{
 "id": "Skylion007/openwebtext",
 "owner": "Skylion007",
 "name": "openwebtext",
 "downloads": 36410,
 "likes": 549,
 "last_modified": "2026-07-21T21:22:12.000Z",
 "stated_licence": "cc0-1.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation",
  "fill-mask"
 ],
 "citation": "@misc{Gokaslan2019OpenWeb,\n    title={OpenWebText Corpus},\n    author={Gokaslan, Aaron and Cohen, Vanya and Pavlick, Ellie and Tellex, Stefanie},\n    howpublished={\\url{http://Skylion007.github.io/OpenWebTextCorpus}},\n    year={2019}\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc0-1.0) is classified as permissive.",
 "revision": "79d93d786212f7344586290adb811d4ae6a1762c",
 "stated_evidence": "https://huggingface.co/datasets/Skylion007/openwebtext/blob/79d93d786212f7344586290adb811d4ae6a1762c/README.md",
 "file_evidence": "https://huggingface.co/datasets/Skylion007/openwebtext/tree/79d93d786212f7344586290adb811d4ae6a1762c",
 "card_nc": false
}