{
 "id": "opencsg/chinese-cosmopedia",
 "owner": "opencsg",
 "name": "chinese-cosmopedia",
 "downloads": 1633,
 "likes": 82,
 "last_modified": "2025-01-15T04:48:47.000Z",
 "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.",
 "revision": "b15fa10b9ec8ac30a719b46eead5ffbdaf644d50",
 "stated_evidence": "https://huggingface.co/datasets/opencsg/chinese-cosmopedia/blob/b15fa10b9ec8ac30a719b46eead5ffbdaf644d50/README.md",
 "file_evidence": "https://huggingface.co/datasets/opencsg/chinese-cosmopedia/tree/b15fa10b9ec8ac30a719b46eead5ffbdaf644d50",
 "card_nc": false
}