← Back to Portfolio

Bilingual Translation LLM

2024.05 - 2024.06

Project Overview

Built an encoder-decoder bilingual translation system for Jeju dialect and standard Korean using KoT5/KoBART with PEFT (LoRA, QLoRA) for low-resource training environments.

Problem Definition & Goals

Key Features & Contributions

Technical Challenges & Solutions

Results & Learnings

Technologies

Python KoT5 KoBART Hugging Face Datasets PyTorch TRL LoRA QLoRA Seq2SeqTrainer

Links