{
 "id": "MaLA-LM/mala-monolingual-split",
 "owner": "MaLA-LM",
 "name": "mala-monolingual-split",
 "downloads": 3690,
 "likes": 4,
 "last_modified": "2026-07-24T17:24:43.000Z",
 "stated_licence": "odc-by",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "@inproceedings{ji2026mala,\n  title     = {MaLA: A Corpus and Data Mix for Massive Language Adaptation of Large Language Models},\n  author    = {Ji, Shaoxiong and Li, Zihao and Paavola, Jaakko and Lin, Peiqin and Chen, Pinzhen and O'Brien, Dayy{\\'a}n and Luo, Hengyu and Sch{\\\"u}tze, Hinrich and Tiedemann, J{\\\"o}rg and Haddow, Barry},\n  booktitle = {Proceedings of Conference on Language Modeling (COLM 2026)},\n  year      = {2026},\n  url       = {https://www.olaresearch.org/MaLA/}\n}",
 "signal": "permissive",
 "reason": "The declared licence (odc-by) is classified as permissive.",
 "revision": "7b44b8a7b0ee4d8df157ed97640abe974c52f8d0",
 "stated_evidence": "https://huggingface.co/datasets/MaLA-LM/mala-monolingual-split/blob/7b44b8a7b0ee4d8df157ed97640abe974c52f8d0/README.md",
 "file_evidence": "https://huggingface.co/datasets/MaLA-LM/mala-monolingual-split/tree/7b44b8a7b0ee4d8df157ed97640abe974c52f8d0",
 "card_nc": false
}