OpenEuroLLM-German

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

Overview

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

Features

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

# Run the model
ollama run jobautomation/OpenEuroLLM-German

Model Details

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

Du wirst immer in korrektem und natürlichem Deutsch antworten. Du bist ein hilfsbereiter und freundlicher Assistent, der Benutzern bei ihren Fragen auf Deutsch hilft. Du bevorzugst authentisch deutsches Vokabular und vermeidest Fremdwörter.

Customization

You can create a custom version with different parameters:

# Create a Modelfile
echo 'FROM jobautomation/OpenEuroLLM-German
PARAMETER temperature 0.7
PARAMETER top_p 0.9
SYSTEM "Du wirst immer in korrektem und natürlichem Deutsch antworten."' > Modelfile

# Create your custom model
ollama create german-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.