, Joseph and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios", booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)", month = may, year = "2012", address = "Istanbul, Turkey", publisher = "European Language Resources Association (ELRA)", url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/463_Paper.pdf", pages = "2214--2218", abstract = "This paper presents the current status of OPUS, a growing language resource of parallel corpora and related tools. The focus in OPUS is to provide freely available data sets in various formats together with basic annotation to be useful for applications in computational linguistics, translation studies and cross-linguistic corpus studies. In this paper, we report about new data sets and their features, additional annotation tools and models provided from the website and essential interfaces and on-line services included in the project.", } ``` ### Contributions Thanks to [@patil-suraj](https://github.com/patil-suraj) for adding this dataset.

pietrolesci/pythia-deduped-stats-raw

pietrolesci

"2025-04-09T19:26:24Z"

15,193

0

[ "language:en", "size_categories:10M<n<100M", "format:parquet", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "arxiv:2406.04327", "region:us" ]

null

"2024-02-12T01:19:05Z"

--- language: - en --- This dataset has been created as an artefact of the paper [Causal Estimation of Memorisation Profiles (Lesci et al., 2024)](https://arxiv.org/abs/2406.04327). More info about this dataset in the related collection [Memorisation-Profiles](https://huggingface.co/collections/pietrolesci/memorisation-profiles-6619604c4594c878cd9d451f). Collection of data statistics computed using the intermediate checkpoints (step0, step1000, ..., step143k) of all Pythia deduped versions. This folder contains the model evaluations (or "stats") for each model size included in the study. This is the "raw" version where we have stats at the token level. We gathered these statistics "just in case" since the inference process was expensive. However, we provide the sequence-level statistics in the `pietrolesci/pythia-deduped-stats` dataset.

jxie/camelyon17

jxie

"2023-06-22T09:10:17Z"

15,192

0

[ "size_categories:1M<n<10M", "format:parquet", "modality:image", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]

null

"2023-06-20T19:19:23Z"

--- dataset_info: features: - name: image dtype: image - name: label dtype: class_label: names: '0': '0' '1': '1' splits: - name: id_train num_bytes: 1028118482.46 num_examples: 302436 - name: id_val num_bytes: 114778024.28 num_examples: 33560 - name: unlabeled_train num_bytes: 2167898085.29 num_examples: 600030 - name: ood_val num_bytes: 129021135.128 num_examples: 34904 - name: ood_test num_bytes: 276517018.354 num_examples: 85054 download_size: 2858780601 dataset_size: 3716332745.5119996 --- # Dataset Card for "camelyon17" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

Yelp/yelp_review_full

Yelp

"2024-01-04T17:14:53Z"

15,147

118

[ "task_categories:text-classification", "task_ids:sentiment-classification", "annotations_creators:crowdsourced", "language_creators:crowdsourced", "multilinguality:monolingual", "source_datasets:original", "language:en", "license:other", "size_categories:100K<n<1M", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "arxiv:1509.01626", "region:us" ]

[ "text-classification" ]

"2022-03-02T23:29:22Z"

--- annotations_creators: - crowdsourced language_creators: - crowdsourced language: - en license: - other multilinguality: - monolingual size_categories: - 100K<n<1M source_datasets: - original task_categories: - text-classification task_ids: - sentiment-classification pretty_name: YelpReviewFull license_details: yelp-licence dataset_info: config_name: yelp_review_full features: - name: label dtype: class_label: names: '0': 1 star '1': 2 star '2': 3 stars '3': 4 stars '4': 5 stars - name: text dtype: string splits: - name: train num_bytes: 483811554 num_examples: 650000 - name: test num_bytes: 37271188 num_examples: 50000 download_size: 322952369 dataset_size: 521082742 configs: - config_name: yelp_review_full data_files: - split: train path: yelp_review_full/train-* - split: test path: yelp_review_full/test-* default: true train-eval-index: - config: yelp_review_full task: text-classification task_id: multi_class_classification splits: train_split: train eval_split: test col_mapping: text: text label: target metrics: - type: accuracy name: Accuracy - type: f1 name: F1 macro args: average: macro - type: f1 name: F1 micro args: average: micro - type: f1 name: F1 weighted args: average: weighted - type: precision name: Precision macro args: average: macro - type: precision name: Precision micro args: average: micro - type: precision name: Precision weighted args: average: weighted - type: recall name: Recall macro args: average: macro - type: recall name: Recall micro args: average: micro - type: recall name: Recall weighted args: average: weighted --- --- # Dataset Card for YelpReviewFull ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Homepage:** [Yelp](https://www.yelp.com/dataset) - **Repository:** [Crepe](https://github.com/zhangxiangxiao/Crepe) - **Paper:** [Character-level Convolutional Networks for Text Classification](https://arxiv.org/abs/1509.01626) - **Point of Contact:** [Xiang Zhang](mailto:[email protected]) ### Dataset Summary The Yelp reviews dataset consists of reviews from Yelp. It is extracted from the Yelp Dataset Challenge 2015 data. ### Supported Tasks and Leaderboards - `text-classification`, `sentiment-classification`: The dataset is mainly used for text classification: given the text, predict the sentiment. ### Languages The reviews were mainly written in english. ## Dataset Structure ### Data Instances A typical data point, comprises of a text and the corresponding label. An example from the YelpReviewFull test set looks as follows: ``` { 'label': 0, 'text': 'I got \'new\' tires from them and within two weeks got a flat. I took my car to a local mechanic to see if i could get the hole patched, but they said the reason I had a flat was because the previous patch had blown - WAIT, WHAT? I just got the tire and never needed to have it patched? This was supposed to be a new tire. \\nI took the tire over to Flynn\'s and they told me that someone punctured my tire, then tried to patch it. So there are resentful tire slashers? I find that very unlikely. After arguing with the guy and telling him that his logic was far fetched he said he\'d give me a new tire \\"this time\\". \\nI will never go back to Flynn\'s b/c of the way this guy treated me and the simple fact that they gave me a used tire!' } ``` ### Data Fields - 'text': The review texts are escaped using double quotes ("), and any internal double quote is escaped by 2 double quotes (""). New lines are escaped by a backslash followed with an "n" character, that is "\n". - 'label': Corresponds to the score associated with the review (between 1 and 5). ### Data Splits The Yelp reviews full star dataset is constructed by randomly taking 130,000 training samples and 10,000 testing samples for each review star from 1 to 5. In total there are 650,000 trainig samples and 50,000 testing samples. ## Dataset Creation ### Curation Rationale The Yelp reviews full star dataset is constructed by Xiang Zhang ([email protected]) from the Yelp Dataset Challenge 2015. It is first used as a text classification benchmark in the following paper: Xiang Zhang, Junbo Zhao, Yann LeCun. Character-level Convolutional Networks for Text Classification. Advances in Neural Information Processing Systems 28 (NIPS 2015). ### Source Data #### Initial Data Collection and Normalization [More Information Needed] #### Who are the source language producers? [More Information Needed] ### Annotations #### Annotation process [More Information Needed] #### Who are the annotators? [More Information Needed] ### Personal and Sensitive Information [More Information Needed] ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed] ### Discussion of Biases [More Information Needed] ### Other Known Limitations [More Information Needed] ## Additional Information ### Dataset Curators [More Information Needed] ### Licensing Information You can check the official [yelp-dataset-agreement](https://s3-media3.fl.yelpcdn.com/assets/srv0/engineering_pages/bea5c1e92bf3/assets/vendor/yelp-dataset-agreement.pdf). ### Citation Information Xiang Zhang, Junbo Zhao, Yann LeCun. Character-level Convolutional Networks for Text Classification. Advances in Neural Information Processing Systems 28 (NIPS 2015). ### Contributions Thanks to [@hfawaz](https://github.com/hfawaz) for adding this dataset.

laion/strategic_game_chess

laion

"2023-10-20T04:14:20Z"

15,087

28

[ "license:cc-by-4.0", "size_categories:1M<n<10M", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us", "game" ]

null

"2023-06-06T02:09:13Z"

--- tags: - game pretty_name: The Chess Dataset license: cc-by-4.0 --- # Chess > Recent advancements in artificial intelligence (AI) underscore the progress of reasoning and planning shown by recent generalist machine learning (ML) models. The progress can be boosted by datasets that can further boost these generic capabilities when used for training foundation models of various kind. This research initiative has generated extensive synthetic datasets from complex games — chess, Rubik's Cube, and mazes — to study facilitation and the advancement of these critical generic skills in AI models. This dataset contains 3.2 billion games, equating to approximately 608 billion individual moves. it is generated through self-play by Stockfish engine using Fugaku and we add initial moves to expand its diversity. Each game has three columns: 'Moves', 'Termination' and 'Result', - 'Move': recorded chess moves of the whole game. - 'Termination': include CHECKMATE, INSUFFICIENT_MATERIAL, ... etc. - Please check this for detail information https://python-chess.readthedocs.io/en/latest/core.html#chess.Outcome.termination - 'Result': result of this game, 1-0, 1/2-1/2, 0-1. ### Call for Collaboration We invite interested researchers and ML practitioners to explore these datasets' potential. Whether training GPT models from scratch or fine-tuning pre-existing models, we encourage the exploration of various pre-training and fine-tuning strategies using these game-based datasets standalone or as enhancement of other already composed large-scale data. Our team is prepared to assist in securing necessary GPU resources for these explorations. We are particularly interested in collaborators eager to pre-train models of small to medium scale on our game data, subsequently transition to standard text-based training, and then perform comparative analyses against models of similar architecture trained exclusively on text data. Conclusively, this initiative marks a significant stride toward intricate problem-solving and strategic planning in AI, extending an open invitation to the research community for collaborative advancement in this domain.

taesiri/arxiv_audio

taesiri

"2023-12-22T04:56:39Z"

15,073

2

[ "license:cc-by-4.0", "size_categories:1K<n<10K", "format:text", "modality:audio", "modality:text", "library:datasets", "library:mlcroissant", "region:us" ]

null

"2023-07-03T03:46:57Z"

--- license: cc-by-4.0 ---

MERaLiON/Multitask-National-Speech-Corpus-v1

MERaLiON

"2025-01-21T03:54:47Z"

15,053

9

[ "size_categories:10M<n<100M", "format:parquet", "modality:audio", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "arxiv:2501.01034", "region:us" ]

null

"2024-11-28T02:20:03Z"

--- dataset_info: - config_name: ASR-PART1-Test features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 571211945.0 num_examples: 3000 download_size: 559850838 dataset_size: 571211945.0 - config_name: ASR-PART1-Train features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 385418198300.75 num_examples: 2258301 download_size: 377045178322 dataset_size: 385418198300.75 - config_name: ASR-PART2-Test features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 465911787.0 num_examples: 3000 download_size: 453955477 dataset_size: 465911787.0 - config_name: ASR-PART2-Train features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 363327397513.5 num_examples: 2473990 download_size: 353295436382 dataset_size: 363327397513.5 - config_name: ASR-PART3-Test features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 888128151.0 num_examples: 1000 download_size: 869839634 dataset_size: 888128151.0 - config_name: ASR-PART3-Train features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 85425161802.75 num_examples: 96245 download_size: 83617613004 dataset_size: 85425161802.75 - config_name: ASR-PART4-Test features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 840669815.0 num_examples: 1000 download_size: 840073363 dataset_size: 840669815.0 - config_name: ASR-PART4-Train features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 8086630962.75 num_examples: 9629 download_size: 8080765859 dataset_size: 8086630962.75 - config_name: ASR-PART5-Test features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 796429463.0 num_examples: 1000 download_size: 793697822 dataset_size: 796429463.0 - config_name: ASR-PART5-Train features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 19368760964.0 num_examples: 24320 download_size: 19307168143 dataset_size: 19368760964.0 - config_name: ASR-PART6-Test features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 778918943.0 num_examples: 1000 download_size: 776120504 dataset_size: 778918943.0 - config_name: ASR-PART6-Train features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 80452740634.25 num_examples: 103935 download_size: 80163834483 dataset_size: 80452740634.25 - config_name: PQA-AR-Dialogue-Test features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 2524213101.0 num_examples: 3000 download_size: 2502881430 dataset_size: 2524213101.0 - config_name: PQA-AR-Dialogue-Train features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 112833638040.5 num_examples: 130194 download_size: 110972595941 dataset_size: 112833638040.5 - config_name: PQA-AR-Sentence-Test features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 1037448188.0 num_examples: 6000 download_size: 1013575979 dataset_size: 1037448188.0 - config_name: PQA-AR-Sentence-Train features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 748962171712.25 num_examples: 4732291 download_size: 730150284902 dataset_size: 748962171712.25 - config_name: PQA-GR-Dialogue-Test features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 2524070317.0 num_examples: 3000 download_size: 2502849279 dataset_size: 2524070317.0 - config_name: PQA-GR-Dialogue-Train features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 112828111831.5 num_examples: 130194 download_size: 110971280799 dataset_size: 112828111831.5 - config_name: PQA-GR-Sentence-Test features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 1037310373.0 num_examples: 6000 download_size: 1013567377 dataset_size: 1037310373.0 - config_name: PQA-GR-Sentence-Train features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 748852926219.25 num_examples: 4732291 download_size: 730143237881 dataset_size: 748852926219.25 - config_name: SDS-PART3-Test features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 90554299.0 num_examples: 100 download_size: 89690527 dataset_size: 90554299.0 - config_name: SDS-PART3-Train features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 85422319098.75 num_examples: 96245 download_size: 83614162476 dataset_size: 85422319098.75 - config_name: SDS-PART4-Test features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 88940350.0 num_examples: 100 download_size: 88911005 dataset_size: 88940350.0 - config_name: SDS-PART4-Train features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 8085687190.75 num_examples: 9629 download_size: 8079929577 dataset_size: 8085687190.75 - config_name: SDS-PART5-Test features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 88124206.0 num_examples: 100 download_size: 87803731 dataset_size: 88124206.0 - config_name: SDS-PART5-Train features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 19367349094.0 num_examples: 24320 download_size: 19305847065 dataset_size: 19367349094.0 - config_name: SDS-PART6-Test features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 87732392.0 num_examples: 100 download_size: 87551938 dataset_size: 87732392.0 - config_name: SDS-PART6-Train features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 80449120699.25 num_examples: 103935 download_size: 80159781897 dataset_size: 80449120699.25 - config_name: SQA-PART3-Test features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 90552574.0 num_examples: 100 download_size: 89693755 dataset_size: 90552574.0 - config_name: SQA-PART3-Train features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 85376993587.0 num_examples: 96232 download_size: 83585944443 dataset_size: 85376993587.0 - config_name: SQA-PART4-Test features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 88935324.0 num_examples: 100 download_size: 88913332 dataset_size: 88935324.0 - config_name: SQA-PART4-Train features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 8080383599.5 num_examples: 9626 download_size: 8076488125 dataset_size: 8080383599.5 - config_name: SQA-PART5-Test features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 88115583.0 num_examples: 100 download_size: 87803336 dataset_size: 88115583.0 - config_name: SQA-PART5-Train features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 19354344382.25 num_examples: 24311 download_size: 19296773516 dataset_size: 19354344382.25 - config_name: SQA-PART6-Test features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 87727131.0 num_examples: 100 download_size: 87554027 dataset_size: 87727131.0 - config_name: SQA-PART6-Train features: - name: context dtype: audio: sampling_rate: 16000 - name: instruction dtype: string - name: answer dtype: string splits: - name: train num_bytes: 80401794701.0 num_examples: 103908 download_size: 80128135250 dataset_size: 80401794701.0 configs: - config_name: ASR-PART1-Test data_files: - split: train path: ASR-PART1-Test/train-* - config_name: ASR-PART1-Train data_files: - split: train path: ASR-PART1-Train/train-* - config_name: ASR-PART2-Test data_files: - split: train path: ASR-PART2-Test/train-* - config_name: ASR-PART2-Train data_files: - split: train path: ASR-PART2-Train/train-* - config_name: ASR-PART3-Test data_files: - split: train path: ASR-PART3-Test/train-* - config_name: ASR-PART3-Train data_files: - split: train path: ASR-PART3-Train/train-* - config_name: ASR-PART4-Test data_files: - split: train path: ASR-PART4-Test/train-* - config_name: ASR-PART4-Train data_files: - split: train path: ASR-PART4-Train/train-* - config_name: ASR-PART5-Test data_files: - split: train path: ASR-PART5-Test/train-* - config_name: ASR-PART5-Train data_files: - split: train path: ASR-PART5-Train/train-* - config_name: ASR-PART6-Test data_files: - split: train path: ASR-PART6-Test/train-* - config_name: ASR-PART6-Train data_files: - split: train path: ASR-PART6-Train/train-* - config_name: PQA-AR-Dialogue-Test data_files: - split: train path: PQA-AR-Dialogue-Test/train-* - config_name: PQA-AR-Dialogue-Train data_files: - split: train path: PQA-AR-Dialogue-Train/train-* - config_name: PQA-AR-Sentence-Test data_files: - split: train path: PQA-AR-Sentence-Test/train-* - config_name: PQA-AR-Sentence-Train data_files: - split: train path: PQA-AR-Sentence-Train/train-* - config_name: PQA-GR-Dialogue-Test data_files: - split: train path: PQA-GR-Dialogue-Test/train-* - config_name: PQA-GR-Dialogue-Train data_files: - split: train path: PQA-GR-Dialogue-Train/train-* - config_name: PQA-GR-Sentence-Test data_files: - split: train path: PQA-GR-Sentence-Test/train-* - config_name: PQA-GR-Sentence-Train data_files: - split: train path: PQA-GR-Sentence-Train/train-* - config_name: SDS-PART3-Test data_files: - split: train path: SDS-PART3-Test/train-* - config_name: SDS-PART3-Train data_files: - split: train path: SDS-PART3-Train/train-* - config_name: SDS-PART4-Test data_files: - split: train path: SDS-PART4-Test/train-* - config_name: SDS-PART4-Train data_files: - split: train path: SDS-PART4-Train/train-* - config_name: SDS-PART5-Test data_files: - split: train path: SDS-PART5-Test/train-* - config_name: SDS-PART5-Train data_files: - split: train path: SDS-PART5-Train/train-* - config_name: SDS-PART6-Test data_files: - split: train path: SDS-PART6-Test/train-* - config_name: SDS-PART6-Train data_files: - split: train path: SDS-PART6-Train/train-* - config_name: SQA-PART3-Test data_files: - split: train path: SQA-PART3-Test/train-* - config_name: SQA-PART3-Train data_files: - split: train path: SQA-PART3-Train/train-* - config_name: SQA-PART4-Test data_files: - split: train path: SQA-PART4-Test/train-* - config_name: SQA-PART4-Train data_files: - split: train path: SQA-PART4-Train/train-* - config_name: SQA-PART5-Test data_files: - split: train path: SQA-PART5-Test/train-* - config_name: SQA-PART5-Train data_files: - split: train path: SQA-PART5-Train/train-* - config_name: SQA-PART6-Test data_files: - split: train path: SQA-PART6-Test/train-* - config_name: SQA-PART6-Train data_files: - split: train path: SQA-PART6-Train/train-* --- Multitask-National-Speech-Corpus (MNSC v1) is derived from [IMDA's NSC Corpus](https://www.imda.gov.sg/how-we-can-help/national-speech-corpus). MNSC is a multitask speech understanding dataset derived and further annotated from IMDA NSC Corpus. It focuses on the knowledge of Singapore's local accent, localised terms, and code-switching. - ASR: Automatic Speech Recognition - SQA: Speech Question Answering - SDS: Spoken Dialogue Summarization - PQA: Paralinguistic Question Answering ``` from datasets import load_dataset data = load_dataset('MERaLiON/Multitask-National-Speech-Corpus-v1', data_dir='ASR-PART1-Train')['train'] ``` ``` @article{wang2025advancing, title={Advancing Singlish Understanding: Bridging the Gap with Datasets and Multimodal Models}, author={Wang, Bin and Zou, Xunlong and Sun, Shuo and Zhang, Wenyu and He, Yingxu and Liu, Zhuohan and Wei, Chengwei and Chen, Nancy F and Aw, AiTi}, journal={arXiv preprint arXiv:2501.01034}, year={2025} } ```

laion/LAION-Audio-300M

laion

"2025-01-10T21:33:57Z"

