Commit graph

15 commits

Author SHA1 Message Date
joesharratt1229
d0faada7a0 added futoshiki and tower hanou (#316)
* added futoshiki and tower hanou

* corrected failed unit tests
2025-03-11 00:12:32 +01:00
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 Köpf
28dc0932c4 Merge pull request #178 from olliestanley/feature/unsloth-train
Add minimal working GRPO training example with Unsloth
2025-02-21 15:37:24 +01:00
Andreas Koepf
ff5b210106 use native types List->list, Dict->dict, Set->set, Tuple->tuple 2025-02-21 15:15:38 +01:00
Oliver
31941d09e6 Answer scoring fixes to address edge cases 2025-02-20 22:04:01 +00:00
Andreas Koepf
5803a2962e more tolerant parsing of futoshiki answers 2025-02-16 14:23:40 +01:00
Oliver
d42b84ef4c Add more instruction to generated questions 2025-02-15 13:47:54 +00:00
Oliver
b730709e34 formatting 2025-02-13 19:00:18 +00:00
Oliver
c716affdd0 Correct string formatting 2025-02-13 18:52:48 +00:00
Oliver
a53073278a Remove rng param 2025-02-09 21:26:03 +00:00
Oliver
0627f2b02d Greatly speed up solver 2025-02-09 21:23:53 +00:00
Oliver
26439cb943 Finish first draft futoshiki solver/gen 2025-02-07 00:09:35 +00:00
Oliver
1d88796c8d Revert "Experiment with alternative solving/generation approach"
This reverts commit f91ee8a5b7.
2025-02-07 00:06:38 +00:00
Oliver
f91ee8a5b7 Experiment with alternative solving/generation approach 2025-02-06 23:58:09 +00:00
Oliver
af16670c01 Initial draft of Futoshiki generator 2025-02-04 17:42:57 +00:00