New Datasets

{
  "sha": "fcbc0d38550e134f273426aa7c9cc2b491270bc4",
  "tags": [
    "task_categories:robotics",
    "task_categories:reinforcement-learning",
    "language:en",
    "language:zh",
    "license:cc-by-sa-4.0",
    "size_categories:n>1T",
    "modality:video",
    "region:us",
    "agent",
    "robotic",
    "real-world",
    "dual-arm",
    "video",
    "vla",
    "embodied intelligence"
  ],
  "gated": "auto",
  "likes": 222,
  "license": "cc-by-sa-4.0",
  "private": false,
  "language": [
    "en",
    "zh"
  ],
  "downloads": 1205822,
  "publisher": "genrobot2025",
  "created_on": "2025-12-31T07:17:19.000Z",
  "dataset_id": "huggingface.co/datasets/genrobot2025/10Kh-RealOmin-OpenData",
  "dataset_url": "https://huggingface.co/datasets/genrobot2025/10Kh-RealOmin-OpenData",
  "description": "Boasting over 13,000 hours of cumulative data and 5 million+ clips, it ranks as the largest open-source embodied intelligence dataset in the industry. Update Notes：Stage 3 data upload completed. 13,000+ hours of pure dual-hand data with frame-level alignment latency < 1ms Full high-precision trajectory reconstruction, breaking the limit of superficial open source, fully ready-to-use 3,000+ contributors and 10,000+ real household scenarios with exceptional diversity Comprehensive… See the full description on the dataset page: https://huggingface.co/datasets/genrobot2025/10Kh-RealOmin-OpenData.",
  "observed_at": "2026-07-06T00:55:46.488Z",
  "pretty_name": null,
  "card_license": "cc-by-sa-4.0",
  "card_languages": [
    "en",
    "zh"
  ],
  "size_categories": [
    "n>1T"
  ],
  "task_categories": [
    "robotics",
    "reinforcement-learning"
  ],
  "last_modified_on": "2026-04-24T05:02:26.000Z",
  "observation_week": "2026-W28",
  "card_task_categories": [
    "robotics",
    "reinforcement-learning"
  ]
}

{
  "sha": "7fd92dc825a75cbff271a5a52eea0eda91a2c112",
  "tags": [
    "task_categories:text-classification",
    "task_categories:text-generation",
    "language:en",
    "license:apache-2.0",
    "size_categories:1B<n<10B",
    "modality:tabular",
    "modality:text",
    "region:us"
  ],
  "gated": false,
  "likes": 153,
  "license": "apache-2.0",
  "private": false,
  "language": [
    "en"
  ],
  "downloads": 1262806,
  "publisher": "m-a-p",
  "created_on": "2024-12-14T12:46:33.000Z",
  "dataset_id": "huggingface.co/datasets/m-a-p/FineFineWeb",
  "dataset_url": "https://huggingface.co/datasets/m-a-p/FineFineWeb",
  "description": "FineFineWeb: A Comprehensive Study on Fine-Grained Domain Web Corpus arXiv: Coming Soon Project Page: Coming Soon Blog: Coming Soon Data Statistics Domain (#tokens/#samples) Iteration 1 Tokens Iteration 2 Tokens Iteration 3 Tokens Total Tokens Iteration 1 Count Iteration 2 Count Iteration 3 Count Total Count aerospace 5.77B 261.63M 309.33M 6.34B 9100000 688505 611034 10399539 agronomy 13.08B 947.41M 229.04M 14.26B 15752828 2711790 649404 19114022 artistic… See the full description on the dataset page: https://huggingface.co/datasets/m-a-p/FineFineWeb.",
  "observed_at": "2026-07-06T00:55:46.488Z",
  "pretty_name": null,
  "card_license": "apache-2.0",
  "card_languages": [
    "en"
  ],
  "size_categories": [
    "1B<n<10B"
  ],
  "task_categories": [
    "text-classification",
    "text-generation"
  ],
  "last_modified_on": "2024-12-19T11:34:03.000Z",
  "observation_week": "2026-W28",
  "card_task_categories": [
    "text-classification",
    "text2text-generation",
    "text-generation"
  ]
}

