{
 "id": "epfml/FineWeb2-HQ-Plus",
 "owner": "epfml",
 "name": "FineWeb2-HQ-Plus",
 "downloads": 25491,
 "likes": 1,
 "last_modified": "2026-10-12T11:06:21.000Z",
 "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": "@misc{turki2026crosslingualqualityclassifiersmultilingual,\n      title={Toward Cross-Lingual Quality Classifiers for Multilingual Pretraining Data Selection}, \n      author={Yassine Turki and Vinko Sabol\u010dec and Bettina Messmer and Martin Jaggi},\n      year={2026},\n      eprint={2604.20549},\n      archivePrefix={arXiv},\n      primaryClass={cs.CL},\n      url={https://arxiv.org/abs/2604.20549}, \n}",
 "signal": "permissive",
 "reason": "The declared licence (odc-by) is classified as permissive."
}