423 commits

Author	SHA1	Message	Date
Shannon Sands	7fe1a40368	readd multistep masking	2025-05-10 09:24:55 +10:00
Shannon Sands	9efd8c1529	linting	2025-05-10 08:44:35 +10:00
Shannon Sands	06c4a9e65c	linting	2025-05-10 08:43:03 +10:00
Shannon Sands	0248cc1227	Removed old code, added comments	2025-05-10 08:39:52 +10:00
Shannon Sands	ba604d44f9	update local server	2025-05-10 08:18:41 +10:00
Shannon Sands	c506bb147e	simplified config and reward	2025-05-10 08:04:39 +10:00
Shannon Sands	7e95c0b67d	moving test sever	2025-05-10 07:47:44 +10:00
Shannon Sands	a7dfd377da	moving env to clean branch	2025-05-10 07:44:29 +10:00
dmahan93	40b12dae60	run pre-commit on all files	2025-05-09 09:54:20 -05:00
dmahan93	b959c30ebf	Merge pull request #31 from NousResearch/fix-math-evals-due-to-updated-dataset ... fix olympiadbench due to upstream changes	2025-05-09 09:42:06 -05:00
dmahan93	e09ae8d3d3	fix olympiadbench due to upstream changes	2025-05-09 09:41:10 -05:00
hjc-puro	629d8c1731	Merge pull request #14 from NousResearch/2025-05-02-server-cli	2025-05-09 13:37:54 +08:00
dmahan93	70cf61c210	add custom server support	2025-05-08 12:01:49 -05:00
Joe Li	63b18d891f	add code execution environment	2025-05-07 21:18:22 -07:00
Artem Yatsenko	0f15be68a2	fix multimodal envs. add view_run_multimodal	2025-05-07 21:53:01 +00:00
dmahan93	46d3a6032a	add ability to only send every n steps	2025-05-07 15:19:26 -05:00
dmahan93	def97fc38c	add an SFT data loading env	2025-05-07 14:56:08 -05:00
edmund	2cb1ff0087	Removed mentions of NousResearch/DeepHermes-3-Llama-3-1B-Preview and swapped it for NousResearch/DeepHermes-3-Llama-3-3B-Preview ... I don't think there is a NousResearch/DeepHermes-3-Llama-3-1B-Preview	2025-05-07 18:03:17 +01:00
teknium1	d2dbab7d22	Add additional completions table info: metric, magnitude, and direction for ground truth	2025-05-04 03:30:50 -07:00
teknium1	c3b80832e9	lowering the defaults for fundamental finance env	2025-05-04 03:05:25 -07:00
hjc-puro	4348dd2ec1	hide complicated openai config override behavior somewhere else	2025-05-03 14:18:50 -07:00
teknium1	a2e36227aa	add metric logging	2025-05-02 02:34:17 -07:00
Dakota Nous	621d00dd80	first commit	2025-04-29 12:10:10 -07:00