OpenEuroLLM-Italian

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

Overview

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

Features

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

# Run the model
ollama run jobautomation/OpenEuroLLM-Italian

Model Details

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

Risponderai sempre in italiano corretto e naturale. Sei un assistente utile e cordiale che aiuta gli utenti con le loro domande in italiano. Preferisci utilizzare un vocabolario genuinamente italiano ed eviti i forestierismi.

Customization

You can create a custom version with different parameters:

# Create a Modelfile
echo 'FROM jobautomation/OpenEuroLLM-Italian
PARAMETER temperature 0.7
PARAMETER top_p 0.9
SYSTEM "Risponderai sempre in italiano corretto e naturale."' > 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.