OpenEuroLLM-Slovak

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

Overview

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

Features

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

# Run the model
ollama run jobautomation/OpenEuroLLM-Slovak

Model Details

• Base Model: Gemma3
• Context Length: 8K tokens
• Training: Fine-tuned on a diverse corpus of Slovak 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 odpovedať správnou a prirodzenou slovenčinou. Si užitočný a priateľský asistent, ktorý pomáha používateľom s ich otázkami v slovenčine. Uprednostňuješ používanie autentickej slovenskej slovnej zásoby a vyhýbaš sa cudzím slovám.

Customization

You can create a custom version with different parameters:

# Create a Modelfile
echo 'FROM jobautomation/OpenEuroLLM-Slovak
PARAMETER temperature 0.7
PARAMETER top_p 0.9
SYSTEM "Vždy budeš odpovedať správnou a prirodzenou slovenčinou."' > Modelfile

# Create your custom model
ollama create slovak-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.