{
 "id": "40u1d10t/to-train-my-model",
 "owner": "40u1d10t",
 "name": "to-train-my-model",
 "downloads": 1172,
 "likes": 1,
 "last_modified": "2026-04-13T22:17:16.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation",
  "fill-mask"
 ],
 "citation": "@misc{nguyen2024culturay,\n      title={CulturaY: A Large Cleaned Multilingual Dataset of 75 Languages}, \n      author={Thuat Nguyen, Huu Nguyen and Thien Nguyen},\n      year={2024},\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "6b6d6e746202488efa76662d56b1484d4c31639c",
 "stated_evidence": "https://huggingface.co/datasets/40u1d10t/to-train-my-model/blob/6b6d6e746202488efa76662d56b1484d4c31639c/README.md",
 "file_evidence": "https://huggingface.co/datasets/40u1d10t/to-train-my-model/tree/6b6d6e746202488efa76662d56b1484d4c31639c",
 "card_nc": false
}