{
 "id": "tiiuae/falcon-refinedweb",
 "owner": "tiiuae",
 "name": "falcon-refinedweb",
 "downloads": 16650,
 "likes": 978,
 "last_modified": "2023-06-20T12:38:07.000Z",
 "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": "@article{refinedweb,\n  title={The {R}efined{W}eb dataset for {F}alcon {LLM}: outperforming curated corpora with web data, and web data only},\n  author={Guilherme Penedo and Quentin Malartic and Daniel Hesslow and Ruxandra Cojocaru and Alessandro Cappelli and Hamza Alobeidli and Baptiste Pannier and Ebtesam Almazrouei and Julien Launay},\n  journal={arXiv preprint arXiv:2306.01116},\n  eprint={2306.01116},\n  eprinttype = {arXiv},\n  url={https://arxiv.org/abs/2306.01116},\n  year={2023}\n}",
 "signal": "permissive",
 "reason": "The declared licence (odc-by) is classified as permissive."
}