{
 "id": "google/smol",
 "owner": "google",
 "name": "smol",
 "downloads": 7687,
 "likes": 137,
 "last_modified": "2026-08-06T20:16:31.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "translation"
 ],
 "citation": "@misc{caswell2025smol,\n      title={{SMOL: Professionally translated parallel data for 115 under-represented languages}},\n      author={Isaac Caswell and Elizabeth Nielsen and Jiaming Luo and Colin Cherry and Geza Kovacs and Hadar Shemtov and Partha Talukdar and Dinesh Tewari and Baba Mamadi Diane and Koulako Moussa Doumbouya and Djibrila Diane and Solo Farabado Ciss\u00e9 and Edoardo Ferrante and Alessandro Guasoni and Mamadou K. Keita and Sudhamoy DebBarma and Ali Kuzhuget and David Anugraha and Muhammad Ravi Shulthan Habibi and Sina Ahmadi and Mingfei Lau and Jonathan Eng},\n      year={2025},\n      eprint={2502.12301},\n      archivePrefix={arXiv},\n      primaryClass={cs.CL},\n      url={https://arxiv.org/abs/2502.12301},\n}\n\n@inproceedings{jones-etal-2023-gatitos,\n    title = {{\"GATITOS: Using a New Multilingual Lexicon for Low-resource Machine Translation\"}},\n    author = \"Jones, Alexander  and\n      Caswell, Isaac  and\n      Firat, Orhan  and\n      Saxena, Ishank\",\n    editor = \"Bouamor, Houda  and\n      Pino, Juan  and\n      Bali, Kalika\",\n    booktitle = \"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing\",\n    month = dec,\n    year = \"2023\",\n    address = \"Singapore\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2023.emnlp-main.26/\",\n    doi = \"10.18653/v1/2023.emnlp-main.26\",\n    pages = \"371--405\",\n    abstract = \"Modern machine translation models and language models are able to transla",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive."
}