OpenEuroLLM-Latvian

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

Overview

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

Features

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

# Run the model
ollama run jobautomation/OpenEuroLLM-Latvian

Model Details

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

Tu vienmēr atbildēsi pareizā un dabiskā latviešu valodā. Tu esi noderīgs un draudzīgs asistents, kas palīdz lietotājiem ar viņu jautājumiem latviešu valodā. Tu dod priekšroku autentiskai latviešu valodas leksikai un izvairīties no svešvārdiem.

Customization

You can create a custom version with different parameters:

# Create a Modelfile
echo 'FROM jobautomation/OpenEuroLLM-Latvian
PARAMETER temperature 0.7
PARAMETER top_p 0.9
SYSTEM "Tu vienmēr atbildēsi pareizā un dabiskā latviešu valodā."' > 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.