Papers
arxiv:2405.13010

UCCIX: Irish-eXcellence Large Language Model

Published on May 13
Authors:
,

Abstract

The development of Large Language Models (LLMs) has predominantly focused on high-resource languages, leaving extremely low-resource languages like Irish with limited representation. This work presents UCCIX, a pioneering effort on the development of an open-source Irish-based LLM. We propose a novel framework for continued pre-training of LLMs specifically adapted for extremely low-resource languages, requiring only a fraction of the textual data typically needed for training LLMs according to scaling laws. Our model, based on Llama 2-13B, outperforms much larger models on Irish language tasks with up to 12% performance improvement, showcasing the effectiveness and efficiency of our approach. We also contribute comprehensive Irish benchmarking datasets, including IrishQA, a question-answering dataset, and Irish version of MT-bench. These datasets enable rigorous evaluation and facilitate future research in Irish LLM systems. Our work aims to preserve and promote the Irish language, knowledge, and culture of Ireland in the digital era while providing a framework for adapting LLMs to other indigenous languages.

Community

Will you be releasing the non instruction version of this model? 'We denote the pre-trained model as UCCIX, and the instruction fine-tuned version as UCCIX-Instruct.'.

·
Paper author

Thank you for your interest in our work. We have released the pre-trained version at: https://huggingface.co/ReliableAI/UCCIX-Llama2-13B

Sign up or log in to comment

Models citing this paper 3

Datasets citing this paper 2

Spaces citing this paper 1

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.