open-compass / open-compass/VLMEvalKit

Different evaluate result between different VLMEvalKit version

Open
#523 11 comments 0 reactions 1 assignee View on GitHub

@kennymckormick is already working on this.

Since Nov 1, 2024.

Dominant language
Python
Stars
4.4k
Forks
768
Avg merge
1d 10h
Merged PRs (30d)
17

Description

The official LLaVA-v1.5-7B model gets 1362 points in MME Perception scores under the newest code 69b7b5e.
image
But it turns out to be 1497 under the 027e38c8df0c312135da70a2abf68fe706b05629 commit.
51a97534b233e0574351b8ef2318272
I was sure about the consistent LLaVA code between this two experiement, why would this happened?

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.