This repository has been archived by the owner on Nov 22, 2022. It is now read-only.
Standardize RoBERTa Tensorizer Vocab Creation #1113
Closed
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Outdated suggestions cannot be applied.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.
Summary: As part of the Tensorizer refactor, I standarize vocab creation for the RoBERTa tesorizer i.e. remove vocab creation from the tokenizer and bring it into the tensorizer. I also make the special tokens for RoBERTa confiurable so that we don't need a separate tensorizer if we decide to train RoBERTa with different special tokens. I also revert some of the changes made in D17974656 which break loading of fairseq vocab for all tensorizers.
Reviewed By: chenyangyu1988
Differential Revision: D18289234