fix: correct judge prompt construction in MM-MT-Bench#14
Open
abdelhadi703 wants to merge 1 commit into
Open
Conversation
- Extract message content from dicts in get_judgement() instead of passing full message dicts to the judge prompt builder - Add _extract_text_content() to extract plain text from reference answers that may be lists of typed chunks - Add _convert_image_chunks() to convert PIL image objects to base64 image_url chunks for the judge model - Fix _add_or_append_chunk() to actually append image chunks to the prompt instead of returning them - Fix operator precedence in _wait_till_healthy() health check condition Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Author
|
Hi @mistralai/team, Bumping this fix for MM-MT-Bench judge prompt construction. It ensures correct prompt formatting for evaluation. Happy to address any review comments. Thanks! |
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
_add_or_append_chunk()to actually append image chunks to the promptmodels.py)Fixes #8
Changes
eval/tasks/mm_mt_bench.py: Extract.contentfrom message dicts, extract text from reference answer chunks, convert PIL images to base64 image_url chunks, fix image chunk appendingeval/models.py: Add parentheses to fix operator precedence in_wait_till_healthy()Test plan
🤖 Generated with Claude Code