{
 "id": "floatai/TKEval",
 "owner": "floatai",
 "name": "TKEval",
 "downloads": 85,
 "likes": 2,
 "last_modified": "2024-12-11T12:53:59.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text2text-generation"
 ],
 "citation": "@inproceedings{chai2024tokenization,\n  title={Tokenization Falling Short: On Subword Robustness in Large Language Models},\n  author={Chai, Yekun and Fang, Yewei and Peng, Qiwei and Li, Xuhong},\n  booktitle={Findings of the Association for Computational Linguistics: EMNLP 2024},\n  pages={1582--1599},\n  year={2024}\n}",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "ecd7fa25d2239ea0e9473f5f37770761f2d0ff13",
 "stated_evidence": "https://huggingface.co/datasets/floatai/TKEval/blob/ecd7fa25d2239ea0e9473f5f37770761f2d0ff13/README.md",
 "file_evidence": "https://huggingface.co/datasets/floatai/TKEval/tree/ecd7fa25d2239ea0e9473f5f37770761f2d0ff13",
 "card_nc": false
}