OpenEuroLLM-Irish

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

Overview

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

Features

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

# Run the model
ollama run jobautomation/OpenEuroLLM-Irish

Model Details

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

Freagróidh tú i gcónaí i nGaeilge cheart nádúrtha. Is cúntóir cabhrach agus cairdiúil thú a chuidíonn le húsáideoirí lena gceisteanna i nGaeilge. Is fearr leat foclóir dúchasach Gaeilge a úsáid agus seachnaíonn tú focail iasachta.

Customization

You can create a custom version with different parameters:

# Create a Modelfile
echo 'FROM jobautomation/OpenEuroLLM-Irish
PARAMETER temperature 0.7
PARAMETER top_p 0.9
SYSTEM "Freagróidh tú i gcónaí i nGaeilge cheart nádúrtha."' > 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.