{
 "id": "quinnlue/regmix-data-sample-stella",
 "owner": "quinnlue",
 "name": "regmix-data-sample-stella",
 "downloads": 367,
 "likes": 0,
 "last_modified": "2026-07-22T16:14:52.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-classification",
  "feature-extraction"
 ],
 "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": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "f9dfaef7155be454943230730821978512ba5005",
 "stated_evidence": "https://huggingface.co/datasets/quinnlue/regmix-data-sample-stella/blob/f9dfaef7155be454943230730821978512ba5005/README.md",
 "file_evidence": "https://huggingface.co/datasets/quinnlue/regmix-data-sample-stella/tree/f9dfaef7155be454943230730821978512ba5005",
 "card_nc": false
}