Fix sequence_length
option in CLIPTokenizer
#2031
Open
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Outdated suggestions cannot be applied.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.
Fix #2018
There is a bug in
CLIPTokenizer
where specifyingsequence_length
causes it to incorrectly usetf.RaggedTensor.to_tensor
for padding, instead ofself.pad_token_id
.Additionally, we need to compute
padding_mask
manually rather than relying ontf.RaggedTensor.to_tensor
for the same reason.This PR resolves the issue.