mirror of
https://github.com/deepseek-ai/DeepSeek-VL.git
synced 2026-11-05 00:47:24 +00:00
[GH-ISSUE #10] deepseek-vl系列的微调支持 (finetune) #8
Labels
No labels
enhancement
environment
pull-request
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
deepseek-ai/DeepSeek-VL#8
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @Jintao-Huang on GitHub (Mar 12, 2024).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-VL/issues/10
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 commented on GitHub (Mar 12, 2024):
Thank you for supporting DeepSeek-VL!
@soloice commented on GitHub (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 commented on GitHub (Mar 13, 2024):
还有就是lora微调后怎么部署使用
@SinanAkkoyun commented on GitHub (Mar 13, 2024):
@soloice Thank you very much for asking
@Jintao-Huang commented on GitHub (Mar 13, 2024):
LoRA fine-tuning and merge-LoRA have been supported for both the visual encoder and aligner.
Full parameter fine-tuning is also supported.
😊
@SinanAkkoyun commented on GitHub (Mar 13, 2024):
I am super grateful for your work, thank you a lot!!! ❤️
@Ethanscuter commented on GitHub (Mar 18, 2025):
最佳实践的link已经打不开了，可以重新给一个link吗？谢谢
@HugNature commented on GitHub (Mar 26, 2025):