Add multilingual MATH-500 (mmath500) task#5
Merged
Conversation
added 3 commits
March 25, 2026 12:53
Uses LumiOpen/MATH-500_mt dataset with Qwen3.5-9B (reasoning disabled) as scorer.
Read SCORER_MODEL_BASE_URL/SCORER_MODEL_PATH from env to connect to an existing scorer server started by the eval harness. Falls back to using the eval model (like original math_500) when no scorer server is set up.
Finnish and Danish prompts reviewed by native speakers (Kai, Maria).
|
Kai said the disabled reasoning from the scorer model, ca we set that as the default? |
Pass enable_thinking=False via extra_body to the scorer model so it doesn't waste tokens on chain-of-thought when grading answers.
|
looks good to me |
|
sorry, accidentally git the close with comment |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
mmath500:fi) with model-graded scoring via inspect-aiSCORER_MODEL_BASE_URL,SCORER_MODEL_PATH) instead of hardcoded vLLM init at module import timeTest plan