Fixed substring not found error #87
Open
Conversation
This file contains hidden or 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
Fixed substring not found error by keeping skip_special_tokens=True for ans_tokenizer.decode in _extract answers.
|
@Hemanth21k Thanks a lot for this answer. Spent a lot of time debugging the issue but was unable to debug it until I found this. Keep on doing the good job. |
|
|
||
| dec = [self.ans_tokenizer.decode(ids, skip_special_tokens=False) for ids in outs] | ||
| dec = [self.ans_tokenizer.decode(ids, skip_special_tokens=True) for ids in outs] | ||
| answers = [item.split('<sep>') for item in dec] |
There was a problem hiding this comment.
Sorry, I'm wondering if you set skip_special_tokens=True, will item.split('<sep>') still work? Will <sep> be skipped in decode?
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
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Outdated suggestions cannot be applied.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.
Fixed substring not found error by keeping skip_special_tokens=True for ans_tokenizer.decode in _extract answers.