{
 "id": "codelion/finewiki-10M",
 "owner": "codelion",
 "name": "finewiki-10M",
 "downloads": 33,
 "likes": 2,
 "last_modified": "2025-11-02T16:00:39.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@article{sharma2025billion,\n  title={The 1 Billion Token Challenge: Finding the Perfect Pre-training Mix},\n  author={Sharma, Asankhaya},\n  year={2025},\n  url={https://huggingface.co/blog/codelion/optimal-dataset-mixing/}\n}",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "100f193a9b4c5158397cbc1c6b080f1f9f34fdef",
 "stated_evidence": "https://huggingface.co/datasets/codelion/finewiki-10M/blob/100f193a9b4c5158397cbc1c6b080f1f9f34fdef/README.md",
 "file_evidence": "https://huggingface.co/datasets/codelion/finewiki-10M/tree/100f193a9b4c5158397cbc1c6b080f1f9f34fdef",
 "card_nc": false
}