ViTucano is our first attempt at creating a vision assistant natively pretrained in Portuguese. ViTucano is built on top of the Tucano series.
AI & ML interests
Developing foundation models for low-resource languages.
Recent Activity
Organization Card
📣 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 Assitant | 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.
models
12

TucanoBR/BERTimbau-base-text-filter
Text Classification
•
0.1B
•
Updated
•
3

TucanoBR/XGBClassifier-text-filter
Updated

TucanoBR/BERTimbau-large-text-filter
Text Classification
•
0.3B
•
Updated
•
4

TucanoBR/XGBRegressor-text-filter
Updated

TucanoBR/Tucano-1b1-Instruct
Text Generation
•
1B
•
Updated
•
131
•
3

TucanoBR/Tucano-160m
Text Generation
•
0.2B
•
Updated
•
1.29k
•
3

TucanoBR/Tucano-630m
Text Generation
•
0.6B
•
Updated
•
1.11k
•
3

TucanoBR/Tucano-1b1
Text Generation
•
1B
•
Updated
•
894
•
3

TucanoBR/Tucano-2b4
Text Generation
•
2B
•
Updated
•
1.17k
•
5

TucanoBR/Tucano-2b4-Instruct
Text Generation
•
2B
•
Updated
•
1.25k
•
5
datasets
8
TucanoBR/GigaVerbo-Text-Filter
Viewer
•
Updated
•
110k
•
109
•
1
TucanoBR/GigaVerbo
Viewer
•
Updated
•
145M
•
651
•
21
TucanoBR/ViTucano-Pretrain
Updated
•
92
•
1
TucanoBR/ViTucano-SFT
Viewer
•
Updated
•
517k
•
93
•
2
TucanoBR/Tucano-SFT
Viewer
•
Updated
•
680k
•
141
•
2
TucanoBR/alpaca-eval-pt
Viewer
•
Updated
•
805
•
14
TucanoBR/lambada-pt
Viewer
•
Updated
•
5.15k
•
22
•
2
TucanoBR/wikipedia-PT
Viewer
•
Updated
•
1.1M
•
35