{
 "id": "davanstrien/fineweb-edu-showcase",
 "owner": "davanstrien",
 "name": "fineweb-edu-showcase",
 "downloads": 24,
 "likes": 0,
 "last_modified": "2026-07-27T08:45:52.000Z",
 "stated_licence": "odc-by",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [
  {
   "id": "HuggingFaceFW/fineweb",
   "licence": "odc-by",
   "found": true,
   "evidence": "https://huggingface.co/datasets/HuggingFaceFW/fineweb/blob/9bb295ddab0e05d785b879661af7260fed5140fc/README.md"
  }
 ],
 "gated": false,
 "tasks": [
  "text-classification"
 ],
 "citation": "@inproceedings{penedo2024fineweb,\n  title={The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale},\n  author={Penedo, Guilherme and Kydl{\\'\\i}{\\v{c}}ek, Hynek and Lozhkov, Anton and Mitchell, Margaret and Raffel, Colin and Von Werra, Leandro and Wolf, Thomas and others},\n  booktitle={NeurIPS Datasets and Benchmarks},\n  year={2024}\n}",
 "signal": "permissive",
 "reason": "The declared licence (odc-by) is classified as permissive.",
 "revision": "0668acb730e1a702a0a348164adcae6e700fb5ea",
 "stated_evidence": "https://huggingface.co/datasets/davanstrien/fineweb-edu-showcase/blob/0668acb730e1a702a0a348164adcae6e700fb5ea/README.md",
 "file_evidence": "https://huggingface.co/datasets/davanstrien/fineweb-edu-showcase/tree/0668acb730e1a702a0a348164adcae6e700fb5ea",
 "card_nc": false
}