metadata
library_name: transformers
license: mit
datasets:
- hutsul/hutsul-synthetic
- hutsul/hutsul-manually-annotated
- hutsul/hutsul-dict
language:
- uk
- en
metrics:
- chrf
- bleu
- ter
base_model:
- meta-llama/Llama-3.1-8B-Instruct
pipeline_tag: translation
paper: https://aclanthology.org/2025.unlp-1.10
Model Card for Model ID
🧑🌾 LLaMa Mistral: Hutsul ↔ Ukrainian Dialectal Translation Model
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}
}