MOSS-RLHF icon indicating copy to clipboard operation
MOSS-RLHF copied to clipboard

Published 20 hours ago • verified publisher icon OpenLMLab

关于reward model的权重合并问题

Open HuipengXu opened this issue 1 year ago • 1 comments

多次重新下载diff权重，合并得到的sum值一直都是 all sum : 49715.3515625

HuipengXu avatar Oct 05 '23 10:10 HuipengXu

您好，这个之前有同学遇到过，可能是包版本问题，请您pip install -r requirement.txt

Ablustrund avatar Oct 11 '23 03:10 Ablustrund