Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Hi, how does the <image> being replaced in PLLava #60

Open
lucasjinreal opened this issue Jun 6, 2024 · 1 comment
Open

Hi, how does the <image> being replaced in PLLava #60

lucasjinreal opened this issue Jun 6, 2024 · 1 comment

Comments

@lucasjinreal
Copy link

Hi, for LLava multi images, it uses <image> <imag> ... <image> indicates N images, each image separated with a space, how should I prpeare the input text for replacing when inference?

Currently, I only found it directly read the text, wihtout any process, but my text is something like <video> diescrie this video in detail,

how to infernece with it?

@Stevetich
Copy link

I am also curious about that, have you fixed this problem?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants