Jie Cheng

icon indicating an email [email protected]

icon company Institute of Automation, Chinese Academy of Sciences icon location Beijing icon location major in reinforcement learning

Results 1 issues of Jie Cheng

Improve PRM inference speed

This pr serves a similar purpose as [this](https://github.com/RLHFlow/RLHF-Reward-Modeling/pull/48), in order to increase the speed of prm evaluation. But instead of modifying the content of the conversation (which can lead to...