Skip to content

基于lora的方式finetune模型后，推理时间很长 #80

Open
Open
基于lora的方式finetune模型后，推理时间很长#80

Description

@wangjiangyue0226
wangjiangyue0226
opened on Aug 22, 2023

基于lora的方式finetune模型后，推理时间很长，平均时间要40s，而相同的case直接用chatglm-6b推理平均时间要16s

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions