{
 "id": "natolambert/rlhf-library",
 "owner": "natolambert",
 "name": "rlhf-library",
 "downloads": 48,
 "likes": 3,
 "last_modified": "2025-09-17T20:39:19.000Z",
 "stated_licence": "odc-by",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@book{rlhf2024,\n  author = {Nathan Lambert},\n  title = {Reinforcement Learning from Human Feedback},\n  year = {2025},\n  publisher = {Online},\n  url = {https://rlhfbook.com}\n}",
 "signal": "permissive",
 "reason": "The declared licence (odc-by) is classified as permissive.",
 "revision": "1a7b0c87e67f9f5c2bf61b818bf36e343184280b",
 "stated_evidence": "https://huggingface.co/datasets/natolambert/rlhf-library/blob/1a7b0c87e67f9f5c2bf61b818bf36e343184280b/README.md",
 "file_evidence": "https://huggingface.co/datasets/natolambert/rlhf-library/tree/1a7b0c87e67f9f5c2bf61b818bf36e343184280b",
 "card_nc": false
}