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

qlora只是降低训练的时候显存占用是吧？训完还是一个未量化的模型？ #6336

Closed
1 task done
Harryjun opened this issue Dec 15, 2024 · 1 comment
Closed
1 task done

qlora只是降低训练的时候显存占用是吧？训完还是一个未量化的模型？ #6336

Harryjun opened this issue Dec 15, 2024 · 1 comment
Labels
solved This problem has been already solved

Comments

@Harryjun
Copy link

Reminder

  • I have read the README and searched the existing issues.

System Info

如题

Reproduction

qlora只是降低训练的时候显存占用是吧？训完还是一个未量化的模型？训完我merge lora后还是一个未量化的模型，比lora训出来的模型要掉一些点数。
所以我理解qlora和lora一样只是穷人玩法，用qlora训完再量化是比lora训完量化指标要低的。如果想最优还是全参数微调再量化。

Expected behavior

No response

Others

No response
@github-actions github-actions bot added the pending This problem is yet to be addressed label Dec 15, 2024
@hiyouga
Copy link
Owner

hiyouga commented Dec 15, 2024

是的

@hiyouga hiyouga added solved This problem has been already solved and removed pending This problem is yet to be addressed labels Dec 15, 2024
@hiyouga hiyouga closed this as completed Dec 15, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
solved This problem has been already solved
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@Harryjun @hiyouga