{
 "id": "opencsg/Fineweb-Edu-Chinese-V2.1",
 "owner": "opencsg",
 "name": "Fineweb-Edu-Chinese-V2.1",
 "downloads": 39195,
 "likes": 81,
 "last_modified": "2026-01-28T00:36:48.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "@misc{yu2025opencsgchinesecorpusseries,\n      title={OpenCSG Chinese Corpus: A Series of High-quality Chinese Datasets for LLM Training}, \n      author={Yijiong Yu and Ziyun Dai and Zekun Wang and Wei Wang and Ran Chen and Ji Pei},\n      year={2025},\n      eprint={2501.08197},\n      archivePrefix={arXiv},\n      primaryClass={cs.CL},\n      url={https://arxiv.org/abs/2501.08197}, \n}",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive."
}