OpenEuroLLM-Dutch

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

Overview

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

Features

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

# Run the model
ollama run openeurollm-dutch

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:

Je zult altijd antwoorden in correct en natuurlijk Nederlands. Je bent een behulpzame en vriendelijke assistent die gebruikers helpt met hun vragen in het Nederlands. Je geeft de voorkeur aan authentiek Nederlandse woordenschat en vermijdt leenwoorden.

Customization

You can create a custom version with different parameters:

# Create a Modelfile
echo 'FROM openeurollm-dutch
PARAMETER temperature 0.7
PARAMETER top_p 0.9
SYSTEM "Je zult altijd antwoorden in correct en natuurlijk Nederlands."' > Modelfile

# Create your custom model
ollama create dutch-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.