15,032

28

[ "license:apache-2.0", "size_categories:100M<n<1B", "format:webdataset", "modality:audio", "modality:text", "library:datasets", "library:webdataset", "library:mlcroissant", "region:us" ]

null

"2024-12-29T09:50:41Z"

--- license: apache-2.0 ---

davanstrien/AmericanStories-parquet

davanstrien

"2023-10-20T15:09:54Z"

15,026

2

[ "size_categories:10M<n<100M", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]

null

"2023-10-20T14:07:00Z"

--- configs: - config_name: default data_files: - split: '1774' path: data/1774-* - split: '1798' path: data/1798-* - split: '1799' path: data/1799-* - split: '1800' path: data/1800-* - split: '1801' path: data/1801-* - split: '1802' path: data/1802-* - split: '1803' path: data/1803-* - split: '1804' path: data/1804-* - split: '1805' path: data/1805-* - split: '1806' path: data/1806-* - split: '1807' path: data/1807-* - split: '1808' path: data/1808-* - split: '1809' path: data/1809-* - split: '1810' path: data/1810-* - split: '1811' path: data/1811-* - split: '1812' path: data/1812-* - split: '1813' path: data/1813-* - split: '1814' path: data/1814-* - split: '1815' path: data/1815-* - split: '1816' path: data/1816-* - split: '1817' path: data/1817-* - split: '1818' path: data/1818-* - split: '1819' path: data/1819-* - split: '1820' path: data/1820-* - split: '1821' path: data/1821-* - split: '1822' path: data/1822-* - split: '1823' path: data/1823-* - split: '1824' path: data/1824-* - split: '1825' path: data/1825-* - split: '1826' path: data/1826-* - split: '1827' path: data/1827-* - split: '1828' path: data/1828-* - split: '1829' path: data/1829-* - split: '1830' path: data/1830-* - split: '1831' path: data/1831-* - split: '1832' path: data/1832-* - split: '1833' path: data/1833-* - split: '1834' path: data/1834-* - split: '1835' path: data/1835-* - split: '1836' path: data/1836-* - split: '1837' path: data/1837-* - split: '1838' path: data/1838-* - split: '1839' path: data/1839-* - split: '1840' path: data/1840-* - split: '1841' path: data/1841-* - split: '1842' path: data/1842-* - split: '1843' path: data/1843-* - split: '1844' path: data/1844-* - split: '1845' path: data/1845-* - split: '1846' path: data/1846-* - split: '1847' path: data/1847-* - split: '1848' path: data/1848-* - split: '1849' path: data/1849-* - split: '1850' path: data/1850-* - split: '1851' path: data/1851-* - split: '1852' path: data/1852-* - split: '1853' path: data/1853-* - split: '1854' path: data/1854-* - split: '1855' path: data/1855-* - split: '1856' path: data/1856-* - split: '1857' path: data/1857-* - split: '1858' path: data/1858-* - split: '1859' path: data/1859-* - split: '1860' path: data/1860-* - split: '1861' path: data/1861-* - split: '1862' path: data/1862-* - split: '1863' path: data/1863-* - split: '1864' path: data/1864-* - split: '1865' path: data/1865-* - split: '1866' path: data/1866-* - split: '1867' path: data/1867-* - split: '1868' path: data/1868-* - split: '1869' path: data/1869-* - split: '1870' path: data/1870-* - split: '1871' path: data/1871-* - split: '1872' path: data/1872-* - split: '1873' path: data/1873-* - split: '1874' path: data/1874-* - split: '1875' path: data/1875-* - split: '1876' path: data/1876-* - split: '1877' path: data/1877-* - split: '1878' path: data/1878-* - split: '1879' path: data/1879-* - split: '1880' path: data/1880-* - split: '1881' path: data/1881-* - split: '1882' path: data/1882-* - split: '1883' path: data/1883-* - split: '1884' path: data/1884-* - split: '1885' path: data/1885-* - split: '1886' path: data/1886-* - split: '1887' path: data/1887-* - split: '1888' path: data/1888-* - split: '1889' path: data/1889-* - split: '1890' path: data/1890-* - split: '1891' path: data/1891-* - split: '1892' path: data/1892-* - split: '1893' path: data/1893-* - split: '1894' path: data/1894-* - split: '1895' path: data/1895-* - split: '1896' path: data/1896-* - split: '1897' path: data/1897-* - split: '1898' path: data/1898-* - split: '1899' path: data/1899-* - split: '1900' path: data/1900-* - split: '1901' path: data/1901-* - split: '1902' path: data/1902-* - split: '1903' path: data/1903-* - split: '1904' path: data/1904-* - split: '1905' path: data/1905-* - split: '1906' path: data/1906-* - split: '1907' path: data/1907-* - split: '1908' path: data/1908-* - split: '1909' path: data/1909-* - split: '1910' path: data/1910-* - split: '1911' path: data/1911-* - split: '1912' path: data/1912-* - split: '1913' path: data/1913-* - split: '1914' path: data/1914-* - split: '1915' path: data/1915-* - split: '1916' path: data/1916-* - split: '1917' path: data/1917-* - split: '1918' path: data/1918-* - split: '1919' path: data/1919-* - split: '1920' path: data/1920-* - split: '1921' path: data/1921-* - split: '1922' path: data/1922-* - split: '1923' path: data/1923-* - split: '1924' path: data/1924-* - split: '1925' path: data/1925-* - split: '1926' path: data/1926-* - split: '1927' path: data/1927-* - split: '1928' path: data/1928-* - split: '1929' path: data/1929-* - split: '1930' path: data/1930-* - split: '1931' path: data/1931-* - split: '1932' path: data/1932-* - split: '1933' path: data/1933-* - split: '1934' path: data/1934-* - split: '1935' path: data/1935-* - split: '1936' path: data/1936-* - split: '1937' path: data/1937-* - split: '1938' path: data/1938-* - split: '1939' path: data/1939-* - split: '1940' path: data/1940-* - split: '1941' path: data/1941-* - split: '1942' path: data/1942-* - split: '1943' path: data/1943-* - split: '1944' path: data/1944-* - split: '1945' path: data/1945-* - split: '1946' path: data/1946-* - split: '1947' path: data/1947-* - split: '1948' path: data/1948-* - split: '1949' path: data/1949-* - split: '1950' path: data/1950-* - split: '1951' path: data/1951-* - split: '1952' path: data/1952-* - split: '1953' path: data/1953-* - split: '1954' path: data/1954-* - split: '1955' path: data/1955-* - split: '1956' path: data/1956-* - split: '1957' path: data/1957-* - split: '1958' path: data/1958-* - split: '1959' path: data/1959-* - split: '1960' path: data/1960-* - split: '1961' path: data/1961-* - split: '1962' path: data/1962-* - split: '1963' path: data/1963-* dataset_info: features: - name: article_id dtype: string - name: newspaper_name dtype: string - name: edition dtype: string - name: date dtype: string - name: page dtype: string - name: headline dtype: string - name: byline dtype: string - name: article dtype: string splits: - name: '1774' num_bytes: 22245 num_examples: 12 - name: '1798' num_bytes: 72288 num_examples: 73 - name: '1799' num_bytes: 946373 num_examples: 623 - name: '1800' num_bytes: 38139 num_examples: 45 - name: '1801' num_bytes: 94991 num_examples: 93 - name: '1802' num_bytes: 1463322 num_examples: 1158 - name: '1803' num_bytes: 799797 num_examples: 654 - name: '1804' num_bytes: 120141 num_examples: 103 - name: '1805' num_bytes: 2475205 num_examples: 2303 - name: '1806' num_bytes: 2043729 num_examples: 1860 - name: '1807' num_bytes: 310568 num_examples: 315 - name: '1808' num_bytes: 75639 num_examples: 45 - name: '1809' num_bytes: 430706 num_examples: 422 - name: '1810' num_bytes: 1319755 num_examples: 982 - name: '1811' num_bytes: 117701 num_examples: 110 - name: '1812' num_bytes: 75299 num_examples: 67 - name: '1813' num_bytes: 290966 num_examples: 242 - name: '1814' num_bytes: 378212 num_examples: 379 - name: '1815' num_bytes: 185179 num_examples: 160 - name: '1816' num_bytes: 495706 num_examples: 409 - name: '1817' num_bytes: 446354 num_examples: 394 - name: '1818' num_bytes: 1257916 num_examples: 1108 - name: '1819' num_bytes: 2476297 num_examples: 1997 - name: '1820' num_bytes: 611884 num_examples: 433 - name: '1821' num_bytes: 347361 num_examples: 270 - name: '1822' num_bytes: 286227 num_examples: 264 - name: '1823' num_bytes: 2030816 num_examples: 1113 - name: '1824' num_bytes: 5171191 num_examples: 3110 - name: '1825' num_bytes: 6341915 num_examples: 4005 - name: '1826' num_bytes: 10462258 num_examples: 7079 - name: '1827' num_bytes: 11634621 num_examples: 7213 - name: '1828' num_bytes: 10253681 num_examples: 6350 - name: '1829' num_bytes: 4021832 num_examples: 2296 - name: '1830' num_bytes: 8321949 num_examples: 4232 - name: '1831' num_bytes: 16796125 num_examples: 9699 - name: '1832' num_bytes: 9982722 num_examples: 6565 - name: '1833' num_bytes: 6653515 num_examples: 4108 - name: '1834' num_bytes: 7099875 num_examples: 4632 - name: '1835' num_bytes: 9066392 num_examples: 6168 - name: '1836' num_bytes: 10473366 num_examples: 7375 - name: '1837' num_bytes: 21002773 num_examples: 13609 - name: '1838' num_bytes: 13735809 num_examples: 8492 - name: '1839' num_bytes: 12512339 num_examples: 8938 - name: '1840' num_bytes: 12647911 num_examples: 8052 - name: '1841' num_bytes: 39146669 num_examples: 30019 - name: '1842' num_bytes: 26218700 num_examples: 21290 - name: '1843' num_bytes: 50447372 num_examples: 41657 - name: '1844' num_bytes: 79351064 num_examples: 61373 - name: '1845' num_bytes: 131632573 num_examples: 95921 - name: '1846' num_bytes: 81086068 num_examples: 70331 - name: '1847' num_bytes: 32733527 num_examples: 24354 - name: '1848' num_bytes: 44577825 num_examples: 32531 - name: '1849' num_bytes: 53877014 num_examples: 42711 - name: '1850' num_bytes: 76697622 num_examples: 49992 - name: '1851' num_bytes: 128372084 num_examples: 90184 - name: '1852' num_bytes: 67005975 num_examples: 51172 - name: '1853' num_bytes: 54210932 num_examples: 48130 - name: '1854' num_bytes: 150406197 num_examples: 118825 - name: '1855' num_bytes: 115893679 num_examples: 99390 - name: '1856' num_bytes: 188859881 num_examples: 157592 - name: '1857' num_bytes: 152841585 num_examples: 129179 - name: '1858' num_bytes: 214657030 num_examples: 171877 - name: '1859' num_bytes: 178711188 num_examples: 160924 - name: '1860' num_bytes: 163889573 num_examples: 150590 - name: '1861' num_bytes: 215595661 num_examples: 173990 - name: '1862' num_bytes: 228323685 num_examples: 171021 - name: '1863' num_bytes: 197294365 num_examples: 151485 - name: '1864' num_bytes: 125113713 num_examples: 94415 - name: '1865' num_bytes: 133515217 num_examples: 99728 - name: '1866' num_bytes: 180768118 num_examples: 135316 - name: '1867' num_bytes: 213571876 num_examples: 161180 - name: '1868' num_bytes: 202156635 num_examples: 140521 - name: '1869' num_bytes: 236506656 num_examples: 171455 - name: '1870' num_bytes: 242779857 num_examples: 174061 - name: '1871' num_bytes: 203189927 num_examples: 151652 - name: '1872' num_bytes: 242624062 num_examples: 194784 - name: '1873' num_bytes: 302626176 num_examples: 241902 - name: '1874' num_bytes: 280814742 num_examples: 213813 - name: '1875' num_bytes: 319815222 num_examples: 274269 - name: '1876' num_bytes: 381483980 num_examples: 288199 - name: '1877' num_bytes: 317703263 num_examples: 254946 - name: '1878' num_bytes: 381274032 num_examples: 307865 - name: '1879' num_bytes: 371703798 num_examples: 287784 - name: '1880' num_bytes: 296465631 num_examples: 272352 - name: '1881' num_bytes: 294568051 num_examples: 270228 - name: '1882' num_bytes: 340511400 num_examples: 311920 - name: '1883' num_bytes: 419078041 num_examples: 387589 - name: '1884' num_bytes: 329666364 num_examples: 304242 - name: '1885' num_bytes: 348144660 num_examples: 318732 - name: '1886' num_bytes: 431746663 num_examples: 423718 - name: '1887' num_bytes: 493647568 num_examples: 494559 - name: '1888' num_bytes: 564523528 num_examples: 547165 - name: '1889' num_bytes: 558168324 num_examples: 536750 - name: '1890' num_bytes: 566964770 num_examples: 540615 - name: '1891' num_bytes: 641124243 num_examples: 620461 - name: '1892' num_bytes: 524812242 num_examples: 527044 - name: '1893' num_bytes: 645853680 num_examples: 656805 - name: '1894' num_bytes: 790577208 num_examples: 795408 - name: '1895' num_bytes: 890097151 num_examples: 897766 - name: '1896' num_bytes: 1235234882 num_examples: 1175701 - name: '1897' num_bytes: 1252347746 num_examples: 1275895 - name: '1898' num_bytes: 1286411001 num_examples: 1323842 - name: '1899' num_bytes: 1176418162 num_examples: 1218682 - name: '1900' num_bytes: 1069983237 num_examples: 1118970 - name: '1901' num_bytes: 1478945214 num_examples: 1468648 - name: '1902' num_bytes: 1376703767 num_examples: 1417935 - name: '1903' num_bytes: 1255538379 num_examples: 1319686 - name: '1904' num_bytes: 1232185827 num_examples: 1340868 - name: '1905' num_bytes: 1563178627 num_examples: 1635134 - name: '1906' num_bytes: 1632815247 num_examples: 1683643 - name: '1907' num_bytes: 1647491794 num_examples: 1714613 - name: '1908' num_bytes: 1771267430 num_examples: 1842874 - name: '1909' num_bytes: 1844179657 num_examples: 1926228 - name: '1910' num_bytes: 1589052587 num_examples: 1684263 - name: '1911' num_bytes: 1402309564 num_examples: 1510259 - name: '1912' num_bytes: 1621648367 num_examples: 1774149 - name: '1913' num_bytes: 1613599136 num_examples: 1822206 - name: '1914' num_bytes: 1736284455 num_examples: 1931901 - name: '1915' num_bytes: 1690248452 num_examples: 1878654 - name: '1916' num_bytes: 1633563499 num_examples: 1838797 - name: '1917' num_bytes: 1605677226 num_examples: 1810757 - name: '1918' num_bytes: 1803695589 num_examples: 1920102 - name: '1919' num_bytes: 1831703767 num_examples: 1981192 - name: '1920' num_bytes: 1901882705 num_examples: 2041192 - name: '1921' num_bytes: 2264618667 num_examples: 2334112 - name: '1922' num_bytes: 2372137567 num_examples: 2405974 - name: '1923' num_bytes: 812177597 num_examples: 880372 - name: '1924' num_bytes: 800835690 num_examples: 845520 - name: '1925' num_bytes: 601426023 num_examples: 662322 - name: '1926' num_bytes: 565307890 num_examples: 623765 - name: '1927' num_bytes: 460501197 num_examples: 504835 - name: '1928' num_bytes: 452526140 num_examples: 487302 - name: '1929' num_bytes: 366246066 num_examples: 421909 - name: '1930' num_bytes: 437657836 num_examples: 492695 - name: '1931' num_bytes: 441972257 num_examples: 493816 - name: '1932' num_bytes: 640501746 num_examples: 664615 - name: '1933' num_bytes: 634373318 num_examples: 642380 - name: '1934' num_bytes: 641841040 num_examples: 654342 - name: '1935' num_bytes: 612406176 num_examples: 635554 - name: '1936' num_bytes: 621035178 num_examples: 662015 - name: '1937' num_bytes: 625107933 num_examples: 676549 - name: '1938' num_bytes: 616370880 num_examples: 665274 - name: '1939' num_bytes: 525913265 num_examples: 556283 - name: '1940' num_bytes: 471830118 num_examples: 496662 - name: '1941' num_bytes: 599694786 num_examples: 637200 - name: '1942' num_bytes: 508785410 num_examples: 523923 - name: '1943' num_bytes: 452079475 num_examples: 467200 - name: '1944' num_bytes: 442871777 num_examples: 433769 - name: '1945' num_bytes: 588623743 num_examples: 588477 - name: '1946' num_bytes: 526027876 num_examples: 470895 - name: '1947' num_bytes: 461281363 num_examples: 393086 - name: '1948' num_bytes: 442999943 num_examples: 396660 - name: '1949' num_bytes: 421752000 num_examples: 419854 - name: '1950' num_bytes: 403717616 num_examples: 415416 - name: '1951' num_bytes: 409600217 num_examples: 419622 - name: '1952' num_bytes: 397051717 num_examples: 396420 - name: '1953' num_bytes: 366253682 num_examples: 358332 - name: '1954' num_bytes: 263197428 num_examples: 266338 - name: '1955' num_bytes: 268993926 num_examples: 273576 - name: '1956' num_bytes: 85126796 num_examples: 98035 - name: '1957' num_bytes: 83757036 num_examples: 93543 - name: '1958' num_bytes: 85807593 num_examples: 98688 - name: '1959' num_bytes: 112707174 num_examples: 129452 - name: '1960' num_bytes: 300484826 num_examples: 344550 - name: '1961' num_bytes: 297225753 num_examples: 339076 - name: '1962' num_bytes: 231525869 num_examples: 264724 - name: '1963' num_bytes: 197520960 num_examples: 226859 download_size: 48388744959 dataset_size: 76303058024 --- # Dataset Card for "AmericanStories-parquet" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

Avelina/smollm-corpus

Avelina

"2025-01-11T16:41:28Z"

15,023

5

[ "task_categories:text-generation", "language:en", "license:odc-by", "size_categories:100M<n<1B", "region:us" ]

[ "text-generation" ]

"2025-01-11T01:39:39Z"

--- license: odc-by dataset_info: - config_name: default features: - name: text dtype: string configs: - config_name: default data_files: - split: train path: data*/train-* task_categories: - text-generation language: - en size_categories: - 100M<n<1B --- # SmolLM-Corpus: Now shuffled and sharded! This is a version of the SmolLM-Corpus where the 3 subsets have been interleved, shuffled and sharded as 23698 `jsonl.zst` files for easy streaming! The dataset is comprised of the `cosmopedia-v2` and `fineweb-edu-dedup` subsets from the original [SmolLM-Corpus repo](https://huggingface.co/datasets/HuggingFaceTB/smollm-corpus), with the `python-edu` subset being pulled from my [python-edu repo](https://huggingface.co/datasets/Avelina/python-edu). ## Dataset Structure The dataset is split into 24 subdirectories, with the first 23 containing 1000 shards and the 24th containing the final 698. The repository is structured as follows: ``` data00/ ├── train-00000-of-23698.jsonl.zst ├── ... └── train-00999-of-23698.jsonl.zst data01/ ├── train-01000-of-23698.jsonl.zst ├── ... └── train-01999-of-23698.jsonl.zst ... data22/ ├── train-22000-of-23698.jsonl.zst ├── ... └── train-22999-of-23698.jsonl.zst data23/ ├── train-23000-of-23698.jsonl.zst ├── ... └── train-23697-of-23698.jsonl.zst ``` In general, you can obtain the exact download URL for all shards using the following python function: ```py def get_url_from_shard( index: int ) -> str: if index >= 23_698: raise ValueError( f'Shard index must be less than 23,698 but received {index}' ) group = index // 1000 return f'https://huggingface.co/datasets/Avelina/smollm-corpus/resolve/main/data{group:02d}/train-{index:05d}-of-23698.jsonl.zst' ``` ## Generation Code Here is the code which was used to generate the shuffled shards. Note the use of non-contiguous interleaving in attempt to uniformly pull documents from across entire subsets to loosely decouple shard index from original document position. Please make sure you `pip install zstandard`!!! ```py import tqdm import datasets from datasets import load_dataset # Output directory and file format. Note that the file extension enforces zst compression is used. OUTPUT_FMT = '/YOUR/FILE/PATH/HERE/data/train-{index:05d}-of-{num_shards:05d}.jsonl.zst' # Total number of shards giving approximately 10,000 documents per shard OUTPUT_NUM_SHARDS = 23698 # Grab the three datasets ds_python = load_dataset( 'Avelina/python-edu' ) ds_cosmo = load_dataset( 'HuggingFaceTB/smollm-corpus', 'cosmopedia-v2' ) ds_edu = load_dataset( 'HuggingFaceTB/smollm-corpus', 'fineweb-edu-dedup' ) # Retain only the text columns and the train splits ds_python = ds_python.select_columns( 'text' )[ 'train' ] ds_cosmo = ds_cosmo.select_columns( 'text' )[ 'train' ] ds_edu = ds_edu.select_columns( 'text' )[ 'train' ] # Iterate over all shards with a nice progbar for index in tqdm.tqdm( range( OUTPUT_NUM_SHARDS ) ): # Get non-contiguous in-memory sub-shards for the three datasets curr_python = ds_python.shard( num_shards=OUTPUT_NUM_SHARDS, index=index, contiguous=False, keep_in_memory=True ) curr_cosmo = ds_cosmo.shard( num_shards=OUTPUT_NUM_SHARDS, index=index, contiguous=False, keep_in_memory=True ) curr_edu = ds_edu.shard( num_shards=OUTPUT_NUM_SHARDS, index=index, contiguous=False, keep_in_memory=True ) # Concatenate the sub-shards curr_shard = datasets.concatenate_datasets( [ curr_python, curr_cosmo, curr_edu ] ) # Deterministically shuffle using the current shard index for reproducibility curr_shard = curr_shard.shuffle( seed=index, keep_in_memory=True ) # Dump the shards to .jsonl.zst curr_shard.to_json( OUTPUT_FMT.format( index=index, num_shards=OUTPUT_NUM_SHARDS ) ) ``` ## In-Memory Decompression Zstandard was chosen as it enables trivial in-memory decompression to minimise the storage impact of the dataset. Here is some example code which creates a python generator that yields each json line from a compressed shard stored at `file_name`, and a second function which creates a python generator that parses and yields the compressed shard. ```py import json from json import JSONDecodeError import zstandard def read_lines_zst( file_name ): # Open the file for reading in binary mode with open( file_name, 'rb' ) as file_handle: # Initialise an empty buffer buffer = '' # Create a reader for the opened file reader = zstandard.ZstdDecompressor( max_window_size=2**31 ).stream_reader( file_handle ) while True: # Read a chunk of up to 128MB chunk = reader.read( 2**27 ).decode() # If chunk is empty we've reached the end of the file and can break out if not chunk: break # Combine any prior buffer with the current chunk and split by newline lines = ( buffer + chunk ).split( '\n' ) # Yield the full lines so far for line in lines[ : -1 ]: yield line # The last 'line' is incomplete, so place in buffer for next chunk buffer = lines[ -1 ] # Always remember to close your reader! reader.close() def parse_jsonl_zst( file_name ): # Iterate over the yielded lines of the compressed shard for i, line in enumerate( read_lines_zst( file_name ) ): try: # Convert the line into a python dict and yield the text field yield json.loads( line )[ 'text' ] except ( KeyError, JSONDecodeError ): # Catch KeyError for 'text' not present in dict # Catch JSONDecodeError for malformed line print( f'JSON error @ shard={file_name}, line={i}' ) ``` Of course you *could* use HuggingFace's in-built streaming mechanics to handle things for you, but in my experience that approach is less reliable, doesn't handle `JSONDecodeError`s if there are malformed lines, can cause memory leaks, and has forced sharding behaviour when used inside a multi-worker PyTorch `DataLoader` which I've not yet found a way to disable!

INo0121/low_quality_call_voice_preprocessed

INo0121

"2023-09-21T13:25:07Z"

14,949

0

[ "size_categories:10K<n<100K", "format:parquet", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]

null

"2023-09-08T05:10:37Z"

--- configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* - split: valid path: data/valid-* dataset_info: features: - name: input_features sequence: sequence: float32 - name: labels sequence: int64 splits: - name: train num_bytes: 64088254376 num_examples: 66720 - name: test num_bytes: 7476961712 num_examples: 7784 - name: valid num_bytes: 7476975416 num_examples: 7784 download_size: 521083513 dataset_size: 79042191504 --- # Dataset Card for "low_quality_call_voice_preprocessed" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

Anthropic/hh-rlhf

Anthropic

"2023-05-26T18:47:34Z"

14,898

1,314

[ "license:mit", "size_categories:100K<n<1M", "format:json", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "arxiv:2204.05862", "region:us", "human-feedback" ]

null

"2022-12-08T20:11:33Z"

--- license: mit tags: - human-feedback --- # Dataset Card for HH-RLHF ## Dataset Summary This repository provides access to two different kinds of data: 1. Human preference data about helpfulness and harmlessness from [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://arxiv.org/abs/2204.05862). These data are meant to train preference (or reward) models for subsequent RLHF training. These data are *not* meant for supervised training of dialogue agents. Training dialogue agents on these data is likely to lead to harmful models and this shold be avoided. 2. Human-generated and annotated red teaming dialogues from [Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned](https://www.anthropic.com/red_teaming.pdf). These data are meant to understand how crowdworkers red team models and what types of red team attacks are succesful or not. The data are *not* meant for fine-tuning or preference modeling (use the data above for preference modeling). These data are entire transcripts of conversations that are derived from the harmlessness preference modeling data described above, where only the chosen response is incorporated into the overall transcript. Furthermore, the transcripts are annotated with human and automated measurements of how harmful the overall dialogues are. **Disclaimer**: The data (especially the harmlessness preference data and the red team data) contain content that may be offensive or upsetting. Topics include, but are not limited to, discriminatory language and discussions of abuse, violence, self-harm, exploitation, and other potentially upsetting subject matter. Please only engage with the data in accordance with your own personal risk tolerance. The data are intended for research purposes, especially research that can make models *less* harmful. The views expressed in the data do not reflect the views of Anthropic or any of its employees. As mentioned above, these data are *not* intended for training dialogue agents as this will likely lead to harmful model behavior. Each of these datasets are described further below. ## Human preference data about helpfulness and harmlessness (PM Data) The data are described in the paper: [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://arxiv.org/abs/2204.05862). If you find the data useful, please cite the paper. The data format is very simple -- each line of the jsonl files contains a pair of texts, one "chosen" and one "rejected". For **helpfulness**, the data are grouped into train/test splits in three tranches: from our base models (context-distilled 52B language models), via rejection sampling (mostly with best-of-16 sampling) against an early preference model, and a dataset sampled during our iterated "online" process. For **harmlessness**, the data are only collected for our base models, but otherwise formatted in the same way. Details about the data collection process and crowdworker population can be found in the paper, specifically in section 2 and appendix D. ## Red teaming data (not PM Data) The data are described in the paper: [Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned](https://www.anthropic.com/red_teaming.pdf). If you find the data useful, please cite the paper. At a high level these data can be examined to understand what succesful red team attempts look like. Details about the data and data collection procedures can be found in the Datasheet in the appendix of the paper. Each line of the jsonl file contains a dictionary with the following fields: - `transcript` a text transcript of a conversation between a human adversary (red team member) and an AI assistant - `min_harmlessness_score_transcript` a real value score of the harmlessness of the AI assistant (lower is more harmful) as obtained from a preference model - `num_params` number of parameters in the language model powering the AI assistant - `model_type` type of model powering the AI assistant - `rating` the red team member's rating of how successful they were at breaking the AI assistant (Likert scale, higher is more successful) - `task_description` a short text description written by the red team member about how they tried to red team the AI assistant - `task_description_harmlessness_score` a real value score of the harmlessness of the task description (lower is more harmful) as obtained from a preference model - `red_team_member_id` an arbitrary identifier of the red team member. one red team member can generate multiple red team attacks - `is_upworker` a binary indicator that is true if the red team member was from the crowd platform Upwork or false if they were from MTurk - `tags` a list of up to 6 tags per transcript. tags are short descriptions of the red team attempts generated by crowdworkers who reviewed red team data post-hoc. tags were only provided for a random sample of 1000 red team attempts for two of four model types. ## Usage Each of the above datasets is located in a separate sub-directory. To load an individual subset, use the `data_dir` argument of the `load_dataset()` function as follows: ```python from datasets import load_dataset # Load all helpfulness/harmless subsets (share the same schema) dataset = load_dataset("Anthropic/hh-rlhf") # Load one of the harmless subsets dataset = load_dataset("Anthropic/hh-rlhf", data_dir="harmless-base") # Load the red teaming subset dataset = load_dataset("Anthropic/hh-rlhf", data_dir="red-team-attempts") ``` ## Contact The original authors host this dataset on GitHub here: https://github.com/anthropics/hh-rlhf You can submit inquiries to: [email protected]

spdenisov/tokenized_udtree

spdenisov

"2023-03-28T21:56:12Z"

14,872

0

[ "size_categories:1M<n<10M", "format:parquet", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]

null

"2023-03-28T21:50:04Z"

--- dataset_info: features: - name: input_ids sequence: int32 - name: attention_mask sequence: int8 splits: - name: cs_0 num_bytes: 73985244 num_examples: 102133 - name: cs_1 num_bytes: 95459594 num_examples: 102133 - name: cs_2 num_bytes: 95354064 num_examples: 102133 - name: cs_3 num_bytes: 128817619 num_examples: 102133 - name: cs_4 num_bytes: 236925044 num_examples: 102133 - name: cs_5 num_bytes: 115688159 num_examples: 102133 - name: cs_6 num_bytes: 132404489 num_examples: 102133 - name: tr_0 num_bytes: 28666902 num_examples: 60089 - name: tr_1 num_bytes: 31887742 num_examples: 60089 - name: tr_2 num_bytes: 31749302 num_examples: 60089 - name: tr_3 num_bytes: 28498032 num_examples: 60089 - name: tr_4 num_bytes: 57177672 num_examples: 60089 - name: tr_5 num_bytes: 37804587 num_examples: 60089 - name: tr_6 num_bytes: 28280762 num_examples: 60089 - name: ar_0 num_bytes: 32848442 num_examples: 21864 - name: ar_1 num_bytes: 49955197 num_examples: 21864 - name: ar_2 num_bytes: 49285292 num_examples: 21864 - name: ar_3 num_bytes: 69585617 num_examples: 21864 - name: ar_4 num_bytes: 91649737 num_examples: 21864 - name: ar_5 num_bytes: 59303592 num_examples: 21864 - name: ar_6 num_bytes: 50935047 num_examples: 21864 - name: de_0 num_bytes: 112997417 num_examples: 166849 - name: de_1 num_bytes: 149332477 num_examples: 166849 - name: de_2 num_bytes: 157628127 num_examples: 166849 - name: de_3 num_bytes: 155444887 num_examples: 166849 - name: de_4 num_bytes: 309419752 num_examples: 166849 - name: de_5 num_bytes: 191783977 num_examples: 166849 - name: de_6 num_bytes: 138689312 num_examples: 166849 - name: fr_0 num_bytes: 27905013 num_examples: 34921 - name: fr_1 num_bytes: 41237113 num_examples: 34921 - name: fr_2 num_bytes: 45655098 num_examples: 34921 - name: fr_3 num_bytes: 39973853 num_examples: 34921 - name: fr_4 num_bytes: 76420558 num_examples: 34921 - name: fr_5 num_bytes: 56197173 num_examples: 34921 - name: fr_6 num_bytes: 39938223 num_examples: 34921 - name: no_0 num_bytes: 19584526 num_examples: 33282 - name: no_1 num_bytes: 25823376 num_examples: 33282 - name: no_2 num_bytes: 26954416 num_examples: 33282 - name: no_3 num_bytes: 23459636 num_examples: 33282 - name: no_4 num_bytes: 43762856 num_examples: 33282 - name: no_5 num_bytes: 32578281 num_examples: 33282 - name: no_6 num_bytes: 23459636 num_examples: 33282 - name: pt_0 num_bytes: 12627085 num_examples: 30720 - name: pt_1 num_bytes: 16475005 num_examples: 30720 - name: pt_2 num_bytes: 17295815 num_examples: 30720 - name: pt_3 num_bytes: 16917200 num_examples: 30720 - name: pt_4 num_bytes: 24168495 num_examples: 30720 - name: pt_5 num_bytes: 20520155 num_examples: 30720 - name: pt_6 num_bytes: 15115165 num_examples: 30720 - name: es_0 num_bytes: 27551907 num_examples: 28474 - name: es_1 num_bytes: 39391152 num_examples: 28474 - name: es_2 num_bytes: 42349787 num_examples: 28474 - name: es_3 num_bytes: 43743597 num_examples: 28474 - name: es_4 num_bytes: 69878787 num_examples: 28474 - name: es_5 num_bytes: 51203677 num_examples: 28474 - name: es_6 num_bytes: 46914367 num_examples: 28474 - name: ru_0 num_bytes: 57566900 num_examples: 89525 - name: ru_1 num_bytes: 74853550 num_examples: 89525 - name: ru_2 num_bytes: 76555950 num_examples: 89525 - name: ru_3 num_bytes: 67072565 num_examples: 89525 - name: ru_4 num_bytes: 155012405 num_examples: 89525 - name: ru_5 num_bytes: 92396515 num_examples: 89525 - name: ru_6 num_bytes: 98333345 num_examples: 89525 - name: en_0 num_bytes: 14945668 num_examples: 28686 - name: en_1 num_bytes: 20836733 num_examples: 28686 - name: en_2 num_bytes: 23313373 num_examples: 28686 - name: en_3 num_bytes: 21978133 num_examples: 28686 - name: en_4 num_bytes: 32732303 num_examples: 28686 - name: en_5 num_bytes: 28539183 num_examples: 28686 - name: en_6 num_bytes: 28399343 num_examples: 28686 - name: fi_0 num_bytes: 14729969 num_examples: 27198 - name: fi_1 num_bytes: 17656509 num_examples: 27198 - name: fi_2 num_bytes: 16915489 num_examples: 27198 - name: fi_3 num_bytes: 18732354 num_examples: 27198 - name: fi_4 num_bytes: 29894674 num_examples: 27198 - name: fi_5 num_bytes: 20079089 num_examples: 27198 - name: fi_6 num_bytes: 18874279 num_examples: 27198 - name: gd_0 num_bytes: 2829948 num_examples: 3541 - name: gd_1 num_bytes: 3700318 num_examples: 3541 - name: gd_2 num_bytes: 3798313 num_examples: 3541 - name: gd_3 num_bytes: 3907648 num_examples: 3541 - name: gd_4 num_bytes: 5359963 num_examples: 3541 - name: gd_5 num_bytes: 4693368 num_examples: 3541 - name: gd_6 num_bytes: 3383253 num_examples: 3541 - name: gv_0 num_bytes: 456221 num_examples: 1172 - name: gv_1 num_bytes: 597391 num_examples: 1172 - name: gv_2 num_bytes: 609501 num_examples: 1172 - name: gv_3 num_bytes: 542486 num_examples: 1172 - name: gv_4 num_bytes: 785231 num_examples: 1172 - name: gv_5 num_bytes: 729026 num_examples: 1172 - name: gv_6 num_bytes: 542486 num_examples: 1172 - name: ga_0 num_bytes: 3928820 num_examples: 4005 - name: ga_1 num_bytes: 5021230 num_examples: 4005 - name: ga_2 num_bytes: 5059580 num_examples: 4005 - name: ga_3 num_bytes: 4843745 num_examples: 4005 - name: ga_4 num_bytes: 9085760 num_examples: 4005 - name: ga_5 num_bytes: 6197075 num_examples: 4005 - name: ga_6 num_bytes: 4483365 num_examples: 4005 - name: cop_0 num_bytes: 4660032 num_examples: 1379 - name: cop_1 num_bytes: 5726842 num_examples: 1379 - name: cop_2 num_bytes: 4508942 num_examples: 1379 - name: cop_3 num_bytes: 4496787 num_examples: 1379 - name: cop_4 num_bytes: 5425137 num_examples: 1379 - name: cop_5 num_bytes: 4907442 num_examples: 1379 - name: cop_6 num_bytes: 4284382 num_examples: 1379 - name: it_0 num_bytes: 17989232 num_examples: 21724 - name: it_1 num_bytes: 25839627 num_examples: 21724 - name: it_2 num_bytes: 27448052 num_examples: 21724 - name: it_3 num_bytes: 24875027 num_examples: 21724 - name: it_4 num_bytes: 43731272 num_examples: 21724 - name: it_5 num_bytes: 33091747 num_examples: 21724 - name: it_6 num_bytes: 30955017 num_examples: 21724 - name: cy_0 num_bytes: 907518 num_examples: 1111 - name: cy_1 num_bytes: 1180383 num_examples: 1111 - name: cy_2 num_bytes: 1192068 num_examples: 1111 - name: cy_3 num_bytes: 1123428 num_examples: 1111 - name: cy_4 num_bytes: 1834888 num_examples: 1111 - name: cy_5 num_bytes: 1439843 num_examples: 1111 - name: cy_6 num_bytes: 1055223 num_examples: 1111 - name: hu_0 num_bytes: 858340 num_examples: 910 - name: hu_1 num_bytes: 1088085 num_examples: 910 - name: hu_2 num_bytes: 1086220 num_examples: 910 - name: hu_3 num_bytes: 957490 num_examples: 910 - name: hu_4 num_bytes: 1964920 num_examples: 910 - name: hu_5 num_bytes: 1370660 num_examples: 910 - name: hu_6 num_bytes: 957490 num_examples: 910 - name: zh_0 num_bytes: 9051347 num_examples: 7994 - name: zh_1 num_bytes: 12537582 num_examples: 7994 - name: zh_2 num_bytes: 11419717 num_examples: 7994 - name: zh_3 num_bytes: 10888407 num_examples: 7994 - name: zh_4 num_bytes: 10558847 num_examples: 7994 - name: zh_5 num_bytes: 13867342 num_examples: 7994 - name: zh_6 num_bytes: 10167967 num_examples: 7994 - name: hy_0 num_bytes: 5120790 num_examples: 3200 - name: hy_1 num_bytes: 5762195 num_examples: 3200 - name: hy_2 num_bytes: 4712195 num_examples: 3200 - name: hy_3 num_bytes: 4260805 num_examples: 3200 - name: hy_4 num_bytes: 8546900 num_examples: 3200 - name: hy_5 num_bytes: 5442440 num_examples: 3200 - name: hy_6 num_bytes: 4260805 num_examples: 3200 - name: ro_0 num_bytes: 6894274 num_examples: 8043 - name: ro_1 num_bytes: 9156564 num_examples: 8043 - name: ro_2 num_bytes: 9493574 num_examples: 8043 - name: ro_3 num_bytes: 10830604 num_examples: 8043 - name: ro_4 num_bytes: 20320209 num_examples: 8043 - name: ro_5 num_bytes: 11507314 num_examples: 8043 - name: ro_6 num_bytes: 8300564 num_examples: 8043 - name: da_0 num_bytes: 2963139 num_examples: 4383 - name: da_1 num_bytes: 3945104 num_examples: 4383 - name: da_2 num_bytes: 4115634 num_examples: 4383 - name: da_3 num_bytes: 3583269 num_examples: 4383 - name: da_4 num_bytes: 7089004 num_examples: 4383 - name: da_5 num_bytes: 4981724 num_examples: 4383 - name: da_6 num_bytes: 3583269 num_examples: 4383 - name: nl_0 num_bytes: 6741817 num_examples: 12289 - name: nl_1 num_bytes: 8989392 num_examples: 12289 - name: nl_2 num_bytes: 9389757 num_examples: 12289 - name: nl_3 num_bytes: 16004832 num_examples: 12289 - name: nl_4 num_bytes: 12089687 num_examples: 12289 - name: nl_5 num_bytes: 11410547 num_examples: 12289 - name: nl_6 num_bytes: 12631912 num_examples: 12289 download_size: 934434422 dataset_size: 5264208717 --- # Dataset Card for "tokenized_udtree" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

