Skip to content

unable to reproduce the gpt-4 performance #2

Open

Description

@RongNanZi

I generate code by gpt-4 with prompt in dataset, and evaluate the code in codegeex/codegeex:0.1.23.

the result is 'pass@1': 47.1 that cannot match 'pass@1': 64.3 in the paper.

image

the gpt-4 output is here
gpt4_ncb_java_zh.jsonl.zip

Activity

  1. joygogo1 commented on Jul 23, 2024

    @joygogo1

    请问时如何调用gpt-4运行的?

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

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions