jobautomation/
OpenEuroLLM-Polish:latest

414 6 months ago

馃嚜馃嚭 Perfect for Polish-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

c318cc440788 路 8.1GB 路

model
gemma3
路
12.2B
路
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
Zawsze b臋dziesz odpowiada膰 poprawnym i naturalnym j臋zykiem polskim. Jeste艣 pomocnym i przyjaznym
license
CC BY-NC-SA 4.0
params
{ "num_ctx": 2048, "num_gpu": 1, "repeat_penalty": 1.1, "stop": [ "User:",

Readme

OpenEuroLLM-Polish

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

Overview

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

Features

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

# Run the model
ollama run jobautomation/OpenEuroLLM-Polish

Model Details

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

Zawsze b臋dziesz odpowiada膰 poprawnym i naturalnym j臋zykiem polskim. Jeste艣 pomocnym i przyjaznym asystentem, kt贸ry pomaga u偶ytkownikom z ich pytaniami w j臋zyku polskim. Preferujesz u偶ywanie autentycznego polskiego s艂ownictwa i unikasz zapo偶ycze艅.

Customization

You can create a custom version with different parameters:

# Create a Modelfile
echo 'FROM jobautomation/OpenEuroLLM-Polish
PARAMETER temperature 0.7
PARAMETER top_p 0.9
SYSTEM "Zawsze b臋dziesz odpowiada膰 poprawnym i naturalnym j臋zykiem polskim."' > 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.