Azathothas/temp

Azathothas

"2025-04-08T06:14:56Z"

14,862

0

[ "license:unlicense", "region:us" ]

null

"2025-03-18T03:49:14Z"

--- license: unlicense --- > [!NOTE] > This serves as way to quickly share temp files with other devs, so the files here are ephemeral & often removed

fixie-ai/covost2

fixie-ai

"2024-08-27T20:58:08Z"

14,834

2

[ "size_categories:1M<n<10M", "format:parquet", "modality:audio", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]

null

"2024-07-16T23:40:52Z"

--- dataset_info: - config_name: ar_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 61607709.192 num_examples: 2283 - name: validation num_bytes: 56223234.024 num_examples: 1758 - name: test num_bytes: 54650910.41 num_examples: 1695 download_size: 160468333 dataset_size: 172481853.626 - config_name: ca_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 4397026262.322 num_examples: 95854 - name: validation num_bytes: 544108371.96 num_examples: 12730 - name: test num_bytes: 604755238.63 num_examples: 12730 download_size: 4957773433 dataset_size: 5545889872.912 - config_name: cy_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 51478765.087 num_examples: 1241 - name: validation num_bytes: 26992697.0 num_examples: 690 - name: test num_bytes: 28772216.0 num_examples: 690 download_size: 102604972 dataset_size: 107243678.087 - config_name: de_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 5680326209.222 num_examples: 127834 - name: validation num_bytes: 631442490.202 num_examples: 13511 - name: test num_bytes: 637042944.685 num_examples: 13511 download_size: 6490850158 dataset_size: 6948811644.108999 - config_name: en_ar features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14105902817.18 num_examples: 289430 - name: validation num_bytes: 718527564.808 num_examples: 15531 - name: test num_bytes: 729114452.301 num_examples: 15531 download_size: 13815709729 dataset_size: 15553544834.289001 - config_name: en_ca features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14099092976.18 num_examples: 289430 - name: validation num_bytes: 718171719.808 num_examples: 15531 - name: test num_bytes: 728790610.301 num_examples: 15531 download_size: 13814365593 dataset_size: 15546055306.289001 - config_name: en_cy features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14098487703.18 num_examples: 289430 - name: validation num_bytes: 718141953.808 num_examples: 15531 - name: test num_bytes: 728793811.301 num_examples: 15531 download_size: 13813953593 dataset_size: 15545423468.289001 - config_name: en_de features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14099886814.18 num_examples: 289430 - name: validation num_bytes: 718219105.808 num_examples: 15531 - name: test num_bytes: 728857067.301 num_examples: 15531 download_size: 13815103686 dataset_size: 15546962987.289001 - config_name: en_et features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14096877545.18 num_examples: 289430 - name: validation num_bytes: 718057559.808 num_examples: 15531 - name: test num_bytes: 728710692.301 num_examples: 15531 download_size: 13813410823 dataset_size: 15543645797.289001 - config_name: en_fa features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14108661241.18 num_examples: 289430 - name: validation num_bytes: 718670909.808 num_examples: 15531 - name: test num_bytes: 729271000.301 num_examples: 15531 download_size: 13816798013 dataset_size: 15556603151.289001 - config_name: en_id features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14098627451.18 num_examples: 289430 - name: validation num_bytes: 718144327.808 num_examples: 15531 - name: test num_bytes: 728802322.301 num_examples: 15531 download_size: 13813201260 dataset_size: 15545574101.289001 - config_name: en_ja features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14103911774.18 num_examples: 289430 - name: validation num_bytes: 718409304.808 num_examples: 15531 - name: test num_bytes: 729050991.301 num_examples: 15531 download_size: 13815875328 dataset_size: 15551372070.289001 - config_name: en_lv features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14098703097.18 num_examples: 289430 - name: validation num_bytes: 718152571.808 num_examples: 15531 - name: test num_bytes: 728792572.301 num_examples: 15531 download_size: 13814849886 dataset_size: 15545648241.289001 - config_name: en_mn features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14113120657.18 num_examples: 289430 - name: validation num_bytes: 718940418.808 num_examples: 15531 - name: test num_bytes: 729461016.301 num_examples: 15531 download_size: 13819427515 dataset_size: 15561522092.289001 - config_name: en_sl features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14097158381.18 num_examples: 289430 - name: validation num_bytes: 718085673.808 num_examples: 15531 - name: test num_bytes: 728705188.301 num_examples: 15531 download_size: 13813603812 dataset_size: 15543949243.289001 - config_name: en_sv-SE features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14097728051.18 num_examples: 289430 - name: validation num_bytes: 718093292.808 num_examples: 15531 - name: test num_bytes: 728747422.301 num_examples: 15531 download_size: 13813332908 dataset_size: 15544568766.289001 - config_name: en_ta features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14135489205.18 num_examples: 289430 - name: validation num_bytes: 720191394.808 num_examples: 15531 - name: test num_bytes: 730578783.301 num_examples: 15531 download_size: 13825121271 dataset_size: 15586259383.289001 - config_name: en_tr features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14098644786.18 num_examples: 289430 - name: validation num_bytes: 718161996.808 num_examples: 15531 - name: test num_bytes: 728786654.301 num_examples: 15531 download_size: 13814279798 dataset_size: 15545593437.289001 - config_name: en_zh-CN features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 14095661460.18 num_examples: 289430 - name: validation num_bytes: 717982705.808 num_examples: 15531 - name: test num_bytes: 728655191.301 num_examples: 15531 download_size: 13812699892 dataset_size: 15542299357.289001 - config_name: es_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: validation num_bytes: 630615357.241 num_examples: 13221 - name: test num_bytes: 666447063.067 num_examples: 13221 - name: train num_bytes: 3769457359.8 num_examples: 79015 download_size: 4531969416 dataset_size: 5066519780.108 - config_name: et_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 97124727.544 num_examples: 1782 - name: validation num_bytes: 80290798.168 num_examples: 1576 - name: test num_bytes: 81970364.51 num_examples: 1571 download_size: 257604448 dataset_size: 259385890.222 - config_name: fa_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 1872724297.149 num_examples: 53949 - name: validation num_bytes: 140067911.23 num_examples: 3445 - name: test num_bytes: 149319550.35 num_examples: 3445 download_size: 1679853440 dataset_size: 2162111758.729 - config_name: fr_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: validation num_bytes: 632191608.84 num_examples: 14760 - name: test num_bytes: 698178059.08 num_examples: 14760 - name: train num_bytes: 8128016830.77 num_examples: 207374 download_size: 8900934523 dataset_size: 9458386498.69 - config_name: id_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 36136135.768 num_examples: 1243 - name: validation num_bytes: 25058845.0 num_examples: 792 - name: test num_bytes: 26577467.0 num_examples: 844 download_size: 86110062 dataset_size: 87772447.768 - config_name: it_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 1517510665.568 num_examples: 31698 - name: validation num_bytes: 422409218.1 num_examples: 8940 - name: test num_bytes: 454569171.595 num_examples: 8951 download_size: 2125529183 dataset_size: 2394489055.2630005 - config_name: ja_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 38181610.624 num_examples: 1119 - name: validation num_bytes: 24623052.0 num_examples: 635 - name: test num_bytes: 25558787.0 num_examples: 684 download_size: 88228548 dataset_size: 88363449.624 - config_name: lv_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 66152116.328 num_examples: 2337 - name: validation num_bytes: 32655276.0 num_examples: 1125 - name: test num_bytes: 50997551.638 num_examples: 1629 download_size: 137700207 dataset_size: 149804943.96600002 - config_name: mn_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 87891433.547 num_examples: 2067 - name: validation num_bytes: 77519039.943 num_examples: 1761 - name: test num_bytes: 83667460.167 num_examples: 1759 download_size: 242638800 dataset_size: 249077933.657 - config_name: nl_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 216102081.4 num_examples: 7108 - name: validation num_bytes: 55386349.319 num_examples: 1699 - name: test num_bytes: 60219179.711 num_examples: 1699 download_size: 320267264 dataset_size: 331707610.43 - config_name: pt_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 274723273.528 num_examples: 9158 - name: validation num_bytes: 118345891.704 num_examples: 3318 - name: test num_bytes: 166247624.001 num_examples: 4023 download_size: 540891735 dataset_size: 559316789.233 - config_name: ru_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 557219472.672 num_examples: 12112 - name: validation num_bytes: 290218427.6 num_examples: 6110 - name: test num_bytes: 312622838.0 num_examples: 6300 download_size: 1112848246 dataset_size: 1160060738.272 - config_name: sl_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 55992153.0 num_examples: 1843 - name: validation num_bytes: 15074155.0 num_examples: 509 - name: test num_bytes: 10209711.0 num_examples: 360 download_size: 83863293 dataset_size: 81276019.0 - config_name: sv-SE_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 48298330.64 num_examples: 2160 - name: validation num_bytes: 32544646.416 num_examples: 1349 - name: test num_bytes: 46894324.615 num_examples: 1595 download_size: 121860373 dataset_size: 127737301.671 - config_name: ta_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 47757197.616 num_examples: 1358 - name: validation num_bytes: 13670695.0 num_examples: 384 - name: test num_bytes: 29891516.0 num_examples: 786 download_size: 87791516 dataset_size: 91319408.616 - config_name: tr_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: train num_bytes: 119299427.798 num_examples: 3966 - name: validation num_bytes: 52552534.232 num_examples: 1624 - name: test num_bytes: 59106253.862 num_examples: 1629 download_size: 224018260 dataset_size: 230958215.89200002 - config_name: zh-CN_en features: - name: client_id dtype: string - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: sentence dtype: string - name: translation dtype: string - name: id dtype: string splits: - name: validation num_bytes: 231018998.33 num_examples: 4843 - name: test num_bytes: 243850956.45 num_examples: 4898 - name: train num_bytes: 341425113.6 num_examples: 7085 download_size: 766660661 dataset_size: 816295068.38 configs: - config_name: ar_en data_files: - split: train path: ar_en/train-* - split: validation path: ar_en/validation-* - split: test path: ar_en/test-* - config_name: ca_en data_files: - split: train path: ca_en/train-* - split: validation path: ca_en/validation-* - split: test path: ca_en/test-* - config_name: cy_en data_files: - split: train path: cy_en/train-* - split: validation path: cy_en/validation-* - split: test path: cy_en/test-* - config_name: de_en data_files: - split: train path: de_en/train-* - split: validation path: de_en/validation-* - split: test path: de_en/test-* - config_name: en_ar data_files: - split: train path: en_ar/train-* - split: validation path: en_ar/validation-* - split: test path: en_ar/test-* - config_name: en_ca data_files: - split: train path: en_ca/train-* - split: validation path: en_ca/validation-* - split: test path: en_ca/test-* - config_name: en_cy data_files: - split: train path: en_cy/train-* - split: validation path: en_cy/validation-* - split: test path: en_cy/test-* - config_name: en_de data_files: - split: train path: en_de/train-* - split: validation path: en_de/validation-* - split: test path: en_de/test-* - config_name: en_et data_files: - split: train path: en_et/train-* - split: validation path: en_et/validation-* - split: test path: en_et/test-* - config_name: en_fa data_files: - split: train path: en_fa/train-* - split: validation path: en_fa/validation-* - split: test path: en_fa/test-* - config_name: en_id data_files: - split: train path: en_id/train-* - split: validation path: en_id/validation-* - split: test path: en_id/test-* - config_name: en_ja data_files: - split: train path: en_ja/train-* - split: validation path: en_ja/validation-* - split: test path: en_ja/test-* - config_name: en_lv data_files: - split: train path: en_lv/train-* - split: validation path: en_lv/validation-* - split: test path: en_lv/test-* - config_name: en_mn data_files: - split: train path: en_mn/train-* - split: validation path: en_mn/validation-* - split: test path: en_mn/test-* - config_name: en_sl data_files: - split: train path: en_sl/train-* - split: validation path: en_sl/validation-* - split: test path: en_sl/test-* - config_name: en_sv-SE data_files: - split: train path: en_sv-SE/train-* - split: validation path: en_sv-SE/validation-* - split: test path: en_sv-SE/test-* - config_name: en_ta data_files: - split: train path: en_ta/train-* - split: validation path: en_ta/validation-* - split: test path: en_ta/test-* - config_name: en_tr data_files: - split: train path: en_tr/train-* - split: validation path: en_tr/validation-* - split: test path: en_tr/test-* - config_name: en_zh-CN data_files: - split: train path: en_zh-CN/train-* - split: validation path: en_zh-CN/validation-* - split: test path: en_zh-CN/test-* - config_name: es_en data_files: - split: validation path: es_en/validation-* - split: test path: es_en/test-* - split: train path: es_en/train-* - config_name: et_en data_files: - split: train path: et_en/train-* - split: validation path: et_en/validation-* - split: test path: et_en/test-* - config_name: fa_en data_files: - split: train path: fa_en/train-* - split: validation path: fa_en/validation-* - split: test path: fa_en/test-* - config_name: fr_en data_files: - split: validation path: fr_en/validation-* - split: test path: fr_en/test-* - split: train path: fr_en/train-* - config_name: id_en data_files: - split: train path: id_en/train-* - split: validation path: id_en/validation-* - split: test path: id_en/test-* - config_name: it_en data_files: - split: train path: it_en/train-* - split: validation path: it_en/validation-* - split: test path: it_en/test-* - config_name: ja_en data_files: - split: train path: ja_en/train-* - split: validation path: ja_en/validation-* - split: test path: ja_en/test-* - config_name: lv_en data_files: - split: train path: lv_en/train-* - split: validation path: lv_en/validation-* - split: test path: lv_en/test-* - config_name: mn_en data_files: - split: train path: mn_en/train-* - split: validation path: mn_en/validation-* - split: test path: mn_en/test-* - config_name: nl_en data_files: - split: train path: nl_en/train-* - split: validation path: nl_en/validation-* - split: test path: nl_en/test-* - config_name: pt_en data_files: - split: train path: pt_en/train-* - split: validation path: pt_en/validation-* - split: test path: pt_en/test-* - config_name: ru_en data_files: - split: train path: ru_en/train-* - split: validation path: ru_en/validation-* - split: test path: ru_en/test-* - config_name: sl_en data_files: - split: train path: sl_en/train-* - split: validation path: sl_en/validation-* - split: test path: sl_en/test-* - config_name: sv-SE_en data_files: - split: train path: sv-SE_en/train-* - split: validation path: sv-SE_en/validation-* - split: test path: sv-SE_en/test-* - config_name: ta_en data_files: - split: train path: ta_en/train-* - split: validation path: ta_en/validation-* - split: test path: ta_en/test-* - config_name: tr_en data_files: - split: train path: tr_en/train-* - split: validation path: tr_en/validation-* - split: test path: tr_en/test-* - config_name: zh-CN_en data_files: - split: validation path: zh-CN_en/validation-* - split: test path: zh-CN_en/test-* - split: train path: zh-CN_en/train-* --- This is a partial copy of [CoVoST2](https://huggingface.co/datasets/facebook/covost2) dataset. The main difference is that the audio data is included in the dataset, which makes usage easier and allows browsing the samples using HF Dataset Viewer. The limitation of this method is that all audio samples of the `EN_XX` subsets are duplicated, as such the size of the dataset is larger. As such, not all the data is included: Only the `validation` and `test` subsets are available. From the `XX_EN` subsets, only `fr`, `es`, and `zh-CN` are included.

