{
 "id": "Omartificial-Intelligence-Space/FineWeb2-MSA",
 "owner": "Omartificial-Intelligence-Space",
 "name": "FineWeb2-MSA",
 "downloads": 501,
 "likes": 2,
 "last_modified": "2024-12-15T11:17:57.000Z",
 "stated_licence": "odc-by",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "If you use this dataset, please cite it as follows:\n\n```bibtex\n@software{penedo2024fineweb-2,\n  author = {Penedo, Guilherme and Kydlíček, Hynek and Sabolčec, Vinko and Messmer, Bettina and Foroutan, Negar and Jaggi, Martin and von Werra, Leandro and Wolf, Thomas},\n  title = {FineWeb2: A sparkling update with 1000s of languages},\n  month = dec,\n  year = 2024,\n  doi = {10.57967/hf/3744},\n  url = {https://huggingface.co/datasets/HuggingFaceFW/fineweb-2}\n}",
 "signal": "permissive",
 "reason": "The declared licence (odc-by) is classified as permissive.",
 "revision": "a9a80002254a08a413f46455bf9de2d409e4e91b",
 "stated_evidence": "https://huggingface.co/datasets/Omartificial-Intelligence-Space/FineWeb2-MSA/blob/a9a80002254a08a413f46455bf9de2d409e4e91b/README.md",
 "file_evidence": "https://huggingface.co/datasets/Omartificial-Intelligence-Space/FineWeb2-MSA/tree/a9a80002254a08a413f46455bf9de2d409e4e91b",
 "card_nc": false
}