{
 "id": "epfml/FineWeb2-embedded",
 "owner": "epfml",
 "name": "FineWeb2-embedded",
 "downloads": 1400,
 "likes": 6,
 "last_modified": "2025-02-19T14:32:51.000Z",
 "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{messmer2025multilingdatacomp,\n  title={Enhancing Multilingual LLM Pretraining with Model-Based Data Selection}, \n  author={Bettina Messmer and Vinko Sabolčec and Martin Jaggi},\n  journal={arXiv},\n  year={2025},\n  url={https://arxiv.org/abs/2502.10361}, \n}",
 "signal": "permissive",
 "reason": "The declared licence (odc-by) is classified as permissive.",
 "revision": "4631ff28026f717d33016acebea7874f71872c15",
 "stated_evidence": "https://huggingface.co/datasets/epfml/FineWeb2-embedded/blob/4631ff28026f717d33016acebea7874f71872c15/README.md",
 "file_evidence": "https://huggingface.co/datasets/epfml/FineWeb2-embedded/tree/4631ff28026f717d33016acebea7874f71872c15",
 "card_nc": false
}