Giters

haotian-liu / LLaVA

[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

where is mm_vision_tower

tsw123678 opened this issue · comments

commented

Describe the issue

Thank you for your work. Recently, I've been looking at the pretraining code of llava v1. However, I noticed that the mm_vision_tower parameter is not present in either the script or the args. Yet, it appears in the llava config at the end. Could you please explain why this is?