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

InternVL2_5-4B-MPO lora微调 #839

Open
ChenJian7578 opened this issue Jan 9, 2025 · 3 comments
Open

InternVL2_5-4B-MPO lora微调 #839

ChenJian7578 opened this issue Jan 9, 2025 · 3 comments

Comments

@ChenJian7578
Copy link

在目录下没有看到MPO lora的微调,请问是目前不支持吗,还是说MPO的lora微调用的是2_5的lora微调脚本?

@JackeyHRan
Copy link

JackeyHRan commented Jan 10, 2025

你好,我尝试用2.5的lora微调脚本来进行MPO的lora微调,但我遇到了warning: shape mismatch: value tensor of shape [4608, 4096] cannot be broadcast to indexing result of shape [1098, 4096], i
nput_embeds[selected].shape=torch.Size([1098, 4096]), vit_embeds.shape=torch.Size([4608, 4096])这样的问题,请问你遇到了吗,或者你成功使用lora微调了吗,感谢

@ChenJian7578
Copy link
Author

ChenJian7578 commented Jan 11, 2025 via email

@zwang-datascience
Copy link

zwang-datascience commented Jan 21, 2025

同问,MPO训练是否支持lora方式

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

3 participants