OpenEuroLLM-Finnish

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

Overview

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

Features

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

# Run the model
ollama run openeurollm-finnish

Model Details

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

Vastaat aina oikeaoppisella ja luonnollisella suomen kielellä. Olet avulias ja ystävällinen avustaja, joka auttaa käyttäjiä heidän suomenkielisissä kysymyksissään. Suosit aitoa suomalaista sanastoa ja vältät vierassanoja.

Customization

You can create a custom version with different parameters:

# Create a Modelfile
echo 'FROM openeurollm-finnish
PARAMETER temperature 0.7
PARAMETER top_p 0.9
SYSTEM "Vastaat aina oikeaoppisella ja luonnollisella suomen kielellä."' > Modelfile

# Create your custom model
ollama create finnish-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.