{
 "id": "anisoleai/fineweb-tokenized",
 "owner": "anisoleai",
 "name": "fineweb-tokenized",
 "downloads": 88891,
 "likes": 39,
 "last_modified": "2026-05-29T12:35:53.000Z",
 "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{anisoleai2026fineweb-tokenized,\n  title        = {FineWeb Tokenized},\n  author       = {AnisoleAI},\n  year         = {2026},\n  howpublished = {Hugging Face Datasets},\n  url          = {https://huggingface.co/datasets/anisoleai/fineweb-tokenized},\n}\n\n@misc{penedo2024fineweb,\n  title         = {FineWeb: decanting the web for the finest text data at scale},\n  author        = {Guilherme Penedo and Hynek Kydl{\\'i}{\\v{c}}ek and Loubna Ben allal\n                   and Anton Lozhkov and Margaret Mitchell and Colin Raffel\n                   and Leandro Von Werra and Thomas Wolf},\n  year          = {2024},\n  eprint        = {2406.17557},\n  archivePrefix = {arXiv},\n  primaryClass  = {cs.NE},\n}",
 "signal": "permissive",
 "reason": "The declared licence (odc-by) is classified as permissive."
}