{
 "id": "BAAI/CCI3-Data",
 "owner": "BAAI",
 "name": "CCI3-Data",
 "downloads": 909,
 "likes": 40,
 "last_modified": "2024-11-11T12:28:09.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": "auto",
 "tasks": [],
 "citation": "@misc{wang2024cci30hqlargescalechinesedataset,\n      title={CCI3.0-HQ: a large-scale Chinese dataset of high quality designed for pre-training large language models}, \n      author={Liangdong Wang and Bo-Wen Zhang and Chengwei Wu and Hanyu Zhao and Xiaofeng Shi and Shuhao Gu and Jijie Li and Quanyue Ma and TengFei Pan and Guang Liu},\n      year={2024},\n      eprint={2410.18505},\n      archivePrefix={arXiv},\n      primaryClass={cs.CL},\n      url={https://arxiv.org/abs/2410.18505}, \n}",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "3747609a85b17a8fabb5f45ef34e3ea42ee16330",
 "stated_evidence": "https://huggingface.co/datasets/BAAI/CCI3-Data/blob/3747609a85b17a8fabb5f45ef34e3ea42ee16330/README.md",
 "file_evidence": "https://huggingface.co/datasets/BAAI/CCI3-Data/tree/3747609a85b17a8fabb5f45ef34e3ea42ee16330",
 "card_nc": false
}