Commit graph

6 commits

Author SHA1 Message Date
Andreas Köpf
b2904ccab9 Minor question template & score_answer improvements (#261)
* math prompt improvements
* ignore brackets in complex_arithmetic results
* improve additional instruction in prompt of polynomial_equations
* more strict tests for score_answer in polynomial_equations
* simplify special reward handling
* fix test_intermediate_integration
* fix sokoban dataset
* add common dataset score_answer consistency test
2025-03-04 21:55:09 +01:00
Andreas Koepf (aider)
59461aaec8 fix: Add validation for size parameter in ABConfig 2025-02-11 23:39:57 +01:00
Andreas Koepf (aider)
38922c7e6e fix: Add missing random import in test_ab.py 2025-02-11 23:37:49 +01:00
Andreas Koepf (aider)
2e3e01eda0 test: Add comprehensive unit tests for ABDataset 2025-02-11 23:37:40 +01:00
Andreas Koepf
4b7abd0ffd test: Add test for ABConfig dataset generation 2025-02-11 23:37:38 +01:00
Rich Jones
cb4baab029 Add A::B Challenges 2025-02-11 18:08:25 +01:00