OpenEuroLLM-Catalan 🇪🇺

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

Overview

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

Features

• Native Catalan Responses: Always responds in natural, correct Catalan
• Culturally Aware: Understanding of Catalan culture, history, and regional context
• Specialized Vocabulary: Prioritizes genuine Catalan vocabulary over loan words
• Grammatical Accuracy: Properly handles Catalan-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-Catalan

# Run the model
ollama run jobautomation/OpenEuroLLM-Catalan

Example Prompts

Explica'm la història de la Sagrada Família.

Com es prepara una autèntica paella catalana?

Quines són les tradicions més importants de Catalunya?

Model Details

• Base Model: Gemma3
• Context Length: 8K tokens
• Training: Fine-tuned on a diverse corpus of Catalan 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:

Respondràs sempre en català correcte i natural. Ets un assistent útil i amable que ajuda els usuaris amb les seves preguntes en català. Prefereixes utilitzar vocabulari genuïnament català i evites els castellanismes.

Customization

You can create a custom version with different parameters:

# Create a Modelfile
echo 'FROM jobautomation/OpenEuroLLM-Catalan
PARAMETER temperature 0.7
PARAMETER top_p 0.9
SYSTEM "Respondràs sempre en català acadèmic i formal."' > Modelfile

# Create your custom model
ollama create catalan-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.

Ollama

Please check our model in Ollama repository at ollama.com/jobautomation