Releases: open-thought/reasoning-gym
Releases · open-thought/reasoning-gym
v0.1.24
What's Changed
- [fix #484] resolve basic_arithmetic fails when size is large by @theblackcat102 in #485
- Curr exp by @joesharratt1229 in #487
- fix: Training README.md by @zafstojano in #491
- Add option to increase timeout by @SzymonOzog in #493
- Run categories in parallel by @SzymonOzog in #492
- feat(curriculum): Knights and Knaves configs by @zafstojano in #488
- fix(evaluation): Add instructions for running on MMLU Pro by @zafstojano in #497
- (README): add GEM to projects using RG by @zafstojano in #498
- (README): Add discord badge by @zafstojano in #500
- fix enconding to be able to run on win by @denini08 in #502
- Add OptimalThinkingBench to Projects Using RG by @Miserlou in #503
- Add probability dataset (initial: Coin Flip dataset + curriculum) by @kumaranant1 in #505
- (README): add gensyn paper by @zafstojano in #506
- fix: Register missing
coin_flipby @zafstojano in #507
New Contributors
- @SzymonOzog made their first contribution in #493
- @denini08 made their first contribution in #502
- @kumaranant1 made their first contribution in #505
Full Changelog: v0.1.23...v0.1.24
v0.1.23
What's Changed
- add kakurasu env by @olliestanley in #460
- Update README.md - Star History by @zafstojano in #463
- add survo env by @olliestanley in #461
- fix color_cubes answer strings, update gallery with latest envs by @olliestanley in #464
- Fix/verl example by @joesharratt1229 in #465
- fix: Rounding issues in score_answer and add unit tests by @Adefioye in #462
- add minimal verifiers example by @olliestanley in #472
- tutorial(training): Add a minimal example with
trlby @zafstojano in #473 - Update README.md by @zafstojano in #475
- corrected countdown issue by @joesharratt1229 in #479
- better usage demo in readme by @olliestanley in #477
- Update README.md (RLSwarm GenRL) by @Miserlou in #480
- Feat/unsloth example by @joesharratt1229 in #482
- Update README.md by @zafstojano in #483
Full Changelog: v0.1.22...v0.1.23
v0.1.22
What's Changed
- abs path for images by @zafstojano in #449
- support python 3.10 by @olliestanley in #450
- Update README.md by @zafstojano in #451
- Update README.md with Atropos by @zafstojano in #458
- simplify training setup instructions by @olliestanley in #454
- Use raw URLs for images in README.md by @andreaskoepf in #459
Full Changelog: v0.1.20...v0.1.22