{
 "id": "legmlai/finefrench-v1",
 "owner": "legmlai",
 "name": "finefrench-v1",
 "downloads": 549,
 "likes": 1,
 "last_modified": "2025-06-30T13:35:31.000Z",
 "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": "@dataset{finefrench2024,\n  title={Fine-French: La Crème de la Crème du Web Français},\n  author={Alhajar, Mohamad and {legml.ai}},\n  year={2024},\n  publisher={Hugging Face},\n  url={https://huggingface.co/datasets/legmlai/finefrench},\n  note={AI-curated French web corpus filtered from 125M to 66M high-quality documents using GPT-4 synthetic annotation},\n  license={ODC-By 1.0}\n}",
 "signal": "permissive",
 "reason": "The declared licence (odc-by) is classified as permissive.",
 "revision": "a03b139cf919f810f921c333cd8bc61238851e64",
 "stated_evidence": "https://huggingface.co/datasets/legmlai/finefrench-v1/blob/a03b139cf919f810f921c333cd8bc61238851e64/README.md",
 "file_evidence": "https://huggingface.co/datasets/legmlai/finefrench-v1/tree/a03b139cf919f810f921c333cd8bc61238851e64",
 "card_nc": false
}