{
 "id": "krisbailey/falcon-refinedweb-1B",
 "owner": "krisbailey",
 "name": "falcon-refinedweb-1B",
 "downloads": 46,
 "likes": 0,
 "last_modified": "2026-01-22T20:06:35.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "@article{penedo2023refinedweb,\n  title={The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only},\n  author={Penedo, Guilherme and Malartic, Quentin and Hesslow, Daniel and Cojocaru, Ruxandra and Cappelli, Alessandro and Alobeidli, Hamza and Pannier, Baptiste and Almazrouei, Ebtesam and Launay, Julien},\n  journal={arXiv preprint arXiv:2306.01116},\n  year={2023}\n}",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "5b4a1a01fb8ef4dac6ca24dacf292a5e32db0e7b",
 "stated_evidence": "https://huggingface.co/datasets/krisbailey/falcon-refinedweb-1B/blob/5b4a1a01fb8ef4dac6ca24dacf292a5e32db0e7b/README.md",
 "file_evidence": "https://huggingface.co/datasets/krisbailey/falcon-refinedweb-1B/tree/5b4a1a01fb8ef4dac6ca24dacf292a5e32db0e7b",
 "card_nc": false
}