{
 "id": "CASIA-LM/ChineseWebText2.0",
 "owner": "CASIA-LM",
 "name": "ChineseWebText2.0",
 "downloads": 3266,
 "likes": 34,
 "last_modified": "2024-12-02T08:43:03.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "Please cite the paper if you use the data or code in this repo.\n\n```shell\n@misc{zhang2024chinesewebtext20largescalehighquality,\n      title={ChineseWebText 2.0: Large-Scale High-quality Chinese Web Text with Multi-dimensional and fine-grained information}, \n      author={Wanyue Zhang and Ziyong Li and Wen Yang and Chunlin Leng and Yinan Bai and Qianlong Du and Chengqing Zong and Jiajun Zhang},\n      year={2024},\n      eprint={2411.19668},\n      archivePrefix={arXiv},\n      primaryClass={cs.CL},\n      url={https://arxiv.org/abs/2411.19668}, \n}\n```",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "9b647306646e5ddd85cc239870fc39bfb60e9531",
 "stated_evidence": "https://huggingface.co/datasets/CASIA-LM/ChineseWebText2.0/blob/9b647306646e5ddd85cc239870fc39bfb60e9531/README.md",
 "file_evidence": "https://huggingface.co/datasets/CASIA-LM/ChineseWebText2.0/tree/9b647306646e5ddd85cc239870fc39bfb60e9531",
 "card_nc": false
}