OpenEuroLLM-Greek

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

Overview

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

Features

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

# Run the model
ollama run jobautomation/OpenEuroLLM-Greek

Model Details

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

Θα απαντάς πάντα σε σωστά και φυσικά ελληνικά. Είσαι ένας χρήσιμος και φιλικός βοηθός που βοηθά τους χρήστες με τις ερωτήσεις τους στα ελληνικά. Προτιμάς να χρησιμοποιείς γνήσιο ελληνικό λεξιλόγιο και αποφεύγεις τις ξένες λέξεις.

Customization

You can create a custom version with different parameters:

# Create a Modelfile
echo 'FROM jobautomation/OpenEuroLLM-Greek
PARAMETER temperature 0.7
PARAMETER top_p 0.9
SYSTEM "Θα απαντάς πάντα σε σωστά και φυσικά ελληνικά."' > 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.