{
 "id": "ma1993/Markhor-Data",
 "owner": "ma1993",
 "name": "Markhor-Data",
 "downloads": 10,
 "likes": 0,
 "last_modified": "2026-09-28T01:29:09.000Z",
 "stated_licence": null,
 "stated_from": "none",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [
  "LICENSE"
 ],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation",
  "text-classification",
  "question-answering"
 ],
 "citation": "@inproceedings{ali2026markhor,\n  title     = {Markhor: A Framework for Adapting LLMs to Urdu via Alignment-Free Tokenizer Replacement},\n  author    = {Ali, Muhammad Zain and Wang, Yuxia and Manzoor, Muhammad Arslan and Smith, Tony and Pfahringer, Bernhard},\n  booktitle = {Findings of the Association for Computational Linguistics: AACL-IJCNLP 2026},\n  year      = {2026}\n}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "0f712f4686f8cc2d77d5f895765e78ad29be269c",
 "stated_evidence": "https://huggingface.co/datasets/ma1993/Markhor-Data/blob/0f712f4686f8cc2d77d5f895765e78ad29be269c/README.md",
 "file_evidence": "https://huggingface.co/datasets/ma1993/Markhor-Data/blob/0f712f4686f8cc2d77d5f895765e78ad29be269c/LICENSE",
 "card_nc": false
}