{
 "id": "uctnlp/mzansi-text-tokenized",
 "owner": "uctnlp",
 "name": "mzansi-text-tokenized",
 "downloads": 413,
 "likes": 0,
 "last_modified": "2026-08-10T19:35:32.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@misc{lombard2026mzansitextmzansilmopencorpus,\n      title={MzansiText and MzansiLM: An Open Corpus and Decoder-Only Language Model for South African Languages},\n      author={Anri Lombard and Simbarashe Mawere and Temi Aina and Ethan Wolff and Sbonelo Gumede and Elan Novick and Francois Meyer and Jan Buys},\n      year={2026},\n      eprint={2603.20732},\n      archivePrefix={arXiv},\n      primaryClass={cs.CL},\n      url={https://arxiv.org/abs/2603.20732},\n}",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "7dab1ebf1e1f00ea967a3845aea0acde6cfc0792",
 "stated_evidence": "https://huggingface.co/datasets/uctnlp/mzansi-text-tokenized/blob/7dab1ebf1e1f00ea967a3845aea0acde6cfc0792/README.md",
 "file_evidence": "https://huggingface.co/datasets/uctnlp/mzansi-text-tokenized/tree/7dab1ebf1e1f00ea967a3845aea0acde6cfc0792",
 "card_nc": false
}