HAERAE-HUB/KMMLU-HARD

HAERAE-HUB

"2024-03-09T23:46:06Z"

14,798

8

[ "task_categories:question-answering", "language:ko", "license:cc-by-nd-4.0", "size_categories:1K<n<10K", "format:csv", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "arxiv:2402.11548", "region:us", "haerae", "mmlu" ]

[ "question-answering" ]

"2024-01-12T05:49:07Z"

--- configs: - config_name: maritime_engineering data_files: - split: dev path: data/maritime_engineering-dev.csv - split: test path: data/maritime_engineering-hard-test.csv - config_name: materials_engineering data_files: - split: dev path: data/materials_engineering-dev.csv - split: test path: data/materials_engineering-hard-test.csv - config_name: railway_and_automotive_engineering data_files: - split: dev path: data/railway_and_automotive_engineering-dev.csv - split: test path: data/railway_and_automotive_engineering-hard-test.csv - config_name: biology data_files: - split: dev path: data/biology-dev.csv - split: test path: data/biology-hard-test.csv - config_name: public_safety data_files: - split: dev path: data/public_safety-dev.csv - split: test path: data/public_safety-hard-test.csv - config_name: criminal_law data_files: - split: dev path: data/criminal_law-dev.csv - split: test path: data/criminal_law-hard-test.csv - config_name: information_technology data_files: - split: dev path: data/information_technology-dev.csv - split: test path: data/information_technology-hard-test.csv - config_name: geomatics data_files: - split: dev path: data/geomatics-dev.csv - split: test path: data/geomatics-hard-test.csv - config_name: management data_files: - split: dev path: data/management-dev.csv - split: test path: data/management-hard-test.csv - config_name: math data_files: - split: dev path: data/math-dev.csv - split: test path: data/math-hard-test.csv - config_name: accounting data_files: - split: dev path: data/accounting-dev.csv - split: test path: data/accounting-hard-test.csv - config_name: chemistry data_files: - split: dev path: data/chemistry-dev.csv - split: test path: data/chemistry-hard-test.csv - config_name: nondestructive_testing data_files: - split: dev path: data/nondestructive_testing-dev.csv - split: test path: data/nondestructive_testing-hard-test.csv - config_name: computer_science data_files: - split: dev path: data/computer_science-dev.csv - split: test path: data/computer_science-hard-test.csv - config_name: ecology data_files: - split: dev path: data/ecology-dev.csv - split: test path: data/ecology-hard-test.csv - config_name: health data_files: - split: dev path: data/health-dev.csv - split: test path: data/health-hard-test.csv - config_name: political_science_and_sociology data_files: - split: dev path: data/political_science_and_sociology-dev.csv - split: test path: data/political_science_and_sociology-hard-test.csv - config_name: patent data_files: - split: dev path: data/patent-dev.csv - split: test path: data/patent-hard-test.csv - config_name: electrical_engineering data_files: - split: dev path: data/electrical_engineering-dev.csv - split: test path: data/electrical_engineering-hard-test.csv - config_name: electronics_engineering data_files: - split: dev path: data/electronics_engineering-dev.csv - split: test path: data/electronics_engineering-hard-test.csv - config_name: korean_history data_files: - split: dev path: data/korean_history-dev.csv - split: test path: data/korean_history-hard-test.csv - config_name: gas_technology_and_engineering data_files: - split: dev path: data/gas_technology_and_engineering-dev.csv - split: test path: data/gas_technology_and_engineering-hard-test.csv - config_name: machine_design_and_manufacturing data_files: - split: dev path: data/machine_design_and_manufacturing-dev.csv - split: test path: data/machine_design_and_manufacturing-hard-test.csv - config_name: chemical_engineering data_files: - split: dev path: data/chemical_engineering-dev.csv - split: test path: data/chemical_engineering-hard-test.csv - config_name: telecommunications_and_wireless_technology data_files: - split: dev path: data/telecommunications_and_wireless_technology-dev.csv - split: test path: data/telecommunications_and_wireless_technology-hard-test.csv - config_name: food_processing data_files: - split: dev path: data/food_processing-dev.csv - split: test path: data/food_processing-hard-test.csv - config_name: social_welfare data_files: - split: dev path: data/social_welfare-dev.csv - split: test path: data/social_welfare-hard-test.csv - config_name: real_estate data_files: - split: dev path: data/real_estate-dev.csv - split: test path: data/real_estate-hard-test.csv - config_name: marketing data_files: - split: dev path: data/marketing-dev.csv - split: test path: data/marketing-hard-test.csv - config_name: mechanical_engineering data_files: - split: dev path: data/mechanical_engineering-dev.csv - split: test path: data/mechanical_engineering-hard-test.csv - config_name: fashion data_files: - split: dev path: data/fashion-dev.csv - split: test path: data/fashion-hard-test.csv - config_name: psychology data_files: - split: dev path: data/psychology-dev.csv - split: test path: data/psychology-hard-test.csv - config_name: taxation data_files: - split: dev path: data/taxation-dev.csv - split: test path: data/taxation-hard-test.csv - config_name: environmental_science data_files: - split: dev path: data/environmental_science-dev.csv - split: test path: data/environmental_science-hard-test.csv - config_name: refrigerating_machinery data_files: - split: dev path: data/refrigerating_machinery-dev.csv - split: test path: data/refrigerating_machinery-hard-test.csv - config_name: education data_files: - split: dev path: data/education-dev.csv - split: test path: data/education-hard-test.csv - config_name: industrial_engineer data_files: - split: dev path: data/industrial_engineer-dev.csv - split: test path: data/industrial_engineer-hard-test.csv - config_name: civil_engineering data_files: - split: dev path: data/civil_engineering-dev.csv - split: test path: data/civil_engineering-hard-test.csv - config_name: energy_management data_files: - split: dev path: data/energy_management-dev.csv - split: test path: data/energy_management-hard-test.csv - config_name: law data_files: - split: dev path: data/law-dev.csv - split: test path: data/law-hard-test.csv - config_name: agricultural_sciences data_files: - split: dev path: data/agricultural_sciences-dev.csv - split: test path: data/agricultural_sciences-hard-test.csv - config_name: interior_architecture_and_design data_files: - split: dev path: data/interior_architecture_and_design-dev.csv - split: test path: data/interior_architecture_and_design-hard-test.csv - config_name: aviation_engineering_and_maintenance data_files: - split: dev path: data/aviation_engineering_and_maintenance-dev.csv - split: test path: data/aviation_engineering_and_maintenance-hard-test.csv - config_name: construction data_files: - split: dev path: data/construction-dev.csv - split: test path: data/construction-hard-test.csv - config_name: economics data_files: - split: dev path: data/economics-dev.csv - split: test path: data/economics-hard-test.csv license: cc-by-nd-4.0 task_categories: - question-answering language: - ko tags: - haerae - mmlu size_categories: - 100K<n<1M --- ### KMMLU (Korean-MMLU) We propose KMMLU, a new Korean benchmark with 35,030 expert-level multiple-choice questions across 45 subjects ranging from humanities to STEM. Unlike previous Korean benchmarks that are translated from existing English benchmarks, KMMLU is collected from original Korean exams, capturing linguistic and cultural aspects of the Korean language. We test 26 publically available and proprietary LLMs, identifying significant room for improvement. The best publicly available model achieves 50.54% on KMMLU, far below the average human performance of 62.6%. This model was primarily trained for English and Chinese, not Korean. Current LLMs tailored to Korean, such as Polyglot-Ko, perform far worse. Surprisingly, even the most capable proprietary LLMs, e.g., GPT-4 and HyperCLOVA X, achieve 59.95% and 53.40%, respectively. This suggests that further work is needed to improve Korean LLMs, and KMMLU offers the right tool to track this progress. We make our dataset publicly available on the Hugging Face Hub and integrate the benchmark into EleutherAI's Language Model Evaluation Harness. Link to Paper: [KMMLU: Measuring Massive Multitask Language Understanding in Korean](https://arxiv.org/abs/2402.11548) ### KMMLU Statistics | Category | # Questions | |------------------------------|-------------| | **Prerequisites** | | | None | 59,909 | | 1 Prerequisite Test | 12,316 | | 2 Prerequisite Tests | 776 | | 2+ Years of Experience | 65,135 | | 4+ Years of Experience | 98,678 | | 9+ Years of Experience | 6,963 | | **Question Type** | | | Positive | 207,030 | | Negation | 36,777 | | **Split** | | | Train | 208,522 | | Validation | 225 | | Test | 35,030 | | **Total** | 243,777 | ### Categories To reimplement the categories in the paper, refer to the following: ``` supercategories = { "accounting": "HUMSS", "agricultural_sciences": "Other", "aviation_engineering_and_maintenance": "Applied Science", "biology": "STEM", "chemical_engineering": "STEM", "chemistry": "STEM", "civil_engineering": "STEM", "computer_science": "STEM", "construction": "Other", "criminal_law": "HUMSS", "ecology": "STEM", "economics": "HUMSS", "education": "HUMSS", "electrical_engineering": "STEM", "electronics_engineering": "Applied Science", "energy_management": "Applied Science", "environmental_science": "Applied Science", "fashion": "Other", "food_processing": "Other", "gas_technology_and_engineering": "Applied Science", "geomatics": "Applied Science", "health": "Other", "industrial_engineer": "Applied Science", "information_technology": "STEM", "interior_architecture_and_design": "Other", "law": "HUMSS", "machine_design_and_manufacturing": "Applied Science", "management": "HUMSS", "maritime_engineering": "Applied Science", "marketing": "Other", "materials_engineering": "STEM", "mechanical_engineering": "STEM", "nondestructive_testing": "Applied Science", "patent": "Other", "political_science_and_sociology": "HUMSS", "psychology": "HUMSS", "public_safety": "Other", "railway_and_automotive_engineering": "Applied Science", "real_estate": "Other", "refrigerating_machinery": "Other", "social_welfare": "HUMSS", "taxation": "HUMSS", "telecommunications_and_wireless_technology": "Applied Science", "korean_history": "HUMSS", "math": "STEM" } ``` ### Point of Contact For any questions contact us via the following email:) ``` [email protected] ```

amitness/logits-mt-it-en-128

amitness

"2023-09-27T10:27:21Z"

14,792

0

[ "size_categories:10M<n<100M", "format:parquet", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]

null

"2023-09-25T19:22:48Z"

--- configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* dataset_info: features: - name: input_ids sequence: int32 - name: token_type_ids sequence: int8 - name: attention_mask sequence: int8 - name: labels sequence: int64 - name: teacher_logits sequence: sequence: float64 - name: teacher_indices sequence: sequence: int64 - name: teacher_mask_indices sequence: int64 splits: - name: train num_bytes: 184467361976 num_examples: 40721350 - name: test num_bytes: 32556394204 num_examples: 7186121 download_size: 0 dataset_size: 217023756180 --- # Dataset Card for "logits-mt-it-en-128" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

distil-whisper/librispeech_long

distil-whisper

"2023-11-02T14:22:54Z"

14,753

2

[ "size_categories:n<1K", "format:parquet", "modality:audio", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]

null

"2023-11-02T14:22:51Z"

--- dataset_info: config_name: clean features: - name: audio dtype: audio splits: - name: validation num_bytes: 1998609.0 num_examples: 1 download_size: 1984721 dataset_size: 1998609.0 configs: - config_name: clean data_files: - split: validation path: clean/validation-* --- # Dataset Card for "librispeech_long" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

alvations/c4p0-x1-es-en

alvations

"2024-03-24T03:52:27Z"

14,723

0

[ "size_categories:n<1K", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]

null

"2024-03-23T10:16:40Z"

--- dataset_info: features: - name: source dtype: string - name: target dtype: string - name: target_backto_source dtype: string - name: raw_target list: - name: generated_text dtype: string - name: raw_target_backto_source list: - name: generated_text dtype: string - name: prompt dtype: string - name: reverse_prompt dtype: string - name: source_langid dtype: string - name: target_langid dtype: string - name: target_backto_source_langid dtype: string - name: doc_id dtype: int64 - name: sent_id dtype: int64 - name: timestamp dtype: timestamp[us] - name: url dtype: string - name: doc_hash dtype: string splits: - name: train num_bytes: 3583 num_examples: 4 download_size: 14029 dataset_size: 3583 configs: - config_name: default data_files: - split: train path: d595973734f0a325/train-* ---

KShivendu/dbpedia-entities-openai-1M

KShivendu

"2024-02-19T08:24:43Z"

14,680

20

[ "task_categories:feature-extraction", "language:en", "license:mit", "size_categories:1M<n<10M", "format:parquet", "modality:text", "modality:timeseries", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]

[ "feature-extraction" ]

"2023-06-20T22:29:43Z"

--- license: mit dataset_info: features: - name: _id dtype: string - name: title dtype: string - name: text dtype: string - name: openai sequence: float32 splits: - name: train num_bytes: 12383152 num_examples: 1000000 download_size: 12383152 dataset_size: 1000000 language: - en task_categories: - feature-extraction pretty_name: OpenAI 1M with DBPedia Entities size_categories: - 1M<n<10M --- 1M OpenAI Embeddings -- 1536 dimensions Created: June 2023. Text used for Embedding: title (string) + text (string) Embedding Model: text-embedding-ada-002 First used for the pgvector vs VectorDB (Qdrant) benchmark: https://nirantk.com/writing/pgvector-vs-qdrant/ ### Future work We are planning to take this up to 10M (and possibly 100M) vectors. Contact [@KShivendu_](https://twitter.com/KShivendu_) on Twitter or mail to [email protected] if you want to help :) ### Credits: This dataset was generated from the first 1M entries of https://huggingface.co/datasets/BeIR/dbpedia-entity

hoskinson-center/proof-pile

hoskinson-center

"2023-08-19T03:24:11Z"

14,644

59

[ "task_categories:text-generation", "task_ids:language-modeling", "annotations_creators:no-annotation", "language_creators:found", "multilinguality:monolingual", "language:en", "license:apache-2.0", "size_categories:100K<n<1M", "modality:text", "library:datasets", "library:mlcroissant", "region:us", "math", "mathematics", "formal-mathematics" ]

[ "text-generation" ]

"2022-08-08T20:57:56Z"

--- annotations_creators: - no-annotation language: - en language_creators: - found license: [apache-2.0] multilinguality: - monolingual pretty_name: proof-pile size_categories: [] source_datasets: [] tags: - math - mathematics - formal-mathematics task_categories: - text-generation task_ids: - language-modeling --- # Dataset Description The `proof-pile` is a 13GB pre-training dataset of mathematical text that comprises 8.3 billion tokens (using the `gpt-neox` tokenizer). Models trained on this dataset are coming soon :) The dataset is composed of diverse sources of both informal and formal mathematics, namely - ArXiv.math (10GB) - Open-source math textbooks (50MB) - Formal mathematics libraries (500MB) - Lean mathlib and other Lean repositories - Isabelle AFP - Coq mathematical components and other Coq repositories - HOL Light - set.mm - Mizar Mathematical Library - Math Overflow and Math Stack Exchange (2.5GB) - Wiki-style sources (50MB) - ProofWiki - Wikipedia math articles - MATH dataset (6MB) The construction of the dataset is reproducible using the code and instructions in the [proof-pile Github repo](https://github.com/zhangir-azerbayev/proof-pile). # Supported Tasks This dataset is intended to be used for pre-training and fine-tuning language models. We envision models trained on the `proof-pile` will have many downstream applications, including informal quantitative reasoning, formal theorem proving, semantic search for formal mathematics, and autoformalization. # Languages All informal mathematics in the `proof-pile` is written in English and LaTeX (arXiv articles in other languages are filtered out using [languagedetect](https://github.com/shuyo/language-detection/blob/wiki/ProjectHome.md)). Formal theorem proving languages represented in this dataset are Lean 3, Isabelle, Coq, HOL Light, Metamath, and Mizar. # Evaluation The version of `set.mm` in this dataset has 10% of proofs replaced with the `?` character in order to preserve a validation and test set for Metamath provers pre-trained on the `proof-pile`. The precise split can be found here: [validation](https://github.com/zhangir-azerbayev/mm-extract/blob/main/valid_decls.json) and [test](https://github.com/zhangir-azerbayev/mm-extract/blob/main/test_decls.json). The Lean mathlib commit used in this dataset is `6313863`. Theorems created in subsequent commits can be used for evaluating Lean theorem provers. This dataset contains only the training set of the [MATH dataset](https://github.com/hendrycks/math). However, because this dataset contains ProofWiki, the Stacks Project, Trench's Analysis, and Stein's Number Theory, models trained on it cannot be evaluated on the [NaturalProofs dataset](https://github.com/wellecks/naturalproofs). # Data Preprocessing This section describes any significant filtering and transformations made to various subsets of the data. **arXiv.math.** The arXiv.math dataset is large, heterogeneous, and contains a great deal of noise. We used the following heuristics when choosing which files from arXiv.math source folders to include in the dataset: - Keep only files with a `.tex` extension. - Only include files that use either a `utf-8/16/32` or `latin-1` text encoding. - Discard files that do not contain a part, chapter, section, sub...section, paragraph, or subparagraph heading. - Delete files that contain the keyword `gnuplot`. Gnuplot-latex is an old command line utility that generates blocks of entirely unintelligible source. - Include only articles in English, as determined by the [langdetect library](https://pypi.org/project/langdetect/). \n", "\n", - Exclude files shorter than 280 characters (characters counted after substring removal described below). In addition, we apply the following transformations to arXiv.math texts: - Delete everything outside of `\begin{document}` and `\end{document}`. - Delete everything including or after `\Refs`, `\begin{thebibliography}`, or `\begin{bibdiv}` - Delete comments. - Any more than three consecutive newlines are replaced by three consecutive newlines. In [this notebook](https://github.com/zhangir-azerbayev/proof-pile/blob/main/analysis/arxiv_noisedetection.ipynb), we provide an analysis of the prevalence of noisy documents in the arXiv.math subset of the proof-pile. **Stack Exchange.** We only include questions that have at least 5 upvotes and an answer. We format Stack Exchange posts as follows ``` QUESTION [{num_upvotes} upvotes]: {text of question} REPLY [{num_upvotes} votes]: {text of reply} REPLY [{num_upvotes} votes]: {text of reply} . . . ``` **set.mm.** We converted `set.mm` into human-readable form by following the instructions in the [mm-extract repo](https://github.com/zhangir-azerbayev/mm-extract) ## Contributions Authors: Zhangir Azerbayev, Edward Ayers, Bartosz Piotrowski. We would like to thank Jeremy Avigad, Albert Jiang, and Wenda Li for their invaluable guidance, and the Hoskinson Center for Formal Mathematics for its support.

