fix broken padding setting in HuggingMazeTokenizer #195
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
need a better actual fix for this, probably via some kind of setting in the saved model aaaaaaaaaaaaaaaaaaaaa going to bed for now
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
as of transformer_lens 1.6.1, in pr TransformerLensOrg/TransformerLens#344 the padding size works differently, and our left-padding was being overriden. this fixes it by doing some things in `ZanjHookedTransformer.__init__` and in the `HuggingMazeTokenizer`
mivanit
changed the title
7 tasks
mivanit
changed the title
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
as of transformer_lens 1.6.1, in pr TransformerLensOrg/TransformerLens#344
the padding size works differently, and our left-padding was being overriden. this fixes it
by doing some things in
ZanjHookedTransformer.__init__and in theHuggingMazeTokenizer