fix the introduction of an additional space and split words in subtokens #1198
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
Codecov ReportAll modified and coverable lines are covered by tests ✅
Additional details and impacted files@@ Coverage Diff @@
## develop #1198 +/- ##
========================================
Coverage 68.62% 68.62%
========================================
Files 161 161
Lines 15966 15966
========================================
Hits 10957 10957
Misses 5009 5009
Flags with carried forward coverage won't be shown. Click here to find out more.
🚀 New features to boost your workflow:
|
trebedea
reviewed
Jun 17, 2025
| @@ -1311,8 +1311,8 @@ def _prepare_params( | |||
| if stream_first: | |||
| words = chunk_str_rep.split() | |||
| if words: | |||
| yield words[0] | |||
| for word in words[1:]: | |||
| # yield words[0] | |||
There was a problem hiding this comment.
This adds an extra space before the first word, no?
I think the previous logic was good here.
| @@ -1297,7 +1297,7 @@ def _prepare_params( | |||
| ) | |||
|
|
|||
| async for chunk_list, chunk_str_rep in buffer_strategy(streaming_handler): | |||
| chunk_str = " ".join(chunk_list) | |||
| chunk_str = "".join(chunk_list) | |||
There was a problem hiding this comment.
Good catch! I assume all tokenizers are adding spaces and any other whitespace and special chars in some of the chunks, so this should work for any LLM provider.
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Outdated suggestions cannot be applied.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.
Description
Fix a problem in which words composed in sub-tokens are spitted in the based sub-tokens.
@Pouyanpi
Related Issue(s)
Solve issue: #1197
Checklist