Fix the string_view subscript overflow for Phi4 Tokenizer #899
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
wenbingl
commented
Feb 28, 2025
| auto res = m_text.substr(0, j); | ||
| m_text = m_text.substr(j); | ||
| return res; | ||
| } | ||
| i = j; |
There was a problem hiding this comment.
@sayanshaw24, any reason that why we need use both i and j here?
There was a problem hiding this comment.
it's because j is a temp variable; before we copy i to it here: https://github.com/microsoft/onnxruntime-extensions/blob/main/operators/tokenizer/bpe_utils.hpp#L373 and so in this line we reset i before the last regex check (for (?i:'s|'t|'re|'ve|'m|'ll|'d)?)
sayanshaw24
approved these changes
Feb 28, 2025
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Outdated suggestions cannot be applied.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.
No description provided.