Commit graph

763 commits

Author SHA1 Message Date
Allan Niemerg
532024d01e remove unnecessary code, change log level 2025-09-08 11:22:08 -05:00
Allan Niemerg
1a2551c812 fixed formatting for HTML inclusion 2025-09-08 11:22:08 -05:00
Allan Niemerg
265e4cd69f working HTML writing 2025-09-08 11:22:08 -05:00
Allan Niemerg
8997a1d750 working environment 2025-09-08 11:22:08 -05:00
Allan Niemerg
374f63acc0 remove unneeded dataset utils 2025-09-08 11:22:08 -05:00
Allan Niemerg
86473f9551 currently making complete rollouts 2025-09-08 11:22:08 -05:00
Allan Niemerg
64a82c4b4f Fix BLEUBERI environment server integration 2025-09-08 11:22:08 -05:00
Allan Niemerg
3109fe349b Update BLEUBERI README with OpenAI API instructions and remove redundant reward functions 2025-09-08 11:22:08 -05:00
Allan Niemerg
a520f5f663 Integrate BLEUBERI as a submodule with direct import of reference-based reward functions. 2025-09-08 11:22:08 -05:00
Allan Niemerg
5bb5bd2c3d Add BLEUBERI environment for reference-based RL 2025-09-08 11:21:27 -05:00
Alvarez
bad4fb84df
Update plot.py 2025-08-30 19:22:57 +02:00
pre-commit-ci[bot]
127b5736a5 [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
2025-08-28 18:08:26 +00:00
Jai Suphavadeeprasit
7462f45447 sampling params 2025-08-28 14:07:29 -04:00
Jai Suphavadeeprasit
3944e7ef9b linting 2025-08-28 12:54:08 -04:00
Jai Suphavadeeprasit
1bfe294414 Other major changes 2025-08-28 12:24:08 -04:00
Jai Suphavadeeprasit
ec09a1caee Other major changes 2025-08-28 12:04:42 -04:00
Jai Suphavadeeprasit
b56d03b25c changes linting 2025-08-28 03:53:12 -04:00
Jai Suphavadeeprasit
f6f3c04313 organized 2025-08-28 03:35:41 -04:00
Jai Suphavadeeprasit
0bcc406b02 race conditions 2025-08-28 03:35:41 -04:00
Jai Suphavadeeprasit
53710e95ec min@ 2025-08-28 03:35:41 -04:00
pre-commit-ci[bot]
8b0a70131b [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
2025-08-20 07:28:38 +00:00
teknium
a8c3e67062 rebuild text reversal env 2025-08-20 07:27:58 +00:00
pre-commit-ci[bot]
dec92b2a6e [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
2025-08-19 16:30:37 +00:00
Jai Suphavadeeprasit
6266748027 Other linting 2025-08-19 12:20:33 -04:00
Jai Suphavadeeprasit
4d404c0be6 os 2025-08-19 12:05:04 -04:00
Jai Suphavadeeprasit
aac9f5a926 linting 2025-08-19 12:03:13 -04:00
pre-commit-ci[bot]
c1d97b85a3 [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
2025-08-19 12:03:13 -04:00
Jai Suphavadeeprasit
8b55815e2f Linting fixes 2025-08-19 12:03:13 -04:00
pre-commit-ci[bot]
750489493f [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
2025-08-19 12:03:13 -04:00
Jai Suphavadeeprasit
f76f9d1596 cleanup 2025-08-19 12:03:13 -04:00
pre-commit-ci[bot]
62b72589c6 [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
2025-08-19 12:03:13 -04:00
Jai Suphavadeeprasit
e55a7a0100 add_danger 2025-08-19 12:03:13 -04:00
teknium
bed7ddcb95 add more default categories 2025-08-19 12:03:13 -04:00
teknium
39f0103313 fix dataset 2025-08-19 12:03:13 -04:00
teknium
ff7a2569dc update default max_toks 2025-08-19 12:03:13 -04:00
teknium
69135320b4 initial refusalbenchv2 2025-08-19 12:03:13 -04:00
pre-commit-ci[bot]
8d81198b99 [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
2025-08-13 21:34:59 +00:00
teknium
65e5386de9 Merge branch 'reverse-text-env' of https://github.com/NousResearch/atropos into reverse-text-env 2025-08-13 21:33:57 +00:00
teknium
5d1854d330 add curriculum system 2025-08-13 21:33:52 +00:00
pre-commit-ci[bot]
781d4320e9 [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
2025-08-13 21:16:48 +00:00
teknium
37013e9ce4 Add length penalty 2025-08-13 21:16:09 +00:00
teknium
564cee80d9 Merge branch 'reverse-text-env' of https://github.com/NousResearch/atropos into reverse-text-env 2025-08-12 20:51:15 +00:00
teknium
64e2792ec9 add text reversal env section to readme 2025-08-12 20:51:09 +00:00
pre-commit-ci[bot]
21605d100c [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
2025-08-12 20:51:05 +00:00
teknium
bcdc51a6fc Add reversed text environment 2025-08-12 20:47:48 +00:00
pre-commit-ci[bot]
321478dd5f [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
2025-08-12 06:45:36 +00:00
interstellarninja
2f6025e65b fixing precommit formatting errors 2025-08-12 02:42:47 -04:00
shannonsands
46f0602227
Diplomacy trainer env (