{
  "sha": "494fce0367580237ed1073a60ac801abb072f521",
  "tags": [
    "license:mit",
    "region:us",
    "documentation"
  ],
  "gated": false,
  "likes": 39,
  "license": "mit",
  "private": false,
  "language": [],
  "downloads": 1268122,
  "publisher": "hf-doc-build",
  "created_on": "2022-11-08T09:03:37.000Z",
  "dataset_id": "huggingface.co/datasets/hf-doc-build/doc-build-dev",
  "dataset_url": "https://huggingface.co/datasets/hf-doc-build/doc-build-dev",
  "description": "This is a dataset which contains the docs from all the PRs that are updating one of the docs from https://huggingface.co/docs. It is automatically updated by this github action from the doc-buider repo.",
  "observed_at": "2026-07-06T00:55:46.488Z",
  "pretty_name": "HF Documentation (PRs)",
  "card_license": "mit",
  "card_languages": [],
  "size_categories": [],
  "task_categories": [],
  "last_modified_on": "2026-04-20T08:59:22.000Z",
  "observation_week": "2026-W28",
  "card_task_categories": []
}

{
  "sha": "711e0811642364e7aa8f10a8918367d0b626d578",
  "tags": [
    "license:apache-2.0",
    "arxiv:2404.07972",
    "region:us"
  ],
  "gated": false,
  "likes": 33,
  "license": "apache-2.0",
  "private": false,
  "language": [],
  "downloads": 1292149,
  "publisher": "xlangai",
  "created_on": "2025-05-27T15:19:04.000Z",
  "dataset_id": "huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache",
  "dataset_url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache",
  "description": "OSWorld File Cache This repository serves as a file cache for the OSWorld project, providing reliable and fast access to evaluation files that were previously hosted on Google Drive. Overview OSWorld is a scalable, real computer environment for multimodal agents, supporting task setup, execution-based evaluation, and interactive learning across various operating systems and applications. This cache repository ensures that all evaluation files are consistently accessible… See the full description on the dataset page: https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache.",
  "observed_at": "2026-07-06T00:55:46.488Z",
  "pretty_name": null,
  "card_license": "apache-2.0",
  "card_languages": [],
  "size_categories": [],
  "task_categories": [],
  "last_modified_on": "2026-05-07T11:32:14.000Z",
  "observation_week": "2026-W28",
  "card_task_categories": []
}

{
  "sha": "1588ec454efa1a09f29cd18ddd04fe05fc8653a2",
  "tags": [
    "task_categories:text-generation",
    "task_categories:fill-mask",
    "task_ids:language-modeling",
    "task_ids:masked-language-modeling",
    "annotations_creators:no-annotation",
    "language_creators:found",
    "multilinguality:multilingual",
    "source_datasets:original",
    "language:af",
    "language:am",
    "language:ar",
    "language:az",
    "language:be",
    "language:bg",
    "language:bn",
    "language:ca",
    "language:ceb",
    "language:co",
    "language:cs",
    "language:cy",
    "language:da",
    "language:de",
    "language:el",
    "language:en",
    "language:eo",
    "language:es",
    "language:et",
    "language:eu",
    "language:fa",
    "language:fi"
  ],
  "gated": false,
  "likes": 605,
  "license": "odc-by",
  "private": false,
  "language": [
    "af",
    "am",
    "ar",
    "az",
    "be",
    "bg",
    "bn",
    "ca",
    "ceb",
    "co",
    "cs",
    "cy",
    "da",
    "de",
    "el",
    "en",
    "eo",
    "es",
    "et",
    "eu",
    "fa",
    "fi",
    "fil",
    "fr",
    "fy",
    "ga",
    "gd",
    "gl",
    "gu",
    "ha",
    "haw",
    "he",
    "hi",
    "hmn",
    "ht",
    "hu",
    "hy",
    "id",
    "ig",
    "is",
    "it",
    "iw",
    "ja",
    "jv",
    "ka",
    "kk",
    "km",
    "kn",
    "ko",
    "ku",
    "ky",
    "la",
    "lb",
    "lo",
    "lt",
    "lv",
    "mg",
    "mi",
    "mk",
    "ml",
    "mn",
    "mr",
    "ms",
    "mt",
    "my",
    "ne",
    "nl",
    "no",
    "ny",
    "pa",
    "pl",
    "ps",
    "pt",
    "ro",
    "ru",
    "sd",
    "si",
    "sk",
    "sl",
    "sm",
    "sn",
    "so",
    "sq",
    "sr",
    "st",
    "su",
    "sv",
    "sw",
    "ta",
    "te",
    "tg",
    "th",
    "tr",
    "uk",
    "und",
    "ur",
    "uz",
    "vi",
    "xh",
    "yi",
    "yo",
    "zh",
    "zu"
  ],
  "downloads": 1300690,
  "publisher": "allenai",
  "created_on": "2022-03-02T23:29:22.000Z",
  "dataset_id": "huggingface.co/datasets/allenai/c4",
  "dataset_url": "https://huggingface.co/datasets/allenai/c4",
  "description": "C4 Dataset Summary A colossal, cleaned version of Common Crawl's web crawl corpus. Based on Common Crawl dataset: \"https://commoncrawl.org\". This is the processed version of Google's C4 dataset We prepared five variants of the data: en, en.noclean, en.noblocklist, realnewslike, and multilingual (mC4). For reference, these are the sizes of the variants: en: 305GB en.noclean: 2.3TB en.noblocklist: 380GB realnewslike: 15GB multilingual (mC4): 9.7TB (108 subsets, one per… See the full description on the dataset page: https://huggingface.co/datasets/allenai/c4.",
  "observed_at": "2026-07-06T00:55:46.488Z",
  "pretty_name": "C4",
  "card_license": [
    "odc-by"
  ],
  "card_languages": [
    "af",
    "am",
    "ar",
    "az",
    "be"
  ],
  "size_categories": [
    "10B<n<100B"
  ],
  "task_categories": [
    "text-generation",
    "fill-mask"
  ],
  "last_modified_on": "2024-01-09T19:14:03.000Z",
  "observation_week": "2026-W28",
  "card_task_categories": [
    "text-generation",
    "fill-mask"
  ]
}

{
  "sha": "b08601e04326c79dfdd32d625aee71d232d685c3",
  "tags": [
    "task_categories:text-generation",
    "task_categories:fill-mask",
    "task_ids:language-modeling",
    "task_ids:masked-language-modeling",
    "annotations_creators:no-annotation",
    "language_creators:crowdsourced",
    "multilinguality:monolingual",
    "source_datasets:original",
    "language:en",
    "license:cc-by-sa-3.0",
    "license:gfdl",
    "size_categories:1M<n<10M",
    "format:parquet",
    "modality:text",
    "library:datasets",
    "library:dask",
    "library:polars",
    "library:mlcroissant",
    "arxiv:1609.07843",
    "region:us"
  ],
  "gated": false,
  "likes": 728,
  "license": "cc-by-sa-3.0",
  "private": false,
  "language": [
    "en"
  ],
  "downloads": 1341990,
  "publisher": "Salesforce",
  "created_on": "2022-03-02T23:29:22.000Z",
  "dataset_id": "huggingface.co/datasets/Salesforce/wikitext",
  "dataset_url": "https://huggingface.co/datasets/Salesforce/wikitext",
  "description": "Dataset Card for \"wikitext\" Dataset Summary The WikiText language modeling dataset is a collection of over 100 million tokens extracted from the set of verified Good and Featured articles on Wikipedia. The dataset is available under the Creative Commons Attribution-ShareAlike License. Compared to the preprocessed version of Penn Treebank (PTB), WikiText-2 is over 2 times larger and WikiText-103 is over 110 times larger. The WikiText dataset also features a far larger… See the full description on the dataset page: https://huggingface.co/datasets/Salesforce/wikitext.",
  "observed_at": "2026-07-06T00:55:46.488Z",
  "pretty_name": "WikiText",
  "card_license": [
    "cc-by-sa-3.0",
    "gfdl"
  ],
  "card_languages": [
    "en"
  ],
  "size_categories": [
    "1M<n<10M"
  ],
  "task_categories": [
    "text-generation",
    "fill-mask"
  ],
  "last_modified_on": "2024-01-04T16:49:18.000Z",
  "observation_week": "2026-W28",
  "card_task_categories": [
    "text-generation",
    "fill-mask"
  ]
}

{
  "sha": "a82400884621626d41bef89b7604f8054e7e00e0",
  "tags": [
    "size_categories:1K<n<10K",
    "format:parquet",
    "modality:text",
    "library:datasets",
    "library:pandas",
    "library:mlcroissant",
    "library:polars",
    "arxiv:2506.04178",
    "region:us"
  ],
  "gated": false,
  "likes": 32,
  "license": null,
  "private": false,
  "language": [],
  "downloads": 1374549,
  "publisher": "ryanmarten",
  "created_on": "2025-08-30T23:58:46.000Z",
  "dataset_id": "huggingface.co/datasets/ryanmarten/OpenThoughts-1k-sample",
  "dataset_url": "https://huggingface.co/datasets/ryanmarten/OpenThoughts-1k-sample",
  "description": "[!NOTE] We have released a paper for OpenThoughts! See our paper here. Open-Thoughts-1k-sample This is a 1k sample of the OpenThoughts-114k dataset. Open synthetic reasoning dataset with high-quality examples covering math, science, code, and puzzles! Inspect the content with rich formatting with Curator Viewer. Available Subsets default subset containing ready-to-train data used to finetune the OpenThinker-7B and OpenThinker-32B models: ds =… See the full description on the dataset page: https://huggingface.co/datasets/ryanmarten/OpenThoughts-1k-sample.",
  "observed_at": "2026-07-06T00:55:46.488Z",
  "pretty_name": null,
  "card_license": null,
  "card_languages": [],
  "size_categories": [
    "1K<n<10K"
  ],
  "task_categories": [],
  "last_modified_on": "2025-08-31T00:33:15.000Z",
  "observation_week": "2026-W28",
  "card_task_categories": []
}

