Brazilian Portuguese Image Captioning with Transformers: A Study on Cross-Native-Translated Dataset Paper • 2602.00393 • Published Jan 30 • 1
ViTucano-v1 Collection ViTucano is our first attempt at creating a vision assistant natively pretrained in Portuguese. ViTucano is built on top of the Tucano series. • 5 items • Updated May 31, 2025 • 2
Tucano 2 Cool: Better Open Source LLMs for Portuguese Paper • 2603.03543 • Published 11 days ago • 6
Tucano2 Collection An open suite of large language models (LLMs) with 0.5-3.7 billion parameters, designed to address the gap in open-source development for Portuguese. • 33 items • Updated 4 days ago • 12
ViTucano-v1 (Portuguese) Collection ViTucano is our first attempt at creating a vision assistant natively pretrained in Portuguese. ViTucano is built on top of the Tucano series. • 5 items • Updated 12 days ago • 1
Tucano (Portuguese) Collection Tucano is a series of decoder-transformers based on the Llama 2 architecture, natively pre-trained in Portuguese. • 17 items • Updated 12 days ago • 1
view article Article Leveraging Pre-trained Language Model Checkpoints for Encoder-Decoder Models Nov 9, 2020 • 16
Tucano: Advancing Neural Text Generation for Portuguese Paper • 2411.07854 • Published Nov 12, 2024 • 9
TeenyTinyLlama: open-source tiny language models trained in Brazilian Portuguese Paper • 2401.16640 • Published Jan 30, 2024 • 11
💾 Datasets for Portuguese Image Captioning Collection Multimodal datasets for Portuguese image captioning, by LAICSI (IFES). • 9 items • Updated Dec 28, 2025 • 2
🤖 VEDs for Brazilian Portuguese IC Collection A Comparative Evaluation of Transformer-Based Vision Encoder-Decoder Models for Brazilian Portuguese Image Captioning, by LAICSI (IFES). • 4 items • Updated Dec 28, 2025 • 1