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

llava_vka_pretrain权重 #6

Open
Yogurtder opened this issue Jan 24, 2025 · 4 comments
Open

llava_vka_pretrain权重 #6

Yogurtder opened this issue Jan 24, 2025 · 4 comments

Comments

@Yogurtder
Copy link

您好，感谢您优秀的工作！请问是否可以提供一下 llava_vka_pretrain的权重参数呢？
@xyChen-HITSZ
Copy link
Collaborator

xyChen-HITSZ commented Jan 24, 2025 •
edited
Loading

https://huggingface.co/Ghaser/CVLM-Opt-pretrain 我们在这个路径下提供了预训练VKA的参数

@Yogurtder
Copy link
Author

感谢您的回复，请问是否在这里还是使用OPT-pretrain的权重呢？

Image

@xyChen-HITSZ
Copy link
Collaborator

这一阶段所使用的参数是OPT与语言模型对齐后的参数，即加载上面链接的参数经过LLaVA\scripts\knowledge\pretrain.sh预训练后得到的参数

@Yogurtder
Copy link
Author

好的，但是由于我在尝试预训练过程中不断OOM，我使用的是4张24GB显存的3090，想问您一下这个阶段您是在多大显存的GPU上训练了多久呢？

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@Yogurtder @xyChen-HITSZ