{
 "id": "idleengine/fineweb",
 "owner": "idleengine",
 "name": "fineweb",
 "downloads": 6957,
 "likes": 0,
 "last_modified": "2026-08-31T16:52:14.000Z",
 "stated_licence": "odc-by",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "@inproceedings{\n  penedo2024the,\n  title={The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale},\n  author={Guilherme Penedo and Hynek Kydl{\\'\\i}{\\v{c}}ek and Loubna Ben allal and Anton Lozhkov and Margaret Mitchell and Colin Raffel and Leandro Von Werra and Thomas Wolf},\n  booktitle={The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track},\n  year={2024},\n  url={https://openreview.net/forum?id=n6SCkn2QaG}\n}",
 "signal": "permissive",
 "reason": "The declared licence (odc-by) is classified as permissive."
}