{
 "id": "epfml/FineWeb-HQ",
 "owner": "epfml",
 "name": "FineWeb-HQ",
 "downloads": 1411474,
 "likes": 31,
 "last_modified": "2025-09-30T10:12:10.000Z",
 "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\n{messmer2025multilingdatacomp,\ntitle={Enhancing Multilingual LLM Pretraining with Model-Based Data Selection},\nauthor={Bettina Messmer and Vinko Sabol\u010dec and Martin Jaggi},\njournal={arXiv},\nyear={2025},\nurl={https://arxiv.org/abs/2502.10361},\n}",
 "signal": "permissive",
 "reason": "The declared licence (odc-by) is classified as permissive."
}