{
 "id": "krisbailey/cosmopedia-100M",
 "owner": "krisbailey",
 "name": "cosmopedia-100M",
 "downloads": 55,
 "likes": 0,
 "last_modified": "2026-01-22T20:02:45.000Z",
 "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{benallal2024cosmopedia,\n      title={Cosmopedia: How to create large-scale synthetic data for pre-training}, \n      author={Loubna Ben Allal and Anton Lozhkov and Elie Bakouch and Gabriel Chimdyalwar and Leandro von Werra and Thomas Wolf},\n      year={2024},\n      journal={arXiv preprint arXiv:2402.13753}\n}",
 "signal": "permissive",
 "reason": "The declared licence (odc-by) is classified as permissive.",
 "revision": "e79d2860d4f3be3e394aee51617454122c86c39c",
 "stated_evidence": "https://huggingface.co/datasets/krisbailey/cosmopedia-100M/blob/e79d2860d4f3be3e394aee51617454122c86c39c/README.md",
 "file_evidence": "https://huggingface.co/datasets/krisbailey/cosmopedia-100M/tree/e79d2860d4f3be3e394aee51617454122c86c39c",
 "card_nc": false
}