hutsul/hutsul-manually-annotated
Viewer • Updated • 9.85k • 29 • 1
How to use hutsul/Vuyko-LLaMa-v0.1 with Transformers:
# Use a pipeline as a high-level helper
# Warning: Pipeline type "translation" is no longer supported in transformers v5.
# You must load the model directly (see below) or downgrade to v4.x with:
# 'pip install "transformers<5.0.0'
from transformers import pipeline
pipe = pipeline("translation", model="hutsul/Vuyko-LLaMa-v0.1") # Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("hutsul/Vuyko-LLaMa-v0.1", device_map="auto")This is the first open-source translation model for Hutsul ↔ Ukrainian, built by fine-tuning Llama-3.1-8B-Instruct on a custom dialectal corpus. It is part of our research on adapting large language models to underrepresented dialects in low-resource languages.
Presented at: UNLP 2025 @ ACL
Paper: Vuyko Mistral: Adapting LLMs for Low-Resource Dialectal Translation
If you use this model or dataset, please cite our paper:
@inproceedings{kyslyi2025vuyko,
title = {Vuyko Mistral: Adapting LLMs for Low-Resource Dialectal Translation},
author = {Kyslyi, Roman and Maksymiuk, Yuliia and Pysmennyi, Ihor},
booktitle = {Proceedings of the Workshop on Ukrainian Natural Language Processing (UNLP)},
year = {2025},
url = {https://aclanthology.org/2025.unlp-1.10}
}
Base model
meta-llama/Llama-3.1-8B