Allow non-standard Tokenizers (e.g. CamemBERT) for DPR via new arg #811
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
tholor
reviewed
Feb 8, 2021
There was a problem hiding this comment.
Hey @psorianom,
Looking good to me! Ready to merge once the mypy issue in the CI is resolved and infer_tokenizer_classes is added to the docstring.
|
super! thanks for the quick review :) |
tholor
changed the title
…pr_tokenizer_class
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Outdated suggestions cannot be applied.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.
Hi all!
Regarding issue #783, I propose this simple solution. I realize that this parameter rises some questions, such as, why only determine the class for the tokenizer and not the model also ? how to deal with each model, should we be taking into account each model (query, passage) separately? How deep in configuration detail should we go during the instantiation of the DPRetriever? and so on.
Of course, it is open for improvements :)
Cheers,