Skip to content
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.

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

Logit comparator tool #765

Merged
merged 2 commits into from
Oct 25, 2024
Merged

Logit comparator tool #765

merged 2 commits into from
Oct 25, 2024

Conversation

curt-tigges
Copy link
Contributor

Description

This PR is just a simple tool that allows you to compare the logits produced by a HuggingFace model vs. the TransformerLens version (when loaded without processing). Rather than a rigorous tool, it is simply intended to identify anomalies/bugs in TransformerLens implementations of models, which can then be investigated more thoroughly through other means.

Fixes # (issue)

Type of change

Please delete options that are not relevant.

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds functionality)
  • Breaking change (fix or feature that would cause existing functionality to not work as expected)
  • This change requires a documentation update

Checklist:

  • I have commented my code, particularly in hard-to-understand areas
  • I have made corresponding changes to the documentation
  • My changes generate no new warnings
  • I have added tests that prove my fix is effective or that my feature works
  • New and existing unit tests pass locally with my changes
  • I have not rewritten tests relating to key interfaces which would affect backward compatibility

@bryce13950 bryce13950 merged commit 8029d13 into dev Oct 25, 2024
11 checks passed
@bryce13950 bryce13950 deleted the model-comparator branch October 26, 2024 21:04
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants