{
 "id": "sail/regmix-data",
 "owner": "sail",
 "name": "regmix-data",
 "downloads": 3517,
 "likes": 4,
 "last_modified": "2024-09-12T08:12:18.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@article{liu2024regmix,\n  title={RegMix: Data Mixture as Regression for Language Model Pre-training},\n  author={Liu, Qian and Zheng, Xiaosen and Muennighoff, Niklas and Zeng, Guangtao and Dou, Longxu and Pang, Tianyu and Jiang, Jing and Lin, Min},\n  journal={arXiv preprint arXiv:2407.01492},\n  year={2024}\n}",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "0db514aa78fd8ce3db09332d7640831ebf15a54c",
 "stated_evidence": "https://huggingface.co/datasets/sail/regmix-data/blob/0db514aa78fd8ce3db09332d7640831ebf15a54c/README.md",
 "file_evidence": "https://huggingface.co/datasets/sail/regmix-data/tree/0db514aa78fd8ce3db09332d7640831ebf15a54c",
 "card_nc": false
}