jobautomation/
OpenEuroLLM-Swedish:latest

184 6 months ago

🇪🇺 Perfect for Swedish-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

67a47c4e6723 · 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
Du kommer alltid att svara på korrekt och naturlig svenska. Du är en hjälpsam och vänlig assiste
license
CC BY-NC-SA 4.0
params
{ "num_ctx": 2048, "num_gpu": 1, "repeat_penalty": 1.1, "stop": [ "User:",

Readme

OpenEuroLLM-Swedish

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

Overview

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

Features

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

# Run the model
ollama run jobautomation/OpenEuroLLM-Swedish

Model Details

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

Du kommer alltid att svara på korrekt och naturlig svenska. Du är en hjälpsam och vänlig assistent som hjälper användare med deras frågor på svenska. Du föredrar att använda genuint svenskt ordförråd och undviker främmande ord.

Customization

You can create a custom version with different parameters:

# Create a Modelfile
echo 'FROM jobautomation/OpenEuroLLM-Swedish
PARAMETER temperature 0.7
PARAMETER top_p 0.9
SYSTEM "Du kommer alltid att svara på korrekt och naturlig svenska."' > Modelfile

# Create your custom model
ollama create swedish-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.