{
 "id": "HuggingFaceFW/fineweb-2",
 "owner": "HuggingFaceFW",
 "name": "fineweb-2",
 "downloads": 133446,
 "likes": 919,
 "last_modified": "2025-10-27T18:32:07.000Z",
 "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": "@misc{penedo2025fineweb2pipelinescale,\n  title={FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language}, \n  author={Guilherme Penedo and Hynek Kydl\u00ed\u010dek and Vinko Sabol\u010dec and Bettina Messmer and Negar Foroutan and Amir Hossein Kargaran and Colin Raffel and Martin Jaggi and Leandro Von Werra and Thomas Wolf},\n  year={2025},\n  eprint={2506.20920},\n  archivePrefix={arXiv},\n  primaryClass={cs.CL},\n  url={https://arxiv.org/abs/2506.20920}, \n}",
 "signal": "permissive",
 "reason": "The declared licence (odc-by) is classified as permissive."
}