What is the input sample of the forward function in videollama

[llx-08]

Hi, I'm wondering what is the input sample of the forward function in videollama.py.

It seems like an dict() which contains image, text_input as its keys, but I can't find any usage as example. Besides, I check the inference process in demo_audiovideo.py, it's different with the forward process. Can you provide some example to use the forward function in videollama? Thank you very much!

[EQ3000]

I am also finding this solution.!