Generate: check that attention_mask is 2D
#33575
Merged
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
gante
commented
Sep 18, 2024
| @@ -1861,6 +1861,10 @@ def generate( | |||
| model_kwargs["attention_mask"] = self._prepare_attention_mask_for_generation( | |||
| inputs_tensor, generation_config._pad_token_tensor, generation_config._eos_token_tensor | |||
| ) | |||
| elif kwargs_has_attention_mask: | |||
| # TODO (joao): generalize this check with other types of inputs | |||
| if model_input_name == "input_ids" and len(model_kwargs["attention_mask"].shape) > 2: | |||
There was a problem hiding this comment.
I'm not sure len(model_kwargs["attention_mask"].shape) > 2 generalizes (e.g. some audio models have 3d inputs), so I'm fixing the most common use case now and adding a TODO in case this issue pops up again for other input formats
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
BernardZach
pushed a commit
to BernardZach/transformers
that referenced
this pull request
Dec 5, 2024
check attention mask in generate
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Outdated suggestions cannot be applied.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.
What does this PR do?
Fixes #33549
In
generate,attention_maskmust be in its 2D format. This PR adds a check for that.