feat: Add Zebra Grid dataset support with ZeroEval alignment#2234
Open
max-yue wants to merge 1 commit intoopen-compass:mainfrom
Open
feat: Add Zebra Grid dataset support with ZeroEval alignment#2234max-yue wants to merge 1 commit intoopen-compass:mainfrom
max-yue wants to merge 1 commit intoopen-compass:mainfrom
Conversation
- Add ZebraGridDataset class for loading allenai/ZebraLogicBench-private - Implement ZebraGridEvaluator with puzzle accuracy and cell accuracy metrics - Use exact ZeroEval prompt template and JSON extraction logic - Include complete evaluation configuration and model setup - Achieve 82.4% accuracy on 1000 samples, close to official 84.8% Features: - Supports HuggingFace datasets integration - Compatible with VLLM backend for efficient inference - Provides detailed evaluation metrics (puzzle_accuracy, cell_accuracy) - Includes example Qwen3-8B thinking model configuration Usage: python run.py opencompass/configs/eval_zebra_grid.py --work-dir ./outputs/zebra_grid
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
📝 Description
Add support for Zebra Grid logic puzzle dataset from allenai/ZebraLogicBench-private with exact ZeroEval alignment.
🚀 Features
🧪 Testing
Tested on 1000 samples with Qwen3-8B thinking model:
📚 Usage
🔗 Related