├── .gitignore ├── .gitmodules ├── CHANGELOG.md ├── CITATION.cff ├── LICENCE ├── Makefile ├── README.md ├── assets └── flow.svg ├── evaluate_model.py ├── evaluate_model_outputs.py ├── examples ├── few_shot_answers.csv ├── model_outputs.csv └── sample_answers.csv ├── extract_answers.py ├── output.csv ├── pyproject.toml ├── scripts └── publish.sh ├── src └── math_verify │ ├── __init__.py │ ├── errors.py │ ├── few_shots.py │ ├── grader.py │ ├── metric.py │ ├── parser.py │ ├── tasks.py │ └── utils.py └── tests ├── __init__.py ├── test_all.py ├── test_boxed.py ├── test_configs.py ├── test_numina_cases.py ├── test_open_thoughts.py ├── test_raise_on_error.py ├── test_strict.py ├── test_string_extraction.py ├── test_timeout.py └── test_yujianll.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/huggingface/Math-Verify/HEAD/.gitignore -------------------------------------------------------------------------------- /.gitmodules: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/huggingface/Math-Verify/HEAD/.gitmodules -------------------------------------------------------------------------------- /CHANGELOG.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/huggingface/Math-Verify/HEAD/CHANGELOG.md -------------------------------------------------------------------------------- /CITATION.cff: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/huggingface/Math-Verify/HEAD/CITATION.cff -------------------------------------------------------------------------------- /LICENCE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/huggingface/Math-Verify/HEAD/LICENCE -------------------------------------------------------------------------------- /Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/huggingface/Math-Verify/HEAD/Makefile -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/huggingface/Math-Verify/HEAD/README.md -------------------------------------------------------------------------------- /assets/flow.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/huggingface/Math-Verify/HEAD/assets/flow.svg -------------------------------------------------------------------------------- /evaluate_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/huggingface/Math-Verify/HEAD/evaluate_model.py -------------------------------------------------------------------------------- /evaluate_model_outputs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/huggingface/Math-Verify/HEAD/evaluate_model_outputs.py -------------------------------------------------------------------------------- /examples/few_shot_answers.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/huggingface/Math-Verify/HEAD/examples/few_shot_answers.csv -------------------------------------------------------------------------------- /examples/model_outputs.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/huggingface/Math-Verify/HEAD/examples/model_outputs.csv -------------------------------------------------------------------------------- /examples/sample_answers.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/huggingface/Math-Verify/HEAD/examples/sample_answers.csv -------------------------------------------------------------------------------- /extract_answers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/huggingface/Math-Verify/HEAD/extract_answers.py -------------------------------------------------------------------------------- /output.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/huggingface/Math-Verify/HEAD/output.csv -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/huggingface/Math-Verify/HEAD/pyproject.toml -------------------------------------------------------------------------------- /scripts/publish.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/huggingface/Math-Verify/HEAD/scripts/publish.sh -------------------------------------------------------------------------------- /src/math_verify/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/huggingface/Math-Verify/HEAD/src/math_verify/__init__.py -------------------------------------------------------------------------------- /src/math_verify/errors.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/huggingface/Math-Verify/HEAD/src/math_verify/errors.py -------------------------------------------------------------------------------- /src/math_verify/few_shots.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/huggingface/Math-Verify/HEAD/src/math_verify/few_shots.py -------------------------------------------------------------------------------- /src/math_verify/grader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/huggingface/Math-Verify/HEAD/src/math_verify/grader.py -------------------------------------------------------------------------------- /src/math_verify/metric.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/huggingface/Math-Verify/HEAD/src/math_verify/metric.py -------------------------------------------------------------------------------- /src/math_verify/parser.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/huggingface/Math-Verify/HEAD/src/math_verify/parser.py -------------------------------------------------------------------------------- /src/math_verify/tasks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/huggingface/Math-Verify/HEAD/src/math_verify/tasks.py -------------------------------------------------------------------------------- /src/math_verify/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/huggingface/Math-Verify/HEAD/src/math_verify/utils.py -------------------------------------------------------------------------------- /tests/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tests/test_all.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/huggingface/Math-Verify/HEAD/tests/test_all.py -------------------------------------------------------------------------------- /tests/test_boxed.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/huggingface/Math-Verify/HEAD/tests/test_boxed.py -------------------------------------------------------------------------------- /tests/test_configs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/huggingface/Math-Verify/HEAD/tests/test_configs.py -------------------------------------------------------------------------------- /tests/test_numina_cases.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/huggingface/Math-Verify/HEAD/tests/test_numina_cases.py -------------------------------------------------------------------------------- /tests/test_open_thoughts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/huggingface/Math-Verify/HEAD/tests/test_open_thoughts.py -------------------------------------------------------------------------------- /tests/test_raise_on_error.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/huggingface/Math-Verify/HEAD/tests/test_raise_on_error.py -------------------------------------------------------------------------------- /tests/test_strict.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/huggingface/Math-Verify/HEAD/tests/test_strict.py -------------------------------------------------------------------------------- /tests/test_string_extraction.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/huggingface/Math-Verify/HEAD/tests/test_string_extraction.py -------------------------------------------------------------------------------- /tests/test_timeout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/huggingface/Math-Verify/HEAD/tests/test_timeout.py -------------------------------------------------------------------------------- /tests/test_yujianll.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/huggingface/Math-Verify/HEAD/tests/test_yujianll.py --------------------------------------------------------------------------------