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

[Feature] 为什么LoRA SFT把freeze_backbone设为True #705

Open
lck1201 opened this issue Nov 18, 2024 · 1 comment
Open

[Feature] 为什么LoRA SFT把freeze_backbone设为True #705

lck1201 opened this issue Nov 18, 2024 · 1 comment

Comments

@lck1201
Copy link

lck1201 commented Nov 18, 2024

Motivation

为什么internvl_chat/shell/internvl2.0/2nd_finetune/internvl2_40b_hermes2_yi_34b_dynamic_res_2nd_finetune_lora.sh，用LoRA跑SFT需要把freeze_backbone，freeze_mlp，freeze_backbone设置为True？是指梯度不直接更新权重吗？

Related resources

No response

Additional context

No response
@czczup
Copy link
Member

czczup commented Nov 23, 2024

您好，这个指的是冻住原本的参数，只训练新增的lora参数。

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
@lck1201 @czczup