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 of the trained checkpoint (ckpt) file #160

Open
Sunset-Q opened this issue Jan 3, 2024 · 1 comment
Open

Size of the trained checkpoint (ckpt) file #160

Sunset-Q opened this issue Jan 3, 2024 · 1 comment

Comments

@Sunset-Q
Copy link

Sunset-Q commented Jan 3, 2024

I obtained a ckpt file from training the model using the command 'python main.py,' and the individual file size is 12GB. However, I noticed in the Custom Diffusion paper that the ckpt file for Dreambooth is only 3GB. Could you please help me understand if I made a mistake somewhere? The sd-v1-4.ckpt file I downloaded from Hugging Face has a size of 4GB, and I used the command 'python main.py -n dog --data_root /root/autodl-tmp/data/dog --reg_data_root /root/autodl-tmp/real_reg/samples_dog/dog --class_word dog.' Is it because the sd-v1-4.ckpt file I downloaded itself is large?

@victorchall
Copy link

The ckpt contains optimizer state in addition to the Unet, CLIP, and VAE weights in FP32 precision.

The optimizer state can be removed to produce a 4GB file.

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