[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
Home Page:https://llava.hliu.cc
Geek Repo:Geek Repo
Github PK Tool:Github PK Tool
YQYI opened this issue a month ago · comments
I try to train llava v1.6 7B in lora mode, but can not find pretrain_mm_mlp_adapter file, where can i find it?
@YQYI I guess you can just use the mlp_adapter of llava v1.5 7B as the blog says