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.

Sign up for GitHub

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

Jump to bottom

About the token cost of one 3D scene #31

Open

KaKa-101 opened this issue Nov 7, 2024 · 1 comment

KaKa-101 commented Nov 7, 2024

Could you tell me how many tokens you used to represent the whole 3D scene before sending them to LLM?
Thanks a lot.

Contributor

ch3cook-fdu commented Nov 7, 2024

We represent a 3D scene with 32 learnable tokens following BLIP2 and InstructBlip https://github.com/Open3DA/LL3DA/blob/main/models/ll3da/captioner.py#L183. We introduce 8 additional tokens for each visual prompt.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment