[ML] add support for question_answering NLP tasks #457
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
benwtrent
added
enhancement
benwtrent
commented
Apr 18, 2022
Comment on lines
+133
to
+134
| if isinstance(response, tuple): | ||
| return torch.stack(list(response), dim=0) |
There was a problem hiding this comment.
our internal BERT inference logic takes the first element of the tuple if the returned value is a tuple. This does not work for question answering models as its a tuple of the starts and ends token scores.
sethmlarson
approved these changes
Apr 27, 2022
|
@benwtrent Looks like there's a merge conflict, can you fix this then I'll merge. |
|
i got it @sethmlarson don't want to merge until the ES side is all approved and merged. Thanks! |
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Outdated suggestions cannot be applied.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.
Adds support for
question_answeringNLP models within the pytorch model uploader.Related: elastic/elasticsearch#85958