{
 "id": "openbmb/Ultra-FineWeb-L1",
 "owner": "openbmb",
 "name": "Ultra-FineWeb-L1",
 "downloads": 10558,
 "likes": 203,
 "last_modified": "2026-08-20T07:36:30.000Z",
 "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{wang2025ultrafineweb,\n  title={{Ultra-FineWeb}: Efficient Data Filtering and Verification for High-Quality LLM Training Data},\n  author={Yudong Wang and Zixuan Fu and Jie Cai and Peijun Tang and Hongya Lyu and Yewei Fang and Zhi Zheng and Jie Zhou and Guoyang Zeng and Chaojun Xiao and Xu Han and Zhiyuan Liu},\n  year={2025},\n  eprint={2505.05427},\n  archivePrefix={arXiv},\n  primaryClass={cs.CL}\n}\n\n@misc{ultra-fineweb-l1,\n  title={Ultra-FineWeb-L1},\n  author={Junshao Guo and Shuaikang Xue and Xiaofei Yang and Chuyue Zhou and Qiang Yin and Qingyang Yuan and Qiang Ma and Yuzhou Zhang and Jie Zhou and Chaojun Xiao and Yudong Wang and Zhiyuan Liu},\n  year={2026},\n  url={https://huggingface.co/datasets/openbmb/Ultra-FineWeb-L1},\n  publisher={Hugging Face}\n}",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive."
}