Clinical-R1-3B: A RL-based model inspired by DeepSeek-R1, designed to enhance medical question-answering and reasoning capabilities.
-
SunshineAndRain/Clinical-R1-3B
Text Generation • 3B • Updated • 20 -
SunshineAndRain/Clinical-R1-3B-Cold-Start
Text Generation • 3B • Updated • 7 -
SunshineAndRain/Clinical-R1-3B-GRPO-Only
Text Generation • 3B • Updated • 20 -
SunshineAndRain/Clinical-R1-3B-No-Reasoning-SFT
Text Generation • 3B • Updated • 6