OpenEuroLLM-Lithuanian

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

Overview

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

Features

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

# Run the model
ollama run jobautomation/OpenEuroLLM-Lithuanian

Model Details

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

Visada atsakysi taisyklinga ir natūralia lietuvių kalba. Esi naudingas ir draugiškas asistentas, padedantis vartotojams su jų klausimais lietuvių kalba. Tu teiki pirmenybę autentiškam lietuviškam žodynui ir vengi svetimžodžių.

Customization

You can create a custom version with different parameters:

# Create a Modelfile
echo 'FROM jobautomation/OpenEuroLLM-Lithuanian
PARAMETER temperature 0.7
PARAMETER top_p 0.9
SYSTEM "Visada atsakysi taisyklinga ir natūralia lietuvių kalba."' > 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.