MBZUAI/Bactrian-X

MBZUAI

"2023-05-27T12:54:05Z"

14,623

116

[ "task_categories:text-generation", "language:af", "language:ar", "language:az", "language:bn", "language:cs", "language:de", "language:en", "language:es", "language:et", "language:fi", "language:fr", "language:gl", "language:gu", "language:he", "language:hi", "language:hr", "language:id", "language:it", "language:ja", "language:ka", "language:kk", "language:km", "language:ko", "language:lt", "language:lv", "language:mk", "language:ml", "language:mn", "language:mr", "language:my", "language:ne", "language:nl", "language:pl", "language:ps", "language:pt", "language:ro", "language:ru", "language:si", "language:sl", "language:sv", "language:sw", "language:ta", "language:te", "language:th", "language:tl", "language:tr", "language:uk", "language:ur", "language:vi", "language:xh", "language:zh", "license:cc-by-nc-4.0", "size_categories:1M<n<10M", "modality:text", "library:datasets", "library:mlcroissant", "arxiv:2008.00401", "arxiv:2305.15011", "region:us", "instruction-finetuning", "multilingual" ]

[ "text-generation" ]

"2023-04-22T12:42:39Z"

--- license: cc-by-nc-4.0 task_categories: - text-generation language: - af - ar - az - bn - cs - de - en - es - et - fi - fr - gl - gu - he - hi - hr - id - it - ja - ka - kk - km - ko - lt - lv - mk - ml - mn - mr - my - ne - nl - pl - ps - pt - ro - ru - si - sl - sv - sw - ta - te - th - tl - tr - uk - ur - vi - xh - zh tags: - instruction-finetuning - multilingual pretty_name: Bactrian-X --- # Dataset Card for "Bactrian-X" ## Table of Contents - [Dataset Description](#a-dataset-description) - [Dataset Summary](#dataset-summary) - [Languages](#languages) - [Dataset Structure](#b-dataset-structure) - [Data Fields](#data-fields) - [Data Instances](#data-instances) - [Data in 52 Languages](#data-in-52-languages) - [Dataset Creation](#c-dataset-creation) - [Considerations for Using the Data](#d-considerations-for-using-the-data) - [Additional Information](#e-additional-information) ## A. Dataset Description - **Homepage:** https://github.com/mbzuai-nlp/Bactrian-X - **Repository:** https://huggingface.co/datasets/MBZUAI/Bactrian-X - **Paper:** to-be-soon released ### Dataset Summary <h3 align="center"> <img src="https://raw.githubusercontent.com/fajri91/eval_picts/master/BactrianX_dataset.jpg" width="950" align="center"> </h3> The Bactrain-X dataset is a collection of 3.4M instruction-response pairs in 52 languages, that are obtained by translating 67K English instructions ([alpaca-52k](https://github.com/tatsu-lab/stanford_alpaca) + [dolly-15k](https://github.com/databrickslabs/dolly/tree/master/data)) into 51 languages using Google Translate API. The translated instructions are then fed to ChatGPT (`gpt-3.5-turbo`) to obtain its natural responses, resulting in 3.4M instruction-response pairs in 52 languages (52 languages x 67k instances = 3.4M instances). ### Languages We follow 52 languages of [mBART-50](https://arxiv.org/abs/2008.00401), with details can be found [below](#data-in-52-languages). ## B. Dataset Structure ### Data Fields The data fields are as follows: * `instruction`: describes the task the model should perform. Each of the 67K instructions is unique. * `input`: optional context or input for the task. For example, when the instruction is "Summarize the following article", the input is the article. Around 40% of the examples have an input. * `output`: the answer to the instruction as generated by `gpt-3.5-turbo`. * `id`: the unique index for each data piece in a specific language. The same `id` across splits corresponds to the same original English data. ### Data Instances An example in `en` looks as follows. ```json { "instruction": "What is the main idea of this text?", "input": "The robotics industry has become one of the fastest growing sectors in today’s economy. Robotics technology is being applied in various industries and applications, such as manufacturing, healthcare, and defense.", "output": "The main idea of the text is that the robotics industry is rapidly growing and its technology is being used in many different industries and applications.", "id": "alpaca-107" } ``` An example in `ar` looks as follows. ```json { "instruction": "قم بالوصول إلى إعدادات المتصفح الافتراضية على جهاز الكمبيوتر.", "input": "", "output": "لا يمكن لي كمساعد افتراضي القيام بهذه المهمة كونها تحتاج إلى الوصول إلى الجهاز المادي. يرجى الرجوع إلى دليل المستخدم للكمبيوتر الخاص بك أو البحث على الإنترنت لمعرفة كيفية الوصول إلى إعدادات المتصفح الافتراضية على جهاز الكمبيوتر الخاص بك.", "id": "alpaca-41997" } ``` An example in `id` looks as follows. ```json { "instruction": "Berapa banyak angka penting yang harus digunakan untuk nilai 0,000187?", "input": "", "output": "Ada tiga angka penting dalam nilai 0,000187.", "id": "alpaca-40382" } ``` An example in `de` looks as follows. ```json { "instruction": "Komponieren Sie ein Musikstück mit einem Titel, der Trauer bezeichnet.", "input": "", "output": ""Schmerzendes Herz"\n\nDas Stück beginnt mit einer langsamen, traurigen Melodie, gespielt von einem Solo-Violoncello. Die Harmonien, die von einem Klavier begleitet werden, sind durcheinander und dissonant, um ein Gefühl von Schmerz und Trauer zu vermitteln.\n\nIm Laufe des Stücks treten andere Instrumente ein, wie Streicher, Flöte und Oboe, um die Melodie zu unterstützen und zu intensivieren. Der Rhythmus bleibt langsam und schwerfällig, um die Schwere des Schmerzes darzustellen.\n\nIn der Mitte des Stücks gibt es einen Höhepunkt, wo die Melodie und Harmonien sich verdichten und ein Gefühl von Überwältigung erzeugen. Der Solo-Violoncello spielt eine traurige und schnelle Phrase, die die Verzweiflung und Isolation des Protagonisten ausdrückt.\n\nDas Stück endet mit einer Wiederholung der ersten Melodie, gespielt von einem Solo-Klavier, während die anderen Instrumente auslaufen. Die Harmonien werden jedoch weicher und sanfter, um einen Hauch von Hoffnung zu vermitteln, dass der Schmerz langsam vergeht.", "id": "alpaca-33619" } ``` An example in `fr` looks as follows. ```json { "instruction": "Les Ceanothus ont-ils des racines peu profondes ?", "input": "", "output": "En tant qu'IA, je ne peux pas répondre avec une certitude absolue, mais voici des informations générales sur les racines de Ceanothus : \n\nLes Ceanothus ont tendance à avoir un système racinaire étendu et peu profond. Les racines peuvent s'étaler jusqu'à 4 à 6 fois la taille de la plante et s'étendre à environ 60 à 90 cm de profondeur. Cependant, cela peut varier en fonction du type de sol et de la variété de Ceanothus. Certaines variétés de Ceanothus pourraient avoir des racines plus profondes si les conditions s'y prêtent.", "id": "dolly-10940" } ``` ### Data in 52 Languages | No | Languages | Code | Train | | ---|---------------- | ----- | ----- | | 1 | [Afrikaans](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/af) | af_ZA | 67017 | | 2 | [Arabic](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/ar) | ar_AR | 67017 | | 3 | [Azerbaijani](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/az) | az_AZ | 67017 | | 4 | [Bengali](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/bn) | bn_IN | 67017 | | 5 | [Czech](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/cs) | cs_CZ | 67017 | | 6 | [German](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/de) | de_DE | 67017 | | 7 | [English](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/en) | en_XX | 67017 | | 8 | [Spanish](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/es) | es_XX | 67017 | | 9 | [Estonian](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/et) | et_EE | 67017 | | 10 | [Persian](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/fa) | fa_IR | 67017 | | 11 | [Finnish](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/fi) | fi_FI | 67017 | | 12 | [French](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/fr) | fr_XX | 67017 | | 13 | [Galician](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/gl) | gl_ES | 67017 | | 14 | [Gujarati](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/gu) | gu_IN | 67017 | | 15 | [Hebrew](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/he) | he_IL | 67017 | | 16 | [Hindi](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/hi) | hi_IN | 67017 | | 17 | [Croatian](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/hr) | hr_HR | 67017 | | 18 | [Indonesian](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/id) | id_ID | 67017 | | 19 | [Italian](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/it) | it_IT | 67017 | | 20 | [Japanese](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/ja) | ja_XX | 67017 | | 21 | [Georgian](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/ka) | ka_GE | 67017 | | 22 | [Kazakh](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/kk) | kk_KZ | 67017 | | 23 | [Khmer](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/km) | km_KH | 67017 | | 24 | [Korean](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/ko) | ko_KR | 67017 | | 25 | [Lithuanian](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/lt) | lt_LT | 67017 | | 26 | [Latvian](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/lv) | lv_LV | 67017 | | 27 | [Macedonian](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/mk) | mk_MK | 67017 | | 28 | [Malayalam](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/ml) | ml_IN | 67017 | | 29 | [Mongolian](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/mn) | mn_MN | 67017 | | 30 | [Marathi](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/mr) | mr_IN | 67017 | | 31 | [Burmese](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/my) | my_MM | 67017 | | 32 | [Nepali](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/ne) | ne_NP | 67017 | | 33 | [Dutch](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/nl) | nl_XX | 67017 | | 34 | [Polish](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/pl) | pl_PL | 67017 | | 35 | [Pashto](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/ps) | ps_AF | 67017 | | 36 | [Portuguese](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/pt) | pt_XX | 67017 | | 37 | [Romanian](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/ro) | ro_RO | 67017 | | 38 | [Russian](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/ru) | ru_RU | 67017 | | 39 | [Sinhala](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/si) | si_LK | 67017 | | 40 | [Slovene](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/sl) | sl_SI | 67017 | | 41 | [Swedish](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/sv) | sv_SE | 67017 | | 42 | [Swahili](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/sw) | sw_KE | 67017 | | 43 | [Tamil](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/ta) | ta_IN | 67017 | | 44 | [Telugu](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/te) | te_IN | 67017 | | 45 | [Thai](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/th) | th_TH | 67017 | | 46 | [Tagalog](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/tl) | tl_XX | 67017 | | 47 | [Turkish](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/tr) | tr_TR | 67017 | | 48 | [Ukrainian](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/uk) | uk_UA | 67017 | | 49 | [Urdu](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/ur) | ur_PK | 67017 | | 50 | [Vietnamese](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/vi) | vi_VN | 67017 | | 51 | [Xhosa](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/xh) | xh_ZA | 67017 | | 52 | [Chinese](https://huggingface.co/datasets/MBZUAI/Bactrian-X/viewer/zh) | zh_CN | 67017 | ## C. Dataset Creation 1. English Instructions: The English instuctions are obtained from [alpaca-53k](https://github.com/tatsu-lab/stanford_alpaca), and [dolly-15k](https://github.com/databrickslabs/dolly/tree/master/data). 2. Instruction Translation: The instructions (and inputs) are translated into 51 languages using Google Translation API (conducted on April 2023). 3. Output Generation: We generate output from `gpt-3.5-turbo` for each language (conducted on April 2023). ## D. Considerations for Using the Data ### Social Impact of Dataset NLP for everyone: this dataset helps to democratize the cutting-edge instruction-following models in 52 languages. This dataset also allows the first experiment on the multilingual LoRA-based LLaMA model. ### Discussion of Biases (1) Translation bias; (2) Potential English-culture bias in the translated dataset. ### Other Known Limitations The `Bactrian-X` data is generated by a language model (`gpt-3.5-turbo`) and inevitably contains some errors or biases. We encourage users to use this data with caution and propose new methods to filter or improve the imperfections. ## E. Additional Information ### Dataset Curators [Haonan Li](https://haonan-li.github.io/) and [Fajri Koto](http://www.fajrikoto.com) ### Licensing Information The dataset is available under the [Creative Commons NonCommercial (CC BY-NC 4.0)](https://creativecommons.org/licenses/by-nc/4.0/legalcode). ### Citation Information ``` @misc{li2023bactrianx, title={Bactrian-X : A Multilingual Replicable Instruction-Following Model with Low-Rank Adaptation}, author={Haonan Li and Fajri Koto and Minghao Wu and Alham Fikri Aji and Timothy Baldwin}, year={2023}, eprint={2305.15011}, archivePrefix={arXiv}, primaryClass={cs.CL} } ``` ### Contributions Thanks to [@haonan-li](https://github.com/haonan-li), [@fajri91](https://github.com/fajri91) for adding this dataset.

qiaojin/PubMedQA

qiaojin

"2024-03-06T01:50:16Z"

14,569

204

[ "task_categories:question-answering", "task_ids:multiple-choice-qa", "annotations_creators:expert-generated", "annotations_creators:machine-generated", "language_creators:expert-generated", "multilinguality:monolingual", "source_datasets:original", "language:en", "license:mit", "size_categories:100K<n<1M", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "arxiv:1909.06146", "region:us" ]

[ "question-answering" ]

"2022-03-02T23:29:22Z"

--- annotations_creators: - expert-generated - machine-generated language_creators: - expert-generated language: - en license: - mit multilinguality: - monolingual size_categories: - 100K<n<1M - 10K<n<100K - 1K<n<10K source_datasets: - original task_categories: - question-answering task_ids: - multiple-choice-qa paperswithcode_id: pubmedqa pretty_name: PubMedQA config_names: - pqa_artificial - pqa_labeled - pqa_unlabeled dataset_info: - config_name: pqa_artificial features: - name: pubid dtype: int32 - name: question dtype: string - name: context sequence: - name: contexts dtype: string - name: labels dtype: string - name: meshes dtype: string - name: long_answer dtype: string - name: final_decision dtype: string splits: - name: train num_bytes: 443501057 num_examples: 211269 download_size: 233411194 dataset_size: 443501057 - config_name: pqa_labeled features: - name: pubid dtype: int32 - name: question dtype: string - name: context sequence: - name: contexts dtype: string - name: labels dtype: string - name: meshes dtype: string - name: reasoning_required_pred dtype: string - name: reasoning_free_pred dtype: string - name: long_answer dtype: string - name: final_decision dtype: string splits: - name: train num_bytes: 2088898 num_examples: 1000 download_size: 1075513 dataset_size: 2088898 - config_name: pqa_unlabeled features: - name: pubid dtype: int32 - name: question dtype: string - name: context sequence: - name: contexts dtype: string - name: labels dtype: string - name: meshes dtype: string - name: long_answer dtype: string splits: - name: train num_bytes: 125922964 num_examples: 61249 download_size: 66010017 dataset_size: 125922964 configs: - config_name: pqa_artificial data_files: - split: train path: pqa_artificial/train-* - config_name: pqa_labeled data_files: - split: train path: pqa_labeled/train-* - config_name: pqa_unlabeled data_files: - split: train path: pqa_unlabeled/train-* --- # Dataset Card for [Dataset Name] ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Homepage:** [PubMedQA homepage](https://pubmedqa.github.io/ ) - **Repository:** [PubMedQA repository](https://github.com/pubmedqa/pubmedqa) - **Paper:** [PubMedQA: A Dataset for Biomedical Research Question Answering](https://arxiv.org/abs/1909.06146) - **Leaderboard:** [PubMedQA: Leaderboard](https://pubmedqa.github.io/) ### Dataset Summary The task of PubMedQA is to answer research questions with yes/no/maybe (e.g.: Do preoperative statins reduce atrial fibrillation after coronary artery bypass grafting?) using the corresponding abstracts. ### Supported Tasks and Leaderboards The official leaderboard is available at: https://pubmedqa.github.io/. 500 questions in the `pqa_labeled` are used as the test set. They can be found at https://github.com/pubmedqa/pubmedqa. ### Languages English ## Dataset Structure ### Data Instances [More Information Needed] ### Data Fields [More Information Needed] ### Data Splits [More Information Needed] ## Dataset Creation ### Curation Rationale [More Information Needed] ### Source Data #### Initial Data Collection and Normalization [More Information Needed] #### Who are the source language producers? [More Information Needed] ### Annotations #### Annotation process [More Information Needed] #### Who are the annotators? [More Information Needed] ### Personal and Sensitive Information [More Information Needed] ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed] ### Discussion of Biases [More Information Needed] ### Other Known Limitations [More Information Needed] ## Additional Information ### Dataset Curators [More Information Needed] ### Licensing Information [More Information Needed] ### Citation Information [More Information Needed] ### Contributions Thanks to [@tuner007](https://github.com/tuner007) for adding this dataset.

zhoujt1994/HumanCellEpigenomeAtlas_sc_allc

zhoujt1994

"2025-03-17T13:52:53Z"

14,564

0

[ "license:mit", "region:us" ]

null

"2025-03-16T22:31:29Z"

--- license: mit ---

eduagarcia-temp/OSCAR-2301_meta

eduagarcia-temp

"2023-08-28T14:07:22Z"

14,552

0

[ "size_categories:10M<n<100M", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]

null

"2023-08-27T20:24:54Z"

--- dataset_info: features: - name: id dtype: int64 - name: text dtype: string - name: meta struct: - name: categories sequence: string - name: dedup struct: - name: exact_norm struct: - name: cluster_main_idx dtype: int64 - name: cluster_size dtype: int64 - name: exact_hash_idx dtype: int64 - name: is_duplicate dtype: bool - name: minhash struct: - name: cluster_main_idx dtype: int64 - name: cluster_size dtype: int64 - name: is_duplicate dtype: bool - name: minhash_idx dtype: int64 - name: harmful_pp dtype: float64 - name: identification struct: - name: label dtype: string - name: prob dtype: float64 - name: quality_warnings sequence: string - name: sentence_identifications list: - name: label dtype: string - name: prob dtype: float64 - name: tlsh dtype: string - name: warc_headers struct: - name: content-length dtype: int64 - name: content-type dtype: string - name: warc-block-digest dtype: string - name: warc-date dtype: string - name: warc-identified-content-language dtype: string - name: warc-record-id dtype: string - name: warc-refers-to dtype: string - name: warc-target-uri dtype: string - name: warc-type dtype: string splits: - name: train num_bytes: 127702717461 num_examples: 18031400 download_size: 40317121912 dataset_size: 127702717461 --- # Dataset Card for "OSCAR-2301_meta" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

OpenGVLab/OmniCorpus-CC

OpenGVLab

"2025-03-20T12:32:06Z"

14,513

16

[ "task_categories:image-to-text", "task_categories:visual-question-answering", "language:en", "license:cc-by-4.0", "size_categories:100M<n<1B", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "arxiv:2406.08418", "region:us" ]

[ "image-to-text", "visual-question-answering" ]

"2024-08-30T06:16:02Z"

--- language: - en license: cc-by-4.0 size_categories: - 100M<n<1B task_categories: - image-to-text - visual-question-answering dataset_info: - config_name: CC-MAIN-2013-20 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 19908676196 num_examples: 3878063 download_size: 9303464923 dataset_size: 19908676196 - config_name: CC-MAIN-2013-48 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 15282078925 num_examples: 3091537 download_size: 6965036866 dataset_size: 15282078925 - config_name: CC-MAIN-2014-10 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 7227087609 num_examples: 1390034 download_size: 3259239561 dataset_size: 7227087609 - config_name: CC-MAIN-2014-15 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 10106913108 num_examples: 1968361 download_size: 4567738362 dataset_size: 10106913108 - config_name: CC-MAIN-2014-23 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 7997621043 num_examples: 1455331 download_size: 3468852905 dataset_size: 7997621043 - config_name: CC-MAIN-2014-35 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 6228103779 num_examples: 1219200 download_size: 2849584613 dataset_size: 6228103779 - config_name: CC-MAIN-2014-41 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 8321822952 num_examples: 1573955 download_size: 3775989970 dataset_size: 8321822952 - config_name: CC-MAIN-2014-42 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 7732679416 num_examples: 1511931 download_size: 3505766162 dataset_size: 7732679416 - config_name: CC-MAIN-2014-49 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 4473311810 num_examples: 837735 download_size: 1982728919 dataset_size: 4473311810 - config_name: CC-MAIN-2014-52 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 7292722888 num_examples: 1304730 download_size: 2957626766 dataset_size: 7292722888 - config_name: CC-MAIN-2015-06 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 5775826679 num_examples: 1061940 download_size: 2462379667 dataset_size: 5775826679 - config_name: CC-MAIN-2015-11 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 6263650452 num_examples: 1129411 download_size: 2528026633 dataset_size: 6263650452 - config_name: CC-MAIN-2015-14 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 4524425019 num_examples: 885221 download_size: 1939222111 dataset_size: 4524425019 - config_name: CC-MAIN-2015-18 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 6195227565 num_examples: 1104115 download_size: 2634204322 dataset_size: 6195227565 - config_name: CC-MAIN-2015-22 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 7008276790 num_examples: 1290530 download_size: 2913627974 dataset_size: 7008276790 - config_name: CC-MAIN-2015-27 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 4320140953 num_examples: 784496 download_size: 1828575226 dataset_size: 4320140953 - config_name: CC-MAIN-2015-32 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 4952806590 num_examples: 875601 download_size: 2065207099 dataset_size: 4952806590 - config_name: CC-MAIN-2015-35 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 6053257306 num_examples: 1086470 download_size: 2632032769 dataset_size: 6053257306 - config_name: CC-MAIN-2015-40 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 5206096790 num_examples: 924036 download_size: 2203603087 dataset_size: 5206096790 - config_name: CC-MAIN-2015-48 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 8343050753 num_examples: 1537468 download_size: 3489600630 dataset_size: 8343050753 - config_name: CC-MAIN-2016-07 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 9329220105 num_examples: 1738650 download_size: 4005599785 dataset_size: 9329220105 - config_name: CC-MAIN-2016-18 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 3897220786 num_examples: 747570 download_size: 1675500816 dataset_size: 3897220786 - config_name: CC-MAIN-2016-22 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 4623903344 num_examples: 857060 download_size: 2000624854 dataset_size: 4623903344 - config_name: CC-MAIN-2016-26 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 3414418701 num_examples: 627995 download_size: 1403890884 dataset_size: 3414418701 - config_name: CC-MAIN-2016-30 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 7244342539 num_examples: 1183776 download_size: 2913394840 dataset_size: 7244342539 - config_name: CC-MAIN-2016-36 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 5402565529 num_examples: 915878 download_size: 2248454753 dataset_size: 5402565529 - config_name: CC-MAIN-2016-40 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 5938544915 num_examples: 1113534 download_size: 2530904625 dataset_size: 5938544915 - config_name: CC-MAIN-2016-44 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 15819536321 num_examples: 3528637 download_size: 6516546200 dataset_size: 15819536321 - config_name: CC-MAIN-2016-50 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 10822695594 num_examples: 2215939 download_size: 4439728574 dataset_size: 10822695594 - config_name: CC-MAIN-2017-04 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 11949732148 num_examples: 2441316 download_size: 5045763620 dataset_size: 11949732148 - config_name: CC-MAIN-2017-09 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 12473370126 num_examples: 2561539 download_size: 5398993614 dataset_size: 12473370126 - config_name: CC-MAIN-2017-13 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 12209904783 num_examples: 2458486 download_size: 5422393873 dataset_size: 12209904783 - config_name: CC-MAIN-2017-17 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 13763109013 num_examples: 2615558 download_size: 6025106556 dataset_size: 13763109013 - config_name: CC-MAIN-2017-22 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 14456991831 num_examples: 2775332 download_size: 6258001465 dataset_size: 14456991831 - config_name: CC-MAIN-2017-26 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 15036103558 num_examples: 2973499 download_size: 6813218532 dataset_size: 15036103558 - config_name: CC-MAIN-2017-30 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 18833639414 num_examples: 3870197 download_size: 8464443468 dataset_size: 18833639414 - config_name: CC-MAIN-2017-34 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 25828116836 num_examples: 4848154 download_size: 11599137919 dataset_size: 25828116836 - config_name: CC-MAIN-2017-39 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 29432150311 num_examples: 4840435 download_size: 13172655761 dataset_size: 29432150311 - config_name: CC-MAIN-2017-43 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 32672966840 num_examples: 5724493 download_size: 15041820212 dataset_size: 32672966840 - config_name: CC-MAIN-2017-47 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 34301891443 num_examples: 5291581 download_size: 15593452226 dataset_size: 34301891443 - config_name: CC-MAIN-2017-51 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 30012533603 num_examples: 5466672 download_size: 14005518471 dataset_size: 30012533603 - config_name: CC-MAIN-2018-05 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 47738703452 num_examples: 8053879 download_size: 22533983733 dataset_size: 47738703452 - config_name: CC-MAIN-2018-09 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 45503126107 num_examples: 8045410 download_size: 21900491411 dataset_size: 45503126107 - config_name: CC-MAIN-2018-13 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 43904789090 num_examples: 7980931 download_size: 21178075620 dataset_size: 43904789090 - config_name: CC-MAIN-2018-17 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 44481167440 num_examples: 8699878 download_size: 21623780968 dataset_size: 44481167440 - config_name: CC-MAIN-2018-22 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 64369136465 num_examples: 13332059 download_size: 32293951649 dataset_size: 64369136465 - config_name: CC-MAIN-2018-26 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 81232597180 num_examples: 16249638 download_size: 41007491366 dataset_size: 81232597180 - config_name: CC-MAIN-2018-30 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 151537007358 num_examples: 32535697 download_size: 77517210537 dataset_size: 151537007358 - config_name: CC-MAIN-2018-34 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 39026071869 num_examples: 6347230 download_size: 19285382621 dataset_size: 39026071869 - config_name: CC-MAIN-2018-39 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 35948493161 num_examples: 6372711 download_size: 17597722170 dataset_size: 35948493161 - config_name: CC-MAIN-2018-43 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 50928918805 num_examples: 8758225 download_size: 25291022646 dataset_size: 50928918805 - config_name: CC-MAIN-2018-47 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 43961213014 num_examples: 7270815 download_size: 22024998684 dataset_size: 43961213014 - config_name: CC-MAIN-2018-51 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 58902353921 num_examples: 10215384 download_size: 29497256483 dataset_size: 58902353921 - config_name: CC-MAIN-2019-04 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 54814836003 num_examples: 9930553 download_size: 27458854931 dataset_size: 54814836003 - config_name: CC-MAIN-2019-09 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 54426174385 num_examples: 8897510 download_size: 28125345656 dataset_size: 54426174385 - config_name: CC-MAIN-2019-13 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 48712051219 num_examples: 7803004 download_size: 25156014252 dataset_size: 48712051219 - config_name: CC-MAIN-2019-18 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 48203751852 num_examples: 7532171 download_size: 24844412087 dataset_size: 48203751852 - config_name: CC-MAIN-2019-22 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 51674379059 num_examples: 8339842 download_size: 26257475492 dataset_size: 51674379059 - config_name: CC-MAIN-2019-26 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 43336967638 num_examples: 7320268 download_size: 21900316910 dataset_size: 43336967638 - config_name: CC-MAIN-2019-30 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 46313133200 num_examples: 7682281 download_size: 23262218065 dataset_size: 46313133200 - config_name: CC-MAIN-2019-35 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 49570657315 num_examples: 8098108 download_size: 24938729240 dataset_size: 49570657315 - config_name: CC-MAIN-2019-39 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 43538081906 num_examples: 7102645 download_size: 21728983014 dataset_size: 43538081906 - config_name: CC-MAIN-2019-43 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 52817470138 num_examples: 8567061 download_size: 26105523209 dataset_size: 52817470138 - config_name: CC-MAIN-2019-47 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 42252827792 num_examples: 6775943 download_size: 21228532199 dataset_size: 42252827792 - config_name: CC-MAIN-2019-51 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 38926356094 num_examples: 6415558 download_size: 19510339598 dataset_size: 38926356094 - config_name: CC-MAIN-2020-05 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 48189844491 num_examples: 7921372 download_size: 24235687030 dataset_size: 48189844491 - config_name: CC-MAIN-2020-10 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 48904133840 num_examples: 8211791 download_size: 24576159189 dataset_size: 48904133840 - config_name: CC-MAIN-2020-16 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 51243682770 num_examples: 8578633 download_size: 25485035979 dataset_size: 51243682770 - config_name: CC-MAIN-2020-24 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 59424939072 num_examples: 10438139 download_size: 29827361603 dataset_size: 59424939072 - config_name: CC-MAIN-2020-29 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 66229730938 num_examples: 11475631 download_size: 33030161773 dataset_size: 66229730938 - config_name: CC-MAIN-2020-34 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 54287690582 num_examples: 9495610 download_size: 27018821467 dataset_size: 54287690582 - config_name: CC-MAIN-2020-40 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 71587907978 num_examples: 12058149 download_size: 35795677487 dataset_size: 71587907978 - config_name: CC-MAIN-2020-45 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 59172857400 num_examples: 9694734 download_size: 29495814784 dataset_size: 59172857400 - config_name: CC-MAIN-2020-50 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 58557861606 num_examples: 9539918 download_size: 29083801775 dataset_size: 58557861606 - config_name: CC-MAIN-2021-04 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 74507336015 num_examples: 12273028 download_size: 36874887518 dataset_size: 74507336015 - config_name: CC-MAIN-2021-10 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 60802783945 num_examples: 10176190 download_size: 30326513365 dataset_size: 60802783945 - config_name: CC-MAIN-2021-17 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 75061494488 num_examples: 12343366 download_size: 37345114890 dataset_size: 75061494488 - config_name: CC-MAIN-2021-21 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 70036417178 num_examples: 11584034 download_size: 34806730527 dataset_size: 70036417178 - config_name: CC-MAIN-2021-25 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 73653674063 num_examples: 12065281 download_size: 36581310312 dataset_size: 73653674063 - config_name: CC-MAIN-2021-31 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 79535885182 num_examples: 13383552 download_size: 39702500971 dataset_size: 79535885182 - config_name: CC-MAIN-2021-39 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 90302065651 num_examples: 14794773 download_size: 45211764750 dataset_size: 90302065651 - config_name: CC-MAIN-2021-43 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 108356023335 num_examples: 17698206 download_size: 54292215300 dataset_size: 108356023335 - config_name: CC-MAIN-2021-49 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 95867022229 num_examples: 15643875 download_size: 47902433321 dataset_size: 95867022229 - config_name: CC-MAIN-2022-05 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 97602903488 num_examples: 15772898 download_size: 48711364812 dataset_size: 97602903488 - config_name: CC-MAIN-2022-21 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 127495492928 num_examples: 21745889 download_size: 63379692210 dataset_size: 127495492928 - config_name: CC-MAIN-2022-27 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 128061655541 num_examples: 21580054 download_size: 63763936007 dataset_size: 128061655541 - config_name: CC-MAIN-2022-33 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 126436062118 num_examples: 21495687 download_size: 63067252044 dataset_size: 126436062118 - config_name: CC-MAIN-2022-40 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 123806739937 num_examples: 20206120 download_size: 61929035270 dataset_size: 123806739937 - config_name: CC-MAIN-2022-49 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 152577158166 num_examples: 24634059 download_size: 76529854484 dataset_size: 152577158166 - config_name: CC-MAIN-2023-06 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 174815301023 num_examples: 28962355 download_size: 87301203013 dataset_size: 174815301023 - config_name: CC-MAIN-2023-14 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 227631152876 num_examples: 37223376 download_size: 114188282465 dataset_size: 227631152876 - config_name: CC-MAIN-2023-23 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 321036722459 num_examples: 52119692 download_size: 161491274249 dataset_size: 321036722459 - config_name: CC-MAIN-2023-40 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 648032999611 num_examples: 101292016 download_size: 317965522325 dataset_size: 648032999611 - config_name: CC-MAIN-2023-50 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 744768384551 num_examples: 117073004 download_size: 365332295606 dataset_size: 744768384551 configs: - config_name: CC-MAIN-2013-20 data_files: - split: train path: CC-MAIN-2013-20/train-* - config_name: CC-MAIN-2013-48 data_files: - split: train path: CC-MAIN-2013-48/train-* - config_name: CC-MAIN-2014-10 data_files: - split: train path: CC-MAIN-2014-10/train-* - config_name: CC-MAIN-2014-15 data_files: - split: train path: CC-MAIN-2014-15/train-* - config_name: CC-MAIN-2014-23 data_files: - split: train path: CC-MAIN-2014-23/train-* - config_name: CC-MAIN-2014-35 data_files: - split: train path: CC-MAIN-2014-35/train-* - config_name: CC-MAIN-2014-41 data_files: - split: train path: CC-MAIN-2014-41/train-* - config_name: CC-MAIN-2014-42 data_files: - split: train path: CC-MAIN-2014-42/train-* - config_name: CC-MAIN-2014-49 data_files: - split: train path: CC-MAIN-2014-49/train-* - config_name: CC-MAIN-2014-52 data_files: - split: train path: CC-MAIN-2014-52/train-* - config_name: CC-MAIN-2015-06 data_files: - split: train path: CC-MAIN-2015-06/train-* - config_name: CC-MAIN-2015-11 data_files: - split: train path: CC-MAIN-2015-11/train-* - config_name: CC-MAIN-2015-14 data_files: - split: train path: CC-MAIN-2015-14/train-* - config_name: CC-MAIN-2015-18 data_files: - split: train path: CC-MAIN-2015-18/train-* - config_name: CC-MAIN-2015-22 data_files: - split: train path: CC-MAIN-2015-22/train-* - config_name: CC-MAIN-2015-27 data_files: - split: train path: CC-MAIN-2015-27/train-* - config_name: CC-MAIN-2015-32 data_files: - split: train path: CC-MAIN-2015-32/train-* - config_name: CC-MAIN-2015-35 data_files: - split: train path: CC-MAIN-2015-35/train-* - config_name: CC-MAIN-2015-40 data_files: - split: train path: CC-MAIN-2015-40/train-* - config_name: CC-MAIN-2015-48 data_files: - split: train path: CC-MAIN-2015-48/train-* - config_name: CC-MAIN-2016-07 data_files: - split: train path: CC-MAIN-2016-07/train-* - config_name: CC-MAIN-2016-18 data_files: - split: train path: CC-MAIN-2016-18/train-* - config_name: CC-MAIN-2016-22 data_files: - split: train path: CC-MAIN-2016-22/train-* - config_name: CC-MAIN-2016-26 data_files: - split: train path: CC-MAIN-2016-26/train-* - config_name: CC-MAIN-2016-30 data_files: - split: train path: CC-MAIN-2016-30/train-* - config_name: CC-MAIN-2016-36 data_files: - split: train path: CC-MAIN-2016-36/train-* - config_name: CC-MAIN-2016-40 data_files: - split: train path: CC-MAIN-2016-40/train-* - config_name: CC-MAIN-2016-44 data_files: - split: train path: CC-MAIN-2016-44/train-* - config_name: CC-MAIN-2016-50 data_files: - split: train path: CC-MAIN-2016-50/train-* - config_name: CC-MAIN-2017-04 data_files: - split: train path: CC-MAIN-2017-04/train-* - config_name: CC-MAIN-2017-09 data_files: - split: train path: CC-MAIN-2017-09/train-* - config_name: CC-MAIN-2017-13 data_files: - split: train path: CC-MAIN-2017-13/train-* - config_name: CC-MAIN-2017-17 data_files: - split: train path: CC-MAIN-2017-17/train-* - config_name: CC-MAIN-2017-22 data_files: - split: train path: CC-MAIN-2017-22/train-* - config_name: CC-MAIN-2017-26 data_files: - split: train path: CC-MAIN-2017-26/train-* - config_name: CC-MAIN-2017-30 data_files: - split: train path: CC-MAIN-2017-30/train-* - config_name: CC-MAIN-2017-34 data_files: - split: train path: CC-MAIN-2017-34/train-* - config_name: CC-MAIN-2017-39 data_files: - split: train path: CC-MAIN-2017-39/train-* - config_name: CC-MAIN-2017-43 data_files: - split: train path: CC-MAIN-2017-43/train-* - config_name: CC-MAIN-2017-47 data_files: - split: train path: CC-MAIN-2017-47/train-* - config_name: CC-MAIN-2017-51 data_files: - split: train path: CC-MAIN-2017-51/train-* - config_name: CC-MAIN-2018-05 data_files: - split: train path: CC-MAIN-2018-05/train-* - config_name: CC-MAIN-2018-09 data_files: - split: train path: CC-MAIN-2018-09/train-* - config_name: CC-MAIN-2018-13 data_files: - split: train path: CC-MAIN-2018-13/train-* - config_name: CC-MAIN-2018-17 data_files: - split: train path: CC-MAIN-2018-17/train-* - config_name: CC-MAIN-2018-22 data_files: - split: train path: CC-MAIN-2018-22/train-* - config_name: CC-MAIN-2018-26 data_files: - split: train path: CC-MAIN-2018-26/train-* - config_name: CC-MAIN-2018-30 data_files: - split: train path: CC-MAIN-2018-30/train-* - config_name: CC-MAIN-2018-34 data_files: - split: train path: CC-MAIN-2018-34/train-* - config_name: CC-MAIN-2018-39 data_files: - split: train path: CC-MAIN-2018-39/train-* - config_name: CC-MAIN-2018-43 data_files: - split: train path: CC-MAIN-2018-43/train-* - config_name: CC-MAIN-2018-47 data_files: - split: train path: CC-MAIN-2018-47/train-* - config_name: CC-MAIN-2018-51 data_files: - split: train path: CC-MAIN-2018-51/train-* - config_name: CC-MAIN-2019-04 data_files: - split: train path: CC-MAIN-2019-04/train-* - config_name: CC-MAIN-2019-09 data_files: - split: train path: CC-MAIN-2019-09/train-* - config_name: CC-MAIN-2019-13 data_files: - split: train path: CC-MAIN-2019-13/train-* - config_name: CC-MAIN-2019-18 data_files: - split: train path: CC-MAIN-2019-18/train-* - config_name: CC-MAIN-2019-22 data_files: - split: train path: CC-MAIN-2019-22/train-* - config_name: CC-MAIN-2019-26 data_files: - split: train path: CC-MAIN-2019-26/train-* - config_name: CC-MAIN-2019-30 data_files: - split: train path: CC-MAIN-2019-30/train-* - config_name: CC-MAIN-2019-35 data_files: - split: train path: CC-MAIN-2019-35/train-* - config_name: CC-MAIN-2019-39 data_files: - split: train path: CC-MAIN-2019-39/train-* - config_name: CC-MAIN-2019-43 data_files: - split: train path: CC-MAIN-2019-43/train-* - config_name: CC-MAIN-2019-47 data_files: - split: train path: CC-MAIN-2019-47/train-* - config_name: CC-MAIN-2019-51 data_files: - split: train path: CC-MAIN-2019-51/train-* - config_name: CC-MAIN-2020-05 data_files: - split: train path: CC-MAIN-2020-05/train-* - config_name: CC-MAIN-2020-10 data_files: - split: train path: CC-MAIN-2020-10/train-* - config_name: CC-MAIN-2020-16 data_files: - split: train path: CC-MAIN-2020-16/train-* - config_name: CC-MAIN-2020-24 data_files: - split: train path: CC-MAIN-2020-24/train-* - config_name: CC-MAIN-2020-29 data_files: - split: train path: CC-MAIN-2020-29/train-* - config_name: CC-MAIN-2020-34 data_files: - split: train path: CC-MAIN-2020-34/train-* - config_name: CC-MAIN-2020-40 data_files: - split: train path: CC-MAIN-2020-40/train-* - config_name: CC-MAIN-2020-45 data_files: - split: train path: CC-MAIN-2020-45/train-* - config_name: CC-MAIN-2020-50 data_files: - split: train path: CC-MAIN-2020-50/train-* - config_name: CC-MAIN-2021-04 data_files: - split: train path: CC-MAIN-2021-04/train-* - config_name: CC-MAIN-2021-10 data_files: - split: train path: CC-MAIN-2021-10/train-* - config_name: CC-MAIN-2021-17 data_files: - split: train path: CC-MAIN-2021-17/train-* - config_name: CC-MAIN-2021-21 data_files: - split: train path: CC-MAIN-2021-21/train-* - config_name: CC-MAIN-2021-25 data_files: - split: train path: CC-MAIN-2021-25/train-* - config_name: CC-MAIN-2021-31 data_files: - split: train path: CC-MAIN-2021-31/train-* - config_name: CC-MAIN-2021-39 data_files: - split: train path: CC-MAIN-2021-39/train-* - config_name: CC-MAIN-2021-43 data_files: - split: train path: CC-MAIN-2021-43/train-* - config_name: CC-MAIN-2021-49 data_files: - split: train path: CC-MAIN-2021-49/train-* - config_name: CC-MAIN-2022-05 data_files: - split: train path: CC-MAIN-2022-05/train-* - config_name: CC-MAIN-2022-21 data_files: - split: train path: CC-MAIN-2022-21/train-* - config_name: CC-MAIN-2022-27 data_files: - split: train path: CC-MAIN-2022-27/train-* - config_name: CC-MAIN-2022-33 data_files: - split: train path: CC-MAIN-2022-33/train-* - config_name: CC-MAIN-2022-40 data_files: - split: train path: CC-MAIN-2022-40/train-* - config_name: CC-MAIN-2022-49 data_files: - split: train path: CC-MAIN-2022-49/train-* - config_name: CC-MAIN-2023-06 data_files: - split: train path: CC-MAIN-2023-06/train-* - config_name: CC-MAIN-2023-14 data_files: - split: train path: CC-MAIN-2023-14/train-* - config_name: CC-MAIN-2023-23 data_files: - split: train path: CC-MAIN-2023-23/train-* - config_name: CC-MAIN-2023-40 data_files: - split: train path: CC-MAIN-2023-40/train-* - config_name: CC-MAIN-2023-50 data_files: - split: train path: CC-MAIN-2023-50/train-* --- <p align="center"> <h1 align="center">🐳 OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text</h1> </p> > ⭐️ **NOTE:** Several parquet files were marked unsafe (viruses) by official scaning of hf, while they are reported safe by ClamAV and Virustotal. > We found [many false positive cases](https://discuss.huggingface.co/u/mcpotato/summary) of the hf automatic scanning in hf discussions and raise [one discussion](https://discuss.huggingface.co/t/one-parquet-file-of-my-dataset-was-marked-unsafe/113745) to ask for a re-scanning. This is the repository of OmniCorpus-CC, which contains 988 million image-text interleaved documents collected from [Common Crawl](https://commoncrawl.org/). - Repository: https://github.com/OpenGVLab/OmniCorpus - Paper (ICLR 2025 Spotlight): https://arxiv.org/abs/2406.08418 OmniCorpus dataset is a large-scale image-text interleaved dataset, which pushes the boundaries of scale and diversity by encompassing **8.6 billion images** interleaved with **1,696 text tokens** from diverse sources, significantly surpassing previous datasets. This dataset demonstrates several advantages over its counterparts: 1. **Larger data scale:** Our dataset is 1.7 times larger in images and 12.5 times larger in texts compared to the previously largest multimodal dataset, LAION-5B, while maintaining excellent data quality. 2. **Richer data diversity:** Drawing from a broader range of data sources, our dataset is more diverse than other image-text interleaved datasets. It includes bilingual multimodal data in both Chinese and English, and encompasses text-centric and vision-centric documents extracted from common websites and video platforms. 3. **More flexible format:** The streaming data format of our dataset offers exceptional flexibility, allowing adaptation to various data structures, including pure text corpora, image-text pairs, and interleaved data formats. <img width="578" alt="image" src="https://github.com/OpenGVLab/OmniCorpus/assets/47669167/641a6427-ba50-41e6-8634-8810113fd803"> The OmniCorpus contains three sections: - **OmniCorpus-CC**: processed from dumps in Common Crawl from 2013 to Nov./Dec. 2023. - **OmniCorpus-CW**: sourced from Chinese internet resources, will be availiable in [OpenDataLab](https://opendatalab.com/) platform. - **OmniCorpus-YT**: samples Youtube video frames as images and collects subtitles as texts. Code for pre-training, evaluating, main body extracting, and filtering have been released in the official [repository](https://github.com/OpenGVLab/OmniCorpus). A pre-trained model is availiable [here](https://huggingface.co/Qingyun/OmniCorpus-InternVL). # Data Pipeline Our data pipeline consists of five key stages: main body extraction, preliminary text filtering, document deduplication, image downloading \& filtering, and detailed text filtering. Each stage efficiently reduces the dataset to retain only high-quality data. Please refer to our paper for more details about the data pipeline. <img width="723" alt="image" src="https://github.com/OpenGVLab/OmniCorpus/assets/47669167/a6de8928-58fb-4ff4-8ef9-4bd90e9ada5f"> # Usages The image-text interleaved documents are recommanded for the following usages: - Pre-training multimodal large language model (MLLM): Recent MLLMs (such as Flamingo series, EMU series, IDEFICS series, MM1, Cambrian-1, and xGen-MM) have shown that image-text interleaved data aids multimodal in-context learning and maintains the capabilities of large language models during multimodal fine-tuning. - Long text-image retrieval: We provide image-text similarities calculated with CLIP, which can convert the documents to image-text retrieval dataset with longer text. A retrieval model pre-trained on such data can retrieval images based on longer text, which can be used for multimodal RAG, converting pure text to multimodal sample, etc. - Source for futher dataset research: Our data is large-scale, which can serve as the source for researches for data curation strategies. We provide many useful attributes as metadata for each document, which can enrich the filtering strategy and reduce the cost. - ...... # Data Format Following common practices, the data is organized into Parquet file format. You might encounter errors when using `pandas.read_parquet` (because the data structure contains nested elements). We recommend using fastparquet to load the parquet files. ```Python import fastparquet df = fastparquet.ParquetFile(parquet_file_path).to_pandas() # You can also use iter_batches parquet_file = pq.ParquetFile(filepath) for batch in parquet_file.iter_batches(): df = batch.to_pandas() ``` You can convert the i-th document and convert it into a dictionary. ```Python doc_dict = df.iloc[i].to_dict() ``` The document format is as follow: ```json { 'images': [ <str: image_1_url>, None, <str: image_2_url>, None, ], 'texts': [ None, <str: text_paragraph_1_content> None, <str: text_paragraph_2_content>, ] 'metadata': [ <dict: image_1_metadata>, None, <dict: image_2_metadata>, None ], 'general_metadata': { "url": <str: document url>, "id": <str: document id>, "domain": <list[str]: domains extracted from document url>, "fluency_prob": <float: the probability of fluency>, "non_advertisement_prob": <float: the probability of non-advertisement>, "porn_prob": <float: the probability of porn content>, "politics_prob": <float: the probability of politics content>, "toxic_prob": <float: the probability of toxic content>, } } ``` Each image metadata is as follow: ```json { "img_url_sha": <str: sha code of image url>, "width": <int: image width>, "height": <int: image height>, "bytes": <int: byte number of the image file>, "d_hash": <str: d_hash code of the image, used for image deduplication>, "p_hash": <str: p_hash code of the image, used for image deduplication>, "d_hash_dup_count": <int: duplicated times detected by d_hash code>, "p_hash_dup_count": <int: duplicated times detected by p_hash code>, "aesthetic prob": <float: aesthetic probility>, "unsafe prob": <float: NSFW probility>, } ``` # License and Terms of Use The OmniCorpus dataset is distributed under [the CC BY 4.0 License](https://creativecommons.org/licenses/by/4.0/). The open-source code is released under the [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0). The Terms of Use (ToUs) have been developed based on widely accepted standards. By accessing or using this dataset, users acknowledge their responsibility to comply with all relevant legal, regulatory, and ethical standards. - All users, whether from academia or industry, must comply with the ToUs outlined in the CC BY 4.0 License. - Any derived datasets or models must acknowledge the use of the OmniCorpus dataset to maintain transparency. - The OmniCorpus must not be used in any project involving sensitive content or harmful outcomes, including but not limited to political manipulation, hate speech generation, misinformation propagation, or tasks that perpetuate harmful stereotypes or biases. - The use of this dataset in any manner that violates rights, such as copyright infringement, privacy breaches, or misuse of sensitive information, is strictly prohibited. - While we do not enforce jurisdiction-specific terms, we strongly recommend that users ensure compliance with applicable local laws and regulations. - The use of specific subset must comply with the ToUs of the primary source. Specifically, the use of OmniCorpus-CC, OmniCorpus-CW, and OmniCorpus-YT must comply with [the Common Crawl ToUs](https://commoncrawl.org/terms-of-use), the [regulations](https://www.gov.cn/zhengce/content/202409/content\_6977766.htm) on the security management of Internet data in China, and [YouTube’s ToUs](https://www.youtube.com/terms), respectively. - These ToUs do not supersede the ToUs of the original content sources. Users must ensure that any use of the dataset’s content complies with the original ToUs and the rights of the data subjects. # Citation ``` @inproceedings{li2024omnicorpus, title={OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text}, author={Li, Qingyun and Chen, Zhe and Wang, Weiyun and Wang, Wenhai and Ye, Shenglong and Jin, Zhenjiang and others}, booktitle={The Thirteenth International Conference on Learning Representations}, year={2025} } ```

