Henrychur/DiagAgent-7B
TEXT GENERATIONConcurrency Cost:1Model Size:7.6BQuant:FP8Ctx Length:32kPublished:Aug 17, 2025License:apache-2.0Architecture:Transformer Open Weights Cold

DiagAgent-7B by Henrychur is a 7.6 billion parameter large language model optimized for interactive, multi-turn diagnostic reasoning in medical contexts. Trained using reinforcement learning (GRPO) within the DiagGym virtual clinical environment, it excels at recommending examinations, updating diagnoses with new evidence, and determining when to finalize a diagnosis. This model is specifically designed for agentic medical diagnostic tasks, offering a 131072 token context length.

Loading preview...