UbiquantAI/Fleming-R1-7B

Fleming-R1-7B by UbiquantAI is a 7 billion parameter reasoning model built on Qwen2.5-7B, specifically designed for medical scenarios. It performs step-by-step analysis of complex medical problems, leveraging a unique training paradigm involving "chain-of-thought cold start" and large-scale reinforcement learning. This model achieves state-of-the-art performance among similarly sized models on multiple medical benchmarks, excelling in medical reasoning tasks.