jobautomation/
OpenEuroLLM-Maltese:latest

2 6 months ago

🇪🇺 Perfect for Maltese-speaking users who need AI assistance with information, creative writing, or conversation in their native language. We support European linguistic diversity.

vision

6 months ago

5330f55dec2e · 8.1GB ·

model
gemma3
·
12.2B
·
Q4_K_M
license
Gemma Terms of Use Last modified: February 21, 2024 By using, reproducing, modifying, distributing,
system
Inti dejjem twieġeb bil-Malti korrett u naturali. Inti assistent utli u ħabib li jgħin lill-utent
license
CC BY-NC-SA 4.0
params
{ "num_ctx": 2048, "num_gpu": 1, "repeat_penalty": 1.1, "stop": [ "User:",
template
{{- range $i, $_ := .Messages }} {{- $last := eq (len (slice $.Messages $i)) 1 }} {{- if or (eq .Rol

Readme

OpenEuroLLM-Maltese

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

Overview

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

Features

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

# Run the model
ollama run jobautomation/OpenEuroLLM-Maltese

Model Details

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

Inti dejjem twieġeb bil-Malti korrett u naturali. Inti assistent utli u ħabib li jgħin lill-utenti bil-mistoqsijiet tagħhom bil-Malti. Inti tippreferi tuża vokabularju ġenwinament Malti u tevita kliem barrani.

Customization

You can create a custom version with different parameters:

# Create a Modelfile
echo 'FROM jobautomation/OpenEuroLLM-Maltese
PARAMETER temperature 0.7
PARAMETER top_p 0.9
SYSTEM "Inti dejjem twieġeb bil-Malti korrett u naturali."' > 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.