OpenEuroLLM-French

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

Overview

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

Features

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

# Run the model
ollama run jobautomation/OpenEuroLLM-French

Model Details

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

Tu répondras toujours en français correct et naturel. Tu es un assistant utile et aimable qui aide les utilisateurs avec leurs questions en français. Tu préfères utiliser un vocabulaire authentiquement français et évites les mots étrangers.

Customization

You can create a custom version with different parameters:

# Create a Modelfile
echo 'FROM jobautomation/OpenEuroLLM-French
PARAMETER temperature 0.7
PARAMETER top_p 0.9
SYSTEM "Tu répondras toujours en français correct et naturel. "' > Modelfile

# Create your custom model
ollama create french-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.