← Back to Portfolio

Korean Medical LLM

2024.09 - 2024.10

Project Overview

Built a Korean medical specialized LLM by constructing a 449,500-sample domain dataset and applying SFT plus model merge on top of google/gemma2-9b.

Problem Definition & Goals

Key Features & Contributions

Technical Challenges & Solutions

Results & Learnings

Technologies

Python Transformers TRL Datasets Unsloth SFT Model Merge

Links