e-tornike commented 1 year ago

PR Description

This PR fixes the tokenization mismatch of long sequences.

Motivation and Context

References issue: #95

Tests and Coverage

Types of changes

[x] Bug fix (non-breaking change which fixes an issue)
[ ] New feature (non-breaking change which adds functionality)
[ ] Docs (Added to or improved Transformers Interpret's documentation)
[ ] Breaking change (fix or feature that would cause existing functionality to not work as expected)

Final Checklist:

[x] My code follows the code style of this project.
[ ] I have updated the documentation accordingly.
[ ] I have added tests to cover my changes.
[ ] All new and existing tests passed.

e-tornike commented 1 year ago

Oh, I followed the contributing guideline. It seems that the dev branch is not up-to-date.

cdpierse commented 1 year ago

Ah yes apologies, that is out of date, I'm no longer doing merge into dev and am doing PR's directly into master could you change the target branch of this PR ?

e-tornike commented 1 year ago

No problem. I've changed the branch of the PR.

cdpierse / transformers-interpret

Fix/sequence truncation #111

PR Description

Motivation and Context

Tests and Coverage

Types of changes

Final Checklist: