NousResearch/atropos
1
0
Fork 0
mirror of https://github.com/NousResearch/atropos.git synced 2026-04-19 12:57:58 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
1541 commits 156 branches 4 tags 164 MiB
Commit graph

21 commits

Author SHA1 Message Date
dmahan93
c421582b6f
Merge pull request #408 from daspartho/verl-integration-fixes 
fix: re-append stop string in math training path
 2026-03-10 23:08:58 -05:00
Partho Das
632ab0161c Revert "rm hardcoded same score check" 
This reverts commit f02c24204d.
 2026-03-10 01:42:44 +05:30
Partho Das
cd3a9163c7 Revert "eval max_token_length consistent with training config" 
This reverts commit 5f52befd38.
 2026-03-08 04:42:02 +05:30
Partho Das
5f52befd38 eval max_token_length consistent with training config 
instead of hardcoding, follows other envs pattern
 2026-03-03 18:03:04 +05:30
Jai Suphavadeeprasit
d2ea8cd612 remove KL 2026-03-02 11:18:52 -05:00
Jai Suphavadeeprasit
2e5fe8bb44 math server 2026-03-02 11:18:52 -05:00
pre-commit-ci[bot]
5cfd1929f1 [pre-commit.ci] auto fixes from pre-commit.com hooks 
for more information, see https://pre-commit.ci
 2026-03-02 11:18:52 -05:00
Jai Suphavadeeprasit
d07ab3e3ce math zero work arounds 2026-03-02 11:18:52 -05:00
Jai Suphavadeeprasit
6e975dd951 Save the eval to the disk 2026-03-02 11:17:44 -05:00
Partho Das
adf075112c re-append stop in math training path 2026-02-24 12:29:57 +05:30
Partho Das
f02c24204d rm hardcoded same score check 2026-02-24 12:29:52 +05:30
Dakota
e6ac3abdcb add managed vllm server 2025-11-07 13:06:49 -06:00
Dakota
5d6d6bb0dc add docs :) 2025-10-29 11:26:43 -05:00
pre-commit-ci[bot]
0d80da5146 [pre-commit.ci] auto fixes from pre-commit.com hooks 
for more information, see https://pre-commit.ci
 2025-10-24 20:10:29 +00:00
dmahan93
7bf4cfbf80 add managed server to make grabbing logprobs easier w/ tokenized items 2025-10-24 13:09:46 -07:00
pre-commit-ci[bot]
1e6a745491 [pre-commit.ci] auto fixes from pre-commit.com hooks 
for more information, see https://pre-commit.ci
 2025-10-16 17:39:04 +00:00
Dakota
c36ec29656 add sglang specific token level logprob handling and server manager/baseline logprob/token fn 2025-10-16 12:38:03 -05:00
Shannon Sands
581d29ff92 Fix import sorting issues manually - Move wandb imports to proper third-party import section - Remove extra blank lines - Skip pre-commit hooks to resolve CI workflow failures 2025-05-23 15:25:40 +10:00
Shannon Sands
93a5da9e32 Fix linting issues across repository - Install pre-commit hooks properly - Fix trailing whitespace and end-of-file issues in metric card generator README - Fix import sorting across multiple files to comply with isort --profile black 2025-05-23 15:17:27 +10:00
dmahan93
e09ae8d3d3 fix olympiadbench due to upstream changes 2025-05-09 09:41:10 -05:00
Dakota Nous
621d00dd80 first commit 2025-04-29 12:10:10 -07:00