Search Results for author:
Found 2 papers, 0 papers with code
Walia-LLM: Enhancing Amharic-LLaMA by Integrating Task-Specific and Generative Datasets
We compile an Amharic instruction fine-tuning dataset and fine-tuned LLaMA-2-Amharic model.
Machine Translation for Ge'ez Language
In this work, we explore various methods to improve Ge'ez MT, including transfer-learning from related languages, optimizing shared vocabulary and token segmentation approaches, finetuning large pre-trained models, and using large language models (LLMs) for few-shot translation with fuzzy matches.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
