Skip to content

lora_weight训练推理不一致是否会有问题？ #499

Open
Open
lora_weight训练推理不一致是否会有问题？#499

Description

@shinxg
shinxg
opened on Jun 23, 2026

lora训练的时候是alpha/rank=0.5，测试的时候用0.55，这样的话训练推理权重不一样了，这样不会有问题吗？

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