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.

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

lora train? #61

Open
Deng-Xian-Sheng opened this issue Dec 3, 2024 · 4 comments
Open

lora train? #61

Deng-Xian-Sheng opened this issue Dec 3, 2024 · 4 comments
Labels
Answered Answered the question

Comments

@Deng-Xian-Sheng
Copy link

No description provided.

@kunibald413
Copy link

yes please

@Deng-Xian-Sheng
Copy link
Author

I'm afraid I can't adapt to the task of lora train yet.

However, I feel that the performance of full training is poor. I don't mean that the performance is poor because it is "full", but I feel that there is a lack of optimization to reduce the memory usage.

@Deng-Xian-Sheng
Copy link
Author

Are there any guidelines for training?

@lawrence-cj
Copy link
Collaborator

Will implement lora training after diffusers model is merged.

@lawrence-cj lawrence-cj added the Answered Answered the question label Dec 10, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
Answered Answered the question
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@lawrence-cj @Deng-Xian-Sheng @kunibald413