haonan-li/cmmlu

haonan-li

"2023-07-13T10:19:29Z"

14,504

66

[ "task_categories:multiple-choice", "task_categories:question-answering", "language:zh", "license:cc-by-nc-4.0", "size_categories:10K<n<100K", "modality:text", "library:datasets", "library:mlcroissant", "arxiv:2306.09212", "region:us", "chinese", "llm", "evaluation" ]

[ "multiple-choice", "question-answering" ]

"2023-06-25T16:37:44Z"

--- license: cc-by-nc-4.0 task_categories: - multiple-choice - question-answering language: - zh tags: - chinese - llm - evaluation pretty_name: CMMLU size_categories: - 10K<n<100K --- # CMMLU: Measuring massive multitask language understanding in Chinese - **Homepage:** [https://github.com/haonan-li/CMMLU](https://github.com/haonan-li/CMMLU) - **Repository:** [https://huggingface.co/datasets/haonan-li/cmmlu](https://huggingface.co/datasets/haonan-li/cmmlu) - **Paper:** [CMMLU: Measuring Chinese Massive Multitask Language Understanding](https://arxiv.org/abs/2306.09212). ## Table of Contents - [Introduction](#introduction) - [Leaderboard](#leaderboard) - [Data](#data) - [Citation](#citation) - [License](#license) ## Introduction CMMLU is a comprehensive Chinese assessment suite specifically designed to evaluate the advanced knowledge and reasoning abilities of LLMs within the Chinese language and cultural context. CMMLU covers a wide range of subjects, comprising 67 topics that span from elementary to advanced professional levels. It includes subjects that require computational expertise, such as physics and mathematics, as well as disciplines within humanities and social sciences. Many of these tasks are not easily translatable from other languages due to their specific contextual nuances and wording. Furthermore, numerous tasks within CMMLU have answers that are specific to China and may not be universally applicable or considered correct in other regions or languages. ## Leaderboard Latest leaderboard is in our [github](https://github.com/haonan-li/CMMLU). ## Data We provide development and test dataset for each of 67 subjects, with 5 questions in development set and 100+ quesitons in test set. Each question in the dataset is a multiple-choice questions with 4 choices and only one choice as the correct answer. Here are two examples: ``` 题目：同一物种的两类细胞各产生一种分泌蛋白，组成这两种蛋白质的各种氨基酸含量相同，但排列顺序不同。其原因是参与这两种蛋白质合成的： A. tRNA种类不同 B. 同一密码子所决定的氨基酸不同 C. mRNA碱基序列不同 D. 核糖体成分不同答案是：C ``` ``` 题目：某种植物病毒V是通过稻飞虱吸食水稻汁液在水稻间传播的。稻田中青蛙数量的增加可减少该病毒在水稻间的传播。下列叙述正确的是： A. 青蛙与稻飞虱是捕食关系 B. 水稻和病毒V是互利共生关系 C. 病毒V与青蛙是寄生关系 D. 水稻与青蛙是竞争关系答案是： ``` #### Load data ```python from datasets import load_dataset cmmlu=load_dataset(r"haonan-li/cmmlu", 'agronomy') print(cmmlu['test'][0]) ``` #### Load all data at once ```python task_list = ['agronomy', 'anatomy', 'ancient_chinese', 'arts', 'astronomy', 'business_ethics', 'chinese_civil_service_exam', 'chinese_driving_rule', 'chinese_food_culture', 'chinese_foreign_policy', 'chinese_history', 'chinese_literature', 'chinese_teacher_qualification', 'clinical_knowledge', 'college_actuarial_science', 'college_education', 'college_engineering_hydrology', 'college_law', 'college_mathematics', 'college_medical_statistics', 'college_medicine', 'computer_science', 'computer_security', 'conceptual_physics', 'construction_project_management', 'economics', 'education', 'electrical_engineering', 'elementary_chinese', 'elementary_commonsense', 'elementary_information_and_technology', 'elementary_mathematics', 'ethnology', 'food_science', 'genetics', 'global_facts', 'high_school_biology', 'high_school_chemistry', 'high_school_geography', 'high_school_mathematics', 'high_school_physics', 'high_school_politics', 'human_sexuality', 'international_law', 'journalism', 'jurisprudence', 'legal_and_moral_basis', 'logical', 'machine_learning', 'management', 'marketing', 'marxist_theory', 'modern_chinese', 'nutrition', 'philosophy', 'professional_accounting', 'professional_law', 'professional_medicine', 'professional_psychology', 'public_relations', 'security_study', 'sociology', 'sports_science', 'traditional_chinese_medicine', 'virology', 'world_history', 'world_religions'] from datasets import load_dataset cmmlu = {k: load_dataset(r"haonan-li/cmmlu", k) for k in task_list} ``` ## Citation ``` @misc{li2023cmmlu, title={CMMLU: Measuring massive multitask language understanding in Chinese}, author={Haonan Li and Yixuan Zhang and Fajri Koto and Yifei Yang and Hai Zhao and Yeyun Gong and Nan Duan and Timothy Baldwin}, year={2023}, eprint={2306.09212}, archivePrefix={arXiv}, primaryClass={cs.CL} } ``` ## License The CMMLU dataset is licensed under a [Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License](http://creativecommons.org/licenses/by-nc-sa/4.0/).

desmondlzy/bigs-data

desmondlzy

"2025-03-11T21:09:56Z"

14,468

0

[ "license:cc-by-sa-4.0", "modality:image", "arxiv:2408.13370", "region:us", "olat" ]

null

"2025-03-10T08:45:14Z"

--- license: cc-by-sa-4.0 tags: - olat pretty_name: 'Dataset for BiGS: Bidirectional Primitives for Relightable 3D Gaussian Splatting' --- # BiGS Dataset The OLAT dataset used in the paper _BiGS: Bidirectional Primitives for Relightable 3D Gaussian Splatting_ (3DV 2025). Check out our [project page](https://desmondlzy.me/publications/bigs/). We provide 7 synthetic scenes in the dataset, featuring various complex light transport effects, such as subsurface scattering, fuzzy surfaces, and iridescent reflection. Each scene (1.8 ~ 3.2 GB) consists of: - 40 training OLAT conditions (`olat_1` - `olat_40`) with 48 views per light condition; - 58 test OLAT conditions (`olat_41` - `olat_98`) with 1 view per light condition; - 1 all-light-on conditions (`olat_all`) with 48 views per light conditions. Each light condition includes `.exr` images, object masks, transforms with camera poses, light positions and intensities. Please refer to our [github repo](https://github.com/desmondlzy/bigs) for how to use the dataset provided here to train BiGS, and our [paper (arxiv)](https://www.arxiv.org/abs/2408.13370) for details of BiGS. ## Citation If you use our dataset in your research, please consider citing us with the below bibtex entry: ``` @misc{zhenyuan2024bigs, title={BiGS: Bidirectional Primitives for Relightable 3D Gaussian Splatting}, author={Liu Zhenyuan and Yu Guo and Xinyuan Li and Bernd Bickel and Ran Zhang}, year={2024}, eprint={2408.13370}, url={https://arxiv.org/abs/2408.13370}, } ``` ## Acknowledgments Our synthetic data is generated using [Mitsuba](https://mitsuba.readthedocs.io/en/stable/). We thank the 3D models' creators: Keenan Crane for _Spot_; Stanford Computer Graphics Laboratory for the models _Dragon_ and _Bunny_; Wenzel Jakob for the model _Mistuba Ball_. Special thanks to Changxi Zheng for supporting the internship program at Tencent Pixel Lab.

kevinjesse/ManyRefactors4C

kevinjesse

"2022-09-25T12:59:34Z"

14,461

0

[ "license:cc-by-2.0", "size_categories:10M<n<100M", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]

null

"2022-09-25T06:28:58Z"

--- license: cc-by-2.0 ---

fixie-ai/peoples_speech

fixie-ai

"2024-08-11T17:26:01Z"

14,320

2

[ "size_categories:1M<n<10M", "format:parquet", "modality:audio", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]

null

"2024-08-05T18:35:01Z"

--- dataset_info: - config_name: clean features: - name: id dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: duration_ms dtype: int32 - name: text dtype: string - name: continuation dtype: string splits: - name: validation num_bytes: 2511523987.692 num_examples: 18622 - name: test num_bytes: 4259695510.794 num_examples: 34898 - name: train num_bytes: 401646320552.671 num_examples: 1501271 download_size: 398922548670 dataset_size: 408417540051 - config_name: dirty_sa features: - name: id dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: duration_ms dtype: int32 - name: text dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 144432442623.054 num_examples: 548014 - name: validation num_bytes: 2511524241.692 num_examples: 18622 - name: test num_bytes: 4259695588.794 num_examples: 34898 download_size: 149491764186 dataset_size: 151203662453.53998 configs: - config_name: clean data_files: - split: validation path: clean/validation-* - split: test path: clean/test-* - split: train path: data/train-* - config_name: dirty_sa data_files: - split: train path: dirty_sa/train-* - split: validation path: dirty_sa/validation-* - split: test path: dirty_sa/test-* ---