OpenEuroLLM-Portuguese

A fine-tuned version of Gemma3 optimized for Portuguese language responses. This model is part of the JobAutomation Collection, aimed at providing high-quality language models for European languages.

Overview

OpenEuroLLM-Portuguese is specifically designed to provide fluent, natural responses in Portuguese. The model maintains the reasoning capabilities of its Gemma3 base while being optimized to understand and generate authentic Portuguese text.

Features

• Native Portuguese Responses: Always responds in natural, correct Portuguese
• Culturally Aware: Understanding of Portuguese culture, history, and regional context
• Specialized Vocabulary: Prioritizes genuine Portuguese vocabulary over loan words
• Grammatical Accuracy: Properly handles Portuguese-specific grammar rules and constructions
• Fast & Efficient: Based on the efficient Gemma3 architecture for good performance even on consumer hardware

Usage

# Pull the model
ollama pull jobautomation/OpenEuroLLM-Portuguese

# Run the model
ollama run jobautomation/OpenEuroLLM-Portuguese

Model Details

• Base Model: Gemma3
• Context Length: 8K tokens
• Training: Fine-tuned on a diverse corpus of Portuguese text including literature, news, academic papers, and conversational data
• License: Apache 2.0
• Recommended RAM: 8GB minimum

System Prompt

This model uses the following default system prompt:

Responderás sempre em português correto e natural. És um assistente útil e amigável que ajuda os utilizadores com as suas perguntas em português. Preferes utilizar vocabulário genuinamente português e evitas estrangeirismos.

Customization

You can create a custom version with different parameters:

# Create a Modelfile
echo 'FROM jobautomation/OpenEuroLLM-Portuguese
PARAMETER temperature 0.7
PARAMETER top_p 0.9
SYSTEM "Responderás sempre em português correto e natural."' > Modelfile

# Create your custom model
ollama create portuguese-academic -f Modelfile

About OpenEuroLLM

OpenEuroLLM is an initiative to create high-quality language models for European languages. Our mission is to ensure that AI language technologies support the linguistic diversity of Europe, providing models that understand and generate content in languages beyond the dominant few.

Acknowledgements

This model was developed with support of the open source community and Ollama.