{
 "id": "Polygl0t/tokenizers",
 "owner": "Polygl0t",
 "name": "tokenizers",
 "downloads": 500,
 "likes": 0,
 "last_modified": "2026-03-05T09:01:22.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "```latex\n@misc{correa2026tucano2cool,\n      title={{Tucano 2 Cool: Better Open Source LLMs for Portuguese}}, \n      author={Nicholas Kluge Corr{\\^e}a and Aniket Sen and Shiza Fatimah and Sophia Falk and Lennard Landgraf and Julia Kastner and Lucie Flek},\n      year={2026},\n      eprint={2603.03543},\n      archivePrefix={arXiv},\n      primaryClass={cs.CL},\n      url={https://arxiv.org/abs/2603.03543}, \n}\n\n@misc{shiza2026lilmoo,\n      title={{Raising Bars, Not Parameters: LilMoo Compact Language Model for Hindi}}, \n      author={Shiza Fatimah and Aniket Sen and Sophia Falk and Florian Mai and Lucie Flek and Nicholas Kluge Corr{\\^e}a},\n      year={2026},\n      eprint={2603.03508},\n      archivePrefix={arXiv},\n      primaryClass={cs.CL},\n      url={https://arxiv.org/abs/2603.03508}, \n}\n\n@misc{fatimah2026liltii,\n  title={{LilTii: A 0.6B Bengali Language Model that Outperforms Qwen}},\n  author={Shiza Fatimah and Aniket Sen and Sophia Falk and Florian Mai and Lucie Flek and Nicholas Kluge Corr{\\^e}a},\n  year={2026},\n  howpublished={\\url{https://hf.co/blog/Polygl0t/liltii}}\n}\n```",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "e8da924a7752bd754b034dbd76a316cd811bc6a3",
 "stated_evidence": "https://huggingface.co/datasets/Polygl0t/tokenizers/blob/e8da924a7752bd754b034dbd76a316cd811bc6a3/README.md",
 "file_evidence": "https://huggingface.co/datasets/Polygl0t/tokenizers/tree/e8da924a7752bd754b034dbd76a316cd811bc6a3",
 "card_nc": false
}