{
 "id": "nicholasKluge/Pt-Corpus-tokenized",
 "owner": "nicholasKluge",
 "name": "Pt-Corpus-tokenized",
 "downloads": 39,
 "likes": 0,
 "last_modified": "2024-06-18T12:06:16.000Z",
 "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{correa24ttllama,\n  title = {TeenyTinyLlama: open-source tiny language models trained in Brazilian Portuguese},\n  author = {Corr{\\^e}a, Nicholas Kluge and Falk, Sophia and Fatimah, Shiza and Sen, Aniket and De Oliveira, Nythamar},\n  journal={arXiv preprint arXiv:2401.16640},\n  year={2024}\n}\n\n@misc{correa24ttllama,\n  doi = {10.1016/j.mlwa.2024.100558},\n  url = {https://www.sciencedirect.com/science/article/pii/S2666827024000343},\n  title = {TeenyTinyLlama: open-source tiny language models trained in Brazilian Portuguese},\n  author = {Corr{\\^e}a, Nicholas Kluge and Falk, Sophia and Fatimah, Shiza and Sen, Aniket and De Oliveira, Nythamar},\n  journal={Machine Learning With Applications},\n  publisher = {Springer},\n  year={2024}\n}\n```",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "bf0d195d1bf2ca48117ac4d21a98ccd71857fff6",
 "stated_evidence": "https://huggingface.co/datasets/nicholasKluge/Pt-Corpus-tokenized/blob/bf0d195d1bf2ca48117ac4d21a98ccd71857fff6/README.md",
 "file_evidence": "https://huggingface.co/datasets/nicholasKluge/Pt-Corpus-tokenized/tree/bf0d195d1bf2ca48117ac4d21a98ccd71857fff6",
 "card_nc": false
}