Skip to content

P-tuning中模型参数冷冻的问题 #42

Description

@YCC-324

您好,我理解的p-tuning的原理是冷冻后面大语言模型,只调整前面的prompt embedding模型。但是在您代码的实现中(https://github.com/THUDM/P-tuning/blob/main/PT-Fewshot/pet/wrapper.py 中optimizer部分) 同时对后面大语言模型的参数进行了微调,想问下这部分是我理解错了吗

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Fields

    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions