Tucano

📣 Tucanos are fun, but we also want to help build tools for other languages! New releases of the Tucano project, as well as new resources for other low-resource languages, will soon be available in our new organization: Polyglot! Polyglot is a research project from the University of Bonn, where we seek to aid in the development of foundation models for low-resource languages. So, if you like Tucanos, go follow Polyglot to stay updated with our new releases. 📣

Publications 📚

• ViTucano: A Portuguese Vision Assistant | GitHub | Collection |
• Tucano: Advancing Neural Text Generation for Portuguese | GitHub | Collection | Paper |
• TeenyTinyLlama: open-source tiny language models trained in Brazilian Portuguese | GitHub | Collection | Paper |

News 🚀

• [24/07/2025] Peer-reviewed article "Tucano: Advancing Neural Text Generation for Portuguese" is published in Patterns, with all models and datasets released on Hugging Face.
• [13/01/2025] We release ViTucano, a pair of vision assistants natively pretrained in Portuguese (ViTucano-1b5-v1, ViTucano-2b8-v1).
• [13/01/2025] We release the datasets used to pretrain and fine-tune the ViTucano models: ViTucano-Pretrain and ViTucano-SFT.
• [29/11/2024] Tucano is mentioned on Deutsche Welle: "Cientistas criam maior banco de dados em português para IA".
• [27/11/2024] Tucano video presentation at the C4AI (USP) [available on YouTube].
• [12/11/2024] "Tucano: Advancing Neural Text Generation for Portuguese" is published as a preprint on ArXiv, with all models and datasets released on Hugging Face.

Community Contributions 🤝

• Demo on how to run inference on ViTucano.
• Demo on how to run inference on Tucano.
• Demo on how to create a simple Chat UI for Tucano using Gradio.
• Tucano OpenVINO is a ported version of Tucano-2b4-Instruct optimized for Intel openVINO inference technology.