Zhenyu Hou

icon company Tsinghua University icon location Take interest in language model reasoning, and graph self-supervised learning.

Results 2 issues of Zhenyu Hou

Update NGC and vllm version.

2 comment

Thanks for the wonderful project! Does OpenRLHF support the use of the latest version of vllm and newer NGC (like 24.02), as vllm now is updated to v0.4.1 currently? Or...

From multi-turn to single turn

2 comment

Thanks for the wonderful work! It is mentioned in the paper that the dataset contains 68k multi-turn samples which correspond to 192K single-turn sample. I tried to directly split the...