Handle either missing <think> start or </think> end tags #7102
+19
−19
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
|
This is a good change, thanks! |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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Outdated suggestions cannot be applied.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.
The model I have been using frequently does not begin replies with <think> but does include the end </think> tag, and so most 'thoughts' weren't getting put into the nice looking UI boxes. This change fixes that issue, which I have tested. I did not see a way to accomplish this through the chat/instruction template.
It preserves the original handling of missing end </think> tags, and (I believe) fixes a potential bug on original line 120 (the lstrip means if the reply starts with whitespace before a <think> tag then content_start would be at the wrong index).
Checklist: