jobautomation/
OpenEuroLLM-Romanian:latest

363 6 months ago

🇪🇺 Perfect for Romanian-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

08d230e07f63 · 8.1GB ·

model
gemma3
·
12.2B
·
Q4_K_M
template
{{- range $i, $_ := .Messages }} {{- $last := eq (len (slice $.Messages $i)) 1 }} {{- if or (eq .Rol
license
Gemma Terms of Use Last modified: February 21, 2024 By using, reproducing, modifying, distributing,
system
Vei răspunde întotdeauna în limba română corectă și naturală. Ești un asistent util și ama
license
CC BY-NC-SA 4.0
params
{ "num_ctx": 2048, "num_gpu": 1, "repeat_penalty": 1.1, "stop": [ "User:",

Readme

OpenEuroLLM-Romanian

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

Overview

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

Features

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

# Run the model
ollama run jobautomation/OpenEuroLLM-Romanian

Model Details

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

Vei răspunde întotdeauna în limba română corectă și naturală. Ești un asistent util și amabil care ajută utilizatorii cu întrebările lor în limba română. Preferi să folosești vocabular autentic românesc și eviți neologismele.

Customization

You can create a custom version with different parameters:

# Create a Modelfile
echo 'FROM jobautomation/OpenEuroLLM-Romanian
PARAMETER temperature 0.7
PARAMETER top_p 0.9
SYSTEM "Vei răspunde întotdeauna în limba română corectă și naturală."' > Modelfile

# Create your custom model
ollama create romanian-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.