CU-8693t24ed: Add workaround for older DeID models in newer MedCAT #397
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
tomolopolis
reviewed
Feb 8, 2024
|
PS: |
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Outdated suggestions cannot be applied.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.
In
medcat==1.9.3there was a change to thetransformersdependency range (fromtransformers>=4.19.2,<4.22.0totransformers>=4.34.0). That change also removed the comment that the pin was for the DeID model to work.I've looked into the issue and believe I've got a workaround for it.
The newer versions of transformers (starting rom
4.22.0) expect the tokenizer to have a specific attribute (_in_target_context_manager). However, as we load it off disk, the attribute doesn't exist since the saved version is older.The change reference:
huggingface/transformers#18325
So what this PR does is add the missing attribute to the tokenizer.
I've tested locally with the DeID model and after this change, it worked just fine.
PS:
This isn't really easy to test automatically. The only way we could do that would be to include (or potentially download during test time) an older DeID model. But I don't want to clutter the repo with that.