Downloads · 30 days
1.6K
2% of all-time downloads
CEIA-UFG/Gemma-3-Gaia-PT-BR-4b-it
Gemma-3-Gaia-PT-BR-4b-it is a image-text-to-text model from CEIA-UFG. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as gemma.
GAIA is an open, state-of-the-art language model for Brazilian Portuguese. It was developed by continuously pre-training the google/gemma-3-4b-pt model on an extensive, high-quality corpus of Portuguese data.
Downloads · 30 days
1.6K
2% of all-time downloads
All-time downloads
70.3K
Public
Parameters
4.3B
16.4 GB on disk
Likes
164
Trending 1
Click a slice to open those files.
.safetensors8.6 GB · 100%
From the Hugging Face model README
GAIA is an open, state-of-the-art language model for Brazilian Portuguese. It was developed by continuously pre-training the google/gemma-3-4b-pt model on an extensive, high-quality corpus of Portuguese data.
The goal of GAIA is to democratize access to cutting-edge AI technology in Brazil, enabling developers, researchers, and organizations to build innovative solutions on a robust and reliable technological foundation.
GAIA was developed through a partnership between The Brazilian Association of AI (ABRIA), the Center of Excellence in Artificial Intelligence (CEIA) at the Federal University of Goiás (UFG), startups Nama and Amadeus AI, and Google DeepMind.
The development process started with the base model google/gemma-3-4b-pt and involved two main stages:
google/gemma-3-4b-ptThis project was made possible by the contributions of the following individuals:
The model is designed for text generation and conversational tasks in Portuguese.
GAIA can be used directly for chat, question answering, summarization, creative content generation, and other tasks requiring natural language understanding and generation in Portuguese.
GAIA serves as an excellent base model for fine-tuning on specific tasks, such as:
This model should not be used for high-stakes, critical decisions without human oversight. Its use for generating malicious, offensive, or illegal content, or for deceptively impersonating a human, is outside the intended scope. The model's performance in languages other than Portuguese will be significantly degraded.
Like any language model, GAIA reflects the biases present in its training data. Although the training corpus was curated with a focus on high quality, it may contain social and cultural biases from sources like Wikipedia and scientific articles. Therefore, the model may generate content that perpetuates existing stereotypes.
Furthermore, the model can "hallucinate," meaning it can generate information that appears factual but is not true. We strongly recommend verifying critical facts generated by the model before any use.
Users (both direct and downstream) should be aware of the model's risks, biases, and limitations. Implementing safeguards and content moderation is recommended, especially in public-facing applications. Human supervision is crucial for sensitive use cases.
The continuous pre-training was performed on a corpus of approximately 13 billion tokens in Portuguese. The data selection prioritized high quality and diversity, including sources such as:
A rigorous cleaning and filtering process was applied to ensure the highest possible data quality.
The training was conducted on a DGX infrastructure with NVIDIA H100 GPUs, using between 3 and 5 GPUs in parallel.
The model was evaluated on a set of multiple-choice benchmarks in Portuguese, comparing its performance against the base model, google/gemma-3-4b-it. The benchmarks include BlueX (a compilation of multiple-choice questions), and questions from the ENEM (Brazilian High School National Exam) and OAB (Brazilian Bar Exam).
| Benchmark | google/gemma-3-4b-it (Baseline) | GAIA (Our Model) |
|---|---|---|
| BlueX | 0.6630 | 0.6575 |
| ENEM 2024 | 0.6556 | 0.7000 |
| ENEM (General) | 0.7416 | 0.7486I |
| OAB (Bar Exam) | 0.4502 | 0.4416 |
The results indicate that continuous pre-training on Portuguese data had a notable impact on the model's performance. GAIA showed a significant improvement on the ENEM 2024 benchmark, outperforming the Google base model. On other benchmarks like BlueX and OAB, its performance is competitive and very close to the original model's, suggesting that the additional training process maintained the model's general capabilities while enhancing its knowledge in specific Portuguese-language domains.
If you use this model in your research or application, please cite our work.
BibTeX:
@misc{gaia-gemma-3-4b-2025,
title={GAIA: An Open Language Model for Brazilian Portuguese},
author={CAMILO-JUNIOR, C. G.; OLIVEIRA, S. S. T.; PEREIRA, L. A.; AMADEUS, M.; SCOTTI, R.; FAZZIONI, D.; NOVAIS, A. M. A.; JORDÃO, S. A. A.},
year={2025},
publisher={Hugging Face},
journal={Hugging Face repository},
howpublished={\url{[https://huggingface.co/CEIA-UFG/Gemma-3-Gaia-PT-BR-4b-it](https://huggingface.co/CEIA-UFG/Gemma-3-Gaia-PT-BR-4b-it)}}
}