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

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions