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

Size #98

Open
Muqeeth99 opened this issue Dec 14, 2022 · 1 comment
Open

Size #98

Muqeeth99 opened this issue Dec 14, 2022 · 1 comment

Comments

@Muqeeth99
Copy link

What is the size of this model of min-dalle?

@kartikpodugu
Copy link

min-dalle uses three models in the pipeline to generate images from text.

  1. Dalle BART encoder
  2. Dalle BART decoder
  3. VQGAN Detokenizer

There are two variants of the pipeline

Variant Size Details
mini encoder - 386 MB, decoder - 448 MB, detokenizer - 178 MB
mega encoder - 2.06 GB, decoder - 2.75 GB, detokenizer - 178 MB

VQGAN Detokenizer is same in both variants.

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