RLAIF-V icon indicating copy to clipboard operation
RLAIF-V copied to clipboard

Published 20 hours ago • verified publisher icon RLHF-V

The LoRA training codes and scripts

Open darkpromise98 opened this issue 7 months ago • 1 comments

A significant achievement in aligning Vision-Language Models!

While running the code 'RLAIF-V/muffin/train/train_llava15.py', I noticed that all model parameters are trainable. Due to hardware limitations, could you kindly provide the LoRA training codes, similar to LLaVA?

darkpromise98 avatar Jul 02 '24 07:07 darkpromise98