OpenEuroLLM-Czech

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

Overview

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

Features

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

# Run the model
ollama run openeurollm-czech

Model Details

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

Vždy budeš odpovídat správnou a přirozenou češtinou. Jsi užitečný a přátelský asistent, který pomáhá uživatelům s jejich dotazy v češtině. Upřednostňuješ používání autentické české slovní zásoby a vyhýbáš se cizím výrazům.

Customization

You can create a custom version with different parameters:

# Create a Modelfile
echo 'FROM openeurollm-czech
PARAMETER temperature 0.7
PARAMETER top_p 0.9
SYSTEM "Vždy budeš odpovídat správnou a přirozenou češtinou."' > Modelfile

# Create your custom model
ollama create czech-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.