{
  "sha": "7ee825405a889ac77b0d404fac868f9813da0c83",
  "tags": [
    "size_categories:n<1K",
    "format:imagefolder",
    "modality:image",
    "library:datasets",
    "library:mlcroissant",
    "region:us"
  ],
  "gated": false,
  "likes": 50,
  "license": null,
  "private": false,
  "language": [],
  "downloads": 1442486,
  "publisher": "banned-historical-archives",
  "created_on": "2023-12-17T14:47:08.000Z",
  "dataset_id": "huggingface.co/datasets/banned-historical-archives/banned-historical-archives",
  "dataset_url": "https://huggingface.co/datasets/banned-historical-archives/banned-historical-archives",
  "description": "和谐历史档案馆数据集 - Banned Historical Archives Datasets 和谐历史档案馆数据集包含已录入 https://banned-historical-archives.github.io 和暂未未录入的原始文件。 目录结构 banned-historical-archives.github.io # 已录入该网站的原始数据，不定期从 github 仓库中同步 raw # 原始文件 config # 配置文件 todo # 存放暂未录入网站的文件 部分报纸和图片资料存放在单独的仓库: 名称 地址 状态 参考消息 https://huggingface.co/datasets/banned-historical-archives/ckxx 未录入 人民日报 https://huggingface.co/datasets/banned-historical-archives/rmrb 已精选重要的文章录入 文汇报… See the full description on the dataset page: https://huggingface.co/datasets/banned-historical-archives/banned-historical-archives.",
  "observed_at": "2026-07-06T00:55:46.488Z",
  "pretty_name": null,
  "card_license": null,
  "card_languages": [],
  "size_categories": [
    "n<1K"
  ],
  "task_categories": [],
  "last_modified_on": "2025-10-19T15:21:40.000Z",
  "observation_week": "2026-W28",
  "card_task_categories": []
}

{
  "sha": "0b7fd955a202c05b39cf9bc816c270fbdb391ea4",
  "tags": [
    "region:us"
  ],
  "gated": false,
  "likes": 19,
  "license": null,
  "private": false,
  "language": [],
  "downloads": 1476158,
  "publisher": "ayuo",
  "created_on": "2026-04-01T14:22:50.000Z",
  "dataset_id": "huggingface.co/datasets/ayuo/hd_tmp",
  "dataset_url": "https://huggingface.co/datasets/ayuo/hd_tmp",
  "description": null,
  "observed_at": "2026-07-06T00:55:46.488Z",
  "pretty_name": null,
  "card_license": null,
  "card_languages": [],
  "size_categories": [],
  "task_categories": [],
  "last_modified_on": "2026-07-05T09:46:14.000Z",
  "observation_week": "2026-W28",
  "card_task_categories": []
}

{
  "sha": "30f759225f89edcc18cb403b93f27bf4231223f7",
  "tags": [
    "license:apache-2.0",
    "region:us"
  ],
  "gated": false,
  "likes": 7,
  "license": "apache-2.0",
  "private": false,
  "language": [],
  "downloads": 1513092,
  "publisher": "hallucinations-leaderboard",
  "created_on": "2023-11-21T11:44:46.000Z",
  "dataset_id": "huggingface.co/datasets/hallucinations-leaderboard/results",
  "dataset_url": "https://huggingface.co/datasets/hallucinations-leaderboard/results",
  "description": null,
  "observed_at": "2026-07-06T00:55:46.488Z",
  "pretty_name": null,
  "card_license": "apache-2.0",
  "card_languages": [],
  "size_categories": [],
  "task_categories": [],
  "last_modified_on": "2024-10-31T20:32:52.000Z",
  "observation_week": "2026-W28",
  "card_task_categories": []
}