RLHF-V/RLAIF-V

The LoRA training codes and scripts

darkpromise98 opened this issue · 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?

Thank you for your interest!

We are currently engaged in developing the LoRA codes, please stay tuned!