RLHF-Reward-Modeling icon indicating copy to clipboard operation
RLHF-Reward-Modeling copied to clipboard
Published 10 months ago • verified publisher icon RLHFlow

Code to reproduce ArmoRM

Open halfrot opened this issue 1 year ago • 1 comments

Hi, this is great work and I'd like to know if there is a plan to release the training code to reproduce the model?

halfrot avatar Aug 21 '24 05:08 halfrot

Sorry for the delay. I try to release it this month.

Haoxiang-Wang avatar Aug 21 '24 08:08 Haoxiang-Wang

what about the moe for the calculation of the coefficients?

teixeira-neospace avatar Sep 03 '24 13:09 teixeira-neospace

Will release the code this week!

Haoxiang-Wang avatar Sep 12 '24 05:09 Haoxiang-Wang

Hi, Haoxiang, when will the code for ArmoRM be released?

vincezh2000 avatar Sep 17 '24 15:09 vincezh2000

Code released!

Haoxiang-Wang avatar Sep 18 '24 07:09 Haoxiang-Wang