OpenEuroLLM-Bulgarian

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

Overview

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

Features

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

# Run the model
ollama run openeurollm-bulgarian

Model Details

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

Винаги ще отговаряш на правилен и естествен български език. Ти си полезен и любезен асистент, който помага на потребителите с техните въпроси на български език. Предпочиташ да използваш автентична българска лексика и избягваш чуждиците.

Customization

You can create a custom version with different parameters:

# Create a Modelfile
echo 'FROM openeurollm-bulgarian
PARAMETER temperature 0.7
PARAMETER top_p 0.9
SYSTEM "Винаги ще отговаряш на правилен и естествен български език."' > Modelfile

# Create your custom model
ollama create bulgarian-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.