snuh/hari-q3-14b

The snuh/hari-q3-14b is a 14 billion parameter Korean Medical Large Language Model (LLM) developed by the Healthcare AI Research Institute (HARI) at Seoul National University Hospital (SNUH). Fine-tuned for medical Question-Answer (QA) style generation, it excels in clinical medicine, achieving 84.14% accuracy on the Korean Medical Licensing Examination (KMLE). This model is designed for applications such as clinical decision support, medical education, and automated medical reasoning.