{
 "id": "agentlans/m-a-p-FineFineWeb-sample",
 "owner": "agentlans",
 "name": "m-a-p-FineFineWeb-sample",
 "downloads": 64,
 "likes": 0,
 "last_modified": "2026-06-15T12:06:12.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-classification",
  "text-generation"
 ],
 "citation": "@misc{map2024finefineweb,\n  title={FineFineWeb: A Comprehensive Study on Fine-grained Domain Web Corpus},\n  url={https://huggingface.co/datasets/m-a-p/FineFineWeb},\n  author={Zhang, Ge and Du, Xinrun and Yu, Zhimiao and Wang, Zili and Wang, Zekun and Guo, Shuyue and Zheng, Tianyu and Zhu, Kang and Liu, Jerry and Yue, Shawn and Liu, Binbin and Peng, Zhongyuan and Yao, Yifan and Yang, Jack and Li, Ziming and Zhang, Bingni and Liu, Minghao and Liu, Tianyu and Gao, Yang and Chen, Wenhu and Zhou, Xiaohuan and Liu, Qian and Wang, Taifeng and Huang, Wenhao},\n  publisher={Hugging Face},\n  version={v0.1.0},\n  month={December},\n  year={2024}\n}",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "bcd33c5efc61487f8cc6cf034ec10e09ea0fd1f5",
 "stated_evidence": "https://huggingface.co/datasets/agentlans/m-a-p-FineFineWeb-sample/blob/bcd33c5efc61487f8cc6cf034ec10e09ea0fd1f5/README.md",
 "file_evidence": "https://huggingface.co/datasets/agentlans/m-a-p-FineFineWeb-sample/tree/bcd33c5efc61487f8cc6cf034ec10e09ea0fd1f5",
 "card_nc": false
}