{
 "id": "hypaai/Hypa-Text-10k",
 "owner": "hypaai",
 "name": "Hypa-Text-10k",
 "downloads": 78,
 "likes": 1,
 "last_modified": "2026-05-21T14:26:08.000Z",
 "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",
  "translation"
 ],
 "citation": "@misc{hypaai2026hypatext10k,\n  title        = {Hypa-Text-10k: A Multilingual Instruction Corpus Subset for Underrepresented Languages},\n  author       = {{Hypa Intelligence}},\n  year         = {2026},\n  publisher    = {Hugging Face},\n  howpublished = {\\url{https://huggingface.co/datasets/hypaai/Hypa-Text-10k}},\n  note         = {Apache 2.0 License. 10k stratified subset of the 17M-row Hypa training corpus used for Hypa-Gemma 4 and Hypa-Llama 3.1.}\n}",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "7a442cf5b029fab79540b093c9ef9abae5e30e96",
 "stated_evidence": "https://huggingface.co/datasets/hypaai/Hypa-Text-10k/blob/7a442cf5b029fab79540b093c9ef9abae5e30e96/README.md",
 "file_evidence": "https://huggingface.co/datasets/hypaai/Hypa-Text-10k/tree/7a442cf5b029fab79540b093c9ef9abae5e30e96",
 "card_nc": false
}