open-thought/reasoning-gym
1
0
Fork 0
mirror of https://github.com/open-thought/reasoning-gym.git synced 2026-04-19 12:58:07 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
1336 commits 21 branches 5 tags 37 MiB

Default branch

main

49b07130b3 · feat: add scoring cascade for reducing false negatives (#526) · Updated 2026-04-17 19:39:15 +00:00
 ZIP  TAR.GZ

Branches

feat/curriculum-exp

70af0ad699 · Update load_fsdp_to_hf.py · Updated 2025-07-28 14:57:15 +00:00    open-thought

31
3
 ZIP  TAR.GZ
feat/multi-curriculum-exp

d73d881073 · reps · Updated 2025-07-28 11:52:31 +00:00    open-thought

27
9
 ZIP  TAR.GZ
fix/update-training-readme

37697e2421 · Update README.md · Updated 2025-07-27 03:59:58 +00:00    open-thought

27
1
 ZIP  TAR.GZ
feat/unsloth-example

c44ff8c542 · updated failing hooks · Updated 2025-06-27 07:59:58 +00:00    open-thought

31
2
 ZIP  TAR.GZ
Miserlou-patch-1

a4006f6d0e · Update README.md - Add Synthetic-2 · Updated 2025-06-24 12:07:55 +00:00    open-thought

35
1
 ZIP  TAR.GZ
rich/genbench

02e0fc1c22 · pull fra main · Updated 2025-06-06 11:43:29 +00:00    open-thought

44
4
 ZIP  TAR.GZ
external-bench-cfg

b7d8832267 · cfg · Updated 2025-04-29 18:23:16 +00:00    open-thought

69
40
 ZIP  TAR.GZ
feat/game-eval-new

cc04297995 · added llama 3b training conf · Updated 2025-04-26 19:30:46 +00:00    open-thought

73
2
 ZIP  TAR.GZ
fix-slow-games

bf9d3b9bab · Changed params in knight_swap and make some clean up · Updated 2025-04-03 14:10:48 +00:00    open-thought

82
5
 ZIP  TAR.GZ
collision-check

4c1a5926dd · Delete files from git history · Updated 2025-04-02 05:26:46 +00:00    open-thought

1336
1254
 ZIP  TAR.GZ
feat/curr-adj

089943b710 · removed results from pr · Updated 2025-04-01 19:40:42 +00:00    open-thought

88
38
 ZIP  TAR.GZ
feat/ollie/tweak-length-reward

3babfbbd29 · wip eval script · Updated 2025-03-27 20:42:53 +00:00    open-thought

93
5
 ZIP  TAR.GZ
rich/qwentweak

eb67c7be9c · add max_model_len to qwen config · Updated 2025-03-21 10:43:43 +00:00    open-thought

95
1
 ZIP  TAR.GZ
rich/verl

e4d54c9e5b · merge · Updated 2025-03-20 12:14:50 +00:00    open-thought

96
45
 ZIP  TAR.GZ
revert_breaking_commits

37170afb50 · Revert "figlet font curriculum" · Updated 2025-03-18 22:36:06 +00:00    open-thought

99
2
 ZIP  TAR.GZ
rich/fixdice

60d9a29d38 · fix dice · Updated 2025-03-10 23:44:48 +00:00    open-thought

171
3
 ZIP  TAR.GZ
rich/docsandstuff

789fa11815 · add count to gallery · Updated 2025-03-07 13:58:32 +00:00    open-thought

216
1
 ZIP  TAR.GZ
get_batch_epoch_param

8dc6cb5228 · fix: Move EpochTrackingDataLoader after ReasoningGymDataset to resolve undefined name error · Updated 2025-02-22 21:18:38 +00:00    open-thought

345
7
 ZIP  TAR.GZ
curriculum

18b6e71fa9 · Refactor LetterJumble · Updated 2025-02-09 12:38:16 +00:00    open-thought

955
21
 ZIP  TAR.GZ
curriculum_refactor

f64d1eb5e3 · Refactor LetterJumble · Updated 2025-02-09 12:36:07 +00:00    open-thought

955
18
 ZIP  TAR.GZ