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

deepseek-vl系列的微调支持 (finetune) #10

Closed
Jintao-Huang opened this issue Mar 12, 2024 · 6 comments
Closed

deepseek-vl系列的微调支持 (finetune) #10

Jintao-Huang opened this issue Mar 12, 2024 · 6 comments

Comments

@Jintao-Huang
Copy link

ms-swift大模型训练框架已经支持了deepseek-vl系列模型的推理和微调~

最佳实践可以查看这里:
https://github.com/modelscope/swift/blob/main/docs/source/Multi-Modal/deepseek-vl%E6%9C%80%E4%BD%B3%E5%AE%9E%E8%B7%B5.md

@RERV
Copy link
Collaborator

RERV commented Mar 12, 2024

Thank you for supporting DeepSeek-VL!

@soloice
Copy link

soloice commented Mar 13, 2024

@Jintao-Huang Can you kindly confirm if swift can be used to finetune visual encoder? If so, how? If not, what's the simplest way to support it?

@xs818818
Copy link

还有就是lora微调后怎么部署使用

@SinanAkkoyun
Copy link
Contributor

@soloice Thank you very much for asking

@Jintao-Huang
Copy link
Author

LoRA fine-tuning and merge-LoRA have been supported for both the visual encoder and aligner.
Full parameter fine-tuning is also supported.
😊

@SinanAkkoyun
Copy link
Contributor

I am super grateful for your work, thank you a lot!!! ❤️

@Jintao-Huang Jintao-Huang changed the title deepseek-vl系列的微调支持 deepseek-vl系列的微调支持 (finetune) Mar 14, 2024
@soloice soloice closed this as completed Mar 15, 2024
@soloice soloice pinned this issue Mar 15, 2024
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

5 participants