rzzhan/ExGRPO-Qwen2.5-Math-7B-Zero
8B
•
Updated
•
13
ExGRPO
Model collections trained using ExGRPO.
-
-
rzzhan/ExGRPO-LUFFY-7B-Continual
8B • Updated • 14 -
rzzhan/ExGRPO-Qwen2.5-7B-Instruct
8B • Updated • 15 -
rzzhan/ExGRPO-Qwen2.5-Math-1.5B-Zero
2B • Updated • 31 -
rzzhan/ExGRPO-Llama3.1-8B-Zero
8B • Updated • 11 -
rzzhan/ExGRPO-Llama3.1-8B-Instruct
8B • Updated • 7 -
ExGRPO: Learning to Reason from Experience
Paper • 2510.02245 • Published • 76