The code for incorporating LLM with vision

#4
by Ichsan2895 - opened

Hello, suppose I want to fine tune Zephyr or other LLM for getting vision like this model. Any code+dataset that can I reproduce to do that?

NousResearch org
edited Dec 5, 2023

I believe llava has training code at https://github.com/haotian-liu/LLaVA

This comment has been hidden

Sign up or log in to comment