LLaVA-NeXT
LLaVA-NeXT copied to clipboard
Missing mm_projector.bin in LLaVA-Video series
Hi, I am trying to fine-tune LLaVA-Video-7B and LLaVA-Video-72B. However, it seems that the checkpoints for mm_projector.bin have not been released yet. Thanks for the help in advance.
Besides, the training and inference scripts of LLaVA-Video do not load mm_projector. Is my understanding correct? If yes, why did you choose only to load the trained Qwen2?
i also found this problem.the code looks like only initialize mm_project but not load weight from pretrained model in infrence mode.