Bug fix in ModularTokenizer.decode() when the input is torch.Tensor type
#376
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
mosheraboh
reviewed
Oct 21, 2024
| @@ -1148,6 +1149,9 @@ def decode(self, ids: Iterable, skip_special_tokens: Optional[bool] = False) -> | |||
| Returns: | |||
| str: _description_ | |||
| """ | |||
| if isinstance(ids, Tensor): | |||
| # Tokens in 'self.decoder_dict' are integers, and not singletons | |||
There was a problem hiding this comment.
Do we need also to move it to CPU before? in cases the tensor is on the GPU.
There was a problem hiding this comment.
Good question, so it's being done automatically:
Returns the tensor as a (nested) list. For scalars, a standard Python number is returned, just like with item(). Tensors are automatically moved to the CPU first if necessary.
https://pytorch.org/docs/stable/generated/torch.Tensor.tolist.html
There was a problem hiding this comment.
singletons?
Meaning a tensor with a single item in it. Will make it clearer
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Outdated suggestions cannot be applied.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.
Another "solution" would be to validate that the input value is a list of integers.
The main problem in the current implementation, is that the user is not aware of the type mismatch - the token just appears as missing (!)