Gemma 3 Gaia PT BR 4b It

🚀 Model Card for GAIA (Gemma-3-Gaia-PT-BR-4b-it)

GAIA is an open, state - of - the - art language model tailored for Brazilian Portuguese. It was developed by continuously pre - training the google/gemma-3-4b-pt model on a vast and high - quality Portuguese data corpus. The aim of GAIA is to make cutting - edge AI technology more accessible in Brazil, empowering developers, researchers, and organizations to build innovative solutions on a strong and reliable technological foundation.

🚀 Quick Start

The details about how to quickly start using GAIA are not provided in the original document.

✨ Features

Model Details

Model Description

GAIA was developed through a collaboration 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 began with the base model google/gemma-3-4b-pt and consisted of two main phases:

1. Continuous Pre - training: The model was trained on a large, high - quality Portuguese dataset with approximately 13 billion tokens. This corpus covers various domains, including scientific articles and Portuguese Wikipedia data, ensuring the model has a profound understanding of the language and its contexts.
2. Instruction - Following Capability Restoration: To enable the model to follow instructions without traditional supervised fine - tuning (SFT), a weight merging operation was applied. This technique, described in the paper “Balancing Continuous Pre - Training and Instruction Fine - Tuning: Optimizing Instruction - Following in LLMs”, allows the model to integrate the knowledge acquired during continuous pre - training with the ability to interact in a chat format and follow instructions.

Team

This project was made possible thanks to the contributions of the following individuals:

• Dr. Celso Gonçalves Camilo - Junior
• Dr. Sávio Salvarino Teles de Oliveira
• Me. Lucas Araujo Pereira
• Marcellus Amadeus
• Daniel Fazzioni
• Artur Matos Andrade Novais
• Salatiel Abraão Avelar Jordão

Model Sources

• Repository: [CEIA - UFG/Gemma - 3 - Gaia - PT - BR - 4b - it](https://huggingface.co/CEIA - UFG/Gemma - 3 - Gaia - PT - BR - 4b - it)
• Paper (Merge Methodology): Balancing Continuous Pre - Training and Instruction Fine - Tuning: Optimizing Instruction - Following in LLMs

Uses

Direct Use

GAIA can be directly used for chat, question answering, summarization, creative content generation, and other tasks that require natural language understanding and generation in Portuguese.

Downstream Use

GAIA serves as an excellent base model for fine - tuning on specific tasks, such as:

• Sentiment analysis in Portuguese.
• Retrieval - Augmented Generation (RAG) systems for corporate knowledge bases.
• Document classification.
• Specialized customer service chatbots.

Out - of - Scope Use

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.

Bias, Risks, and Limitations

Like any language model, GAIA reflects the biases present in its training data. Although the training corpus was carefully curated for 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.

⚠️ Important Note

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.

Training Details

Training Data

The continuous pre - training was carried out on a Portuguese corpus of approximately 13 billion tokens. The data selection emphasized high quality and diversity, including sources such as:

• Scientific Articles in Portuguese: To provide the model with more formal and technical knowledge.
• Portuguese Wikipedia: To cover a wide range of general knowledge.

A strict cleaning and filtering process was applied to ensure the highest possible data quality.

Training Procedure

The training was conducted on a DGX infrastructure with NVIDIA H100 GPUs, using between 3 and 5 GPUs in parallel.

Training Hyperparameters

• Training regime: Mixed Precision (bf16)
• Global Batch Size: 4 million tokens

Evaluation

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).

Results

Summary

The results show 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, indicating that the additional training process maintained the model's general capabilities while enhancing its knowledge in specific Portuguese - language domains.

📚 Documentation

Citation

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.; 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)}}
}

📄 License

The license of GAIA is Gemma.