New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[WIP] Evals for HallusionBench #31

Open

chiral-carbon wants to merge 2 commits into nahidalam:maya_eval from chiral-carbon:maya_eval

chiral-carbon commented Oct 28, 2024

Adds:

download instructions for dataset in docs/Evaluation.md
script to convert HallusionBench.json to llava format for inference
custom model_vqa_hallusionbench.py script for inference and generating results
script to convert result file back to .json format to evaluate with official evaluation scripts from HallusionBench GitHub repo

The pipeline works correctly, but the custom vqa script has issues.

TODO:

Investigate and fix model_vqa_hallusionbench.py as it fails to generate response correctly, hence defaulting to model prediction category "2" for all inputs and accuracy = 0

chiral-carbon added 2 commits

October 28, 2024 07:44


          evals for hallusion-bench

20b8107


          Merge remote-tracking branch 'upstream/maya_eval' into maya_eval

4e0ecda

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

Labels

None yet