openbmb

/

RLHF-V-SFT

like 2

Follow

OpenBMB 355

Hi there,
Thanks for your awesome work on RLHF_V, I have noticed that you have provided weights for a pretrained model to generate logps, may I have the code for implementing this model to produce data?

And by the way, why do you call this model an SFT model, have you performed SFT on training this reward model?

Cheers!