{
 "id": "mimir-lcm/fineweb-edu-350BT-sentence-split",
 "owner": "mimir-lcm",
 "name": "fineweb-edu-350BT-sentence-split",
 "downloads": 1125,
 "likes": 0,
 "last_modified": "2026-05-26T05:15:21.000Z",
 "stated_licence": "odc-by",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@misc{lozhkov2024fineweb-edu,\n    author       = { Lozhkov, Anton and Ben Allal, Loubna and von Werra, Leandro and Wolf, Thomas },  \n    title        = { FineWeb-Edu: the Finest Collection of Educational Content }, \n    year         = 2024,  \n    url          = { https://huggingface.co/datasets/HuggingFaceFW/fineweb-edu },  \n    doi          = { 10.57967/hf/2497 },\n    publisher    = { Hugging Face }\n}\n\n@misc{musacchio2026mimirlargescalemultilingualconcept,\n      title={Mimir: Large-scale Multilingual Concept Modeling}, \n      author={Elio Musacchio and Lucia Siciliani and Pierpaolo Basile},\n      year={2026},\n      eprint={2605.25263},\n      archivePrefix={arXiv},\n      primaryClass={cs.CL},\n      url={https://arxiv.org/abs/2605.25263}, \n}",
 "signal": "permissive",
 "reason": "The declared licence (odc-by) is classified as permissive.",
 "revision": "c972b59dbd294c281898d1cd940e61dbf61b9d15",
 "stated_evidence": "https://huggingface.co/datasets/mimir-lcm/fineweb-edu-350BT-sentence-split/blob/c972b59dbd294c281898d1cd940e61dbf61b9d15/README.md",
 "file_evidence": "https://huggingface.co/datasets/mimir-lcm/fineweb-edu-350BT-sentence-split/tree/c972b59dbd294c281898d1cd940e61dbf61b9d15",
 "card_nc": false
}