770 commits

Author	SHA1	Message	Date
pre-commit-ci[bot]	60fb6cae11	[pre-commit.ci] auto fixes from pre-commit.com hooks ... for more information, see https://pre-commit.ci	2026-02-20 04:58:47 +00:00
Jai Suphavadeeprasit	ccdd5a1ca6	linting	2026-02-19 23:57:47 -05:00
Jai Suphavadeeprasit	11fabaa7f7	gsm8k trial	2026-02-19 21:55:33 -05:00
Jai Suphavadeeprasit	0dcc9156d2	change OPD style	2026-02-19 19:19:23 -05:00
Jai Suphavadeeprasit	527433b5bc	change OPD style	2026-02-19 17:08:27 -05:00
Jai Suphavadeeprasit	33f5696171	Merge branch 'pipelineRL' into OnPolicyDistillation	2026-02-19 16:39:21 -05:00
Jai Suphavadeeprasit	00908ec366	packageification	2026-02-19 15:16:24 -05:00
Jai Suphavadeeprasit	bc0f9ee625	debug changes	2026-02-17 08:15:07 -05:00
Jai Suphavadeeprasit	0e81c62e90	on policy changes	2026-02-16 17:39:37 -05:00
Jai Suphavadeeprasit	becadb54b0	Fix math_server_zero.py to support CLI OpenAI arguments ... Change ServerBaseline to APIServerConfig in config_init() so that --openai.base_url and other CLI arguments work for on-policy distillation. Co-authored-by: Cursor <cursoragent@cursor.com>	2026-02-16 17:18:01 -05:00
Jai Suphavadeeprasit	2501e33ae3	nccl loras	2026-02-13 11:26:25 -05:00
Jai Suphavadeeprasit	950be6f0d4	math server	2026-02-13 11:26:25 -05:00
pre-commit-ci[bot]	11f495a381	[pre-commit.ci] auto fixes from pre-commit.com hooks ... for more information, see https://pre-commit.ci	2026-02-13 11:26:25 -05:00
Jai Suphavadeeprasit	33505fe981	math zero work arounds	2026-02-13 11:26:25 -05:00
Jai Suphavadeeprasit	4cf0416e78	evals errors	2026-02-13 11:26:25 -05:00
Jai Suphavadeeprasit	abe4cec824	evals errors	2026-02-13 11:26:25 -05:00
Jai Suphavadeeprasit	7326bec25c	evals erros	2026-02-13 11:26:25 -05:00
Jai Suphavadeeprasit	5d4baf8c76	evals	2026-02-13 11:26:25 -05:00
Jai Suphavadeeprasit	67b322353d	evals	2026-02-13 11:26:25 -05:00
Jai Suphavadeeprasit	806888d9d3	pipelineRL	2026-02-13 11:26:25 -05:00
Jai Suphavadeeprasit	407a22ba12	Save the eval to the disk	2026-02-13 11:25:49 -05:00
dmahan93	1580ab5934	Merge pull request #365 from alireza78a/fix/replace-debug-prints-with-logger ... fix: replace debug print statements with logger	2026-02-09 21:01:38 -08:00
Alireza	6b92ee16ec	fix duplicate code + add safety checks	2026-02-09 10:58:49 +03:30
alireza78a	1303cb59e8	fix: replace debug print statements with logger in dataset_env and infinimath_env	2026-02-07 14:51:33 +00:00
Teknium	462abbebf7	Merge pull request #339 from VolodymyrBg/bg ... chore: fix typos	2026-01-31 09:03:17 -08:00
Teknium	efc85528bc	Merge pull request #338 from windlgrass/fix-init-current-item ... fix: initialize current_item in __init__ to prevent AttributeError	2026-01-31 09:02:06 -08:00
Teknium	8b22416dd4	Merge branch 'main' into fix-duplicate-code	2026-01-31 08:52:43 -08:00
VolodymyrBg	f285bbd417	Update refusalbench_environment.py	2026-01-29 12:43:15 +02:00
VolodymyrBg	94f29eac18	Update simpleqa_eval.py	2026-01-29 12:42:28 +02:00
VolodymyrBg	347edc9188	Update instructions.py	2026-01-29 12:31:52 +02:00
VolodymyrBg	466fd96b41	Update patient.py	2026-01-29 12:16:31 +02:00
VolodymyrBg	39f3509965	Update instruction_following_algorithm_environment.py	2026-01-29 11:22:05 +02:00
Wind	eb5be87f81	Update dataset_env.py	2026-01-29 15:16:34 +07:00
Wind	6c2f1ac408	Update dataset_env.py	2026-01-29 15:16:05 +07:00
Wind	2607942ffa	Update dataset_env.py	2026-01-29 15:11:31 +07:00
dmahan93	e8fd85429f	Merge pull request #323 from NousResearch/pre-commit-ci-update-config ... [pre-commit.ci] pre-commit autoupdate	2026-01-26 11:02:44 -08:00
dmahan93	b8ec055942	Merge pull request #324 from DeVikingMark/fix/gradient-quantile-prefix ... fix: use correct prefix for gradient quantiles with NaN/Inf	2026-01-26 11:01:36 -08:00
dmahan93	cf2b280d52	Merge pull request #325 from crStiv/typo ... fix: multiple typos of different importance	2026-01-26 11:00:44 -08:00
pre-commit-ci[bot]	2be7442dd5	[pre-commit.ci] auto fixes from pre-commit.com hooks ... for more information, see https://pre-commit.ci	2026-01-26 16:41:26 +00:00
Wind	42601e2325	Update instructions_utils.py	2026-01-26 17:24:12 +07:00
Wind	7feb826fed	Update instructions_registry.py	2026-01-26 17:23:39 +07:00
Wind	883043de49	Update instructions.py	2026-01-26 17:14:57 +07:00
dmahan93	5af29933a7	Merge pull request #305 from alt-glitch/sid/verifiers ... Verifiers Integration	2026-01-23 10:21:49 -08:00
balyan.sid@gmail.com	4ba69d3a80	revert to using evalbase	2026-01-23 23:41:32 +05:30
balyan.sid@gmail.com	5a20abdce7	switch eval to use managed server adapter impl. moved managed server ... adapter	2026-01-23 23:26:29 +05:30
Siddharth Balyan	32d12c05c3	Merge branch 'main' into sid/verifiers	2026-01-23 21:57:13 +05:30
Wind	4f24688d18	Update coding_server.py	2026-01-22 15:19:28 +07:00
Teknium	faf84d241c	Merge branch 'main' into patch-1	2026-01-21 05:55:56 -08:00
crStiv	b44eca5a5e	Fix typo in TODO comment in plot.py	2026-01-20 00:14:51 +02:00
crStiv	8edfbe1de4	Fix typo in error message for resume type	2026-01-20 00:12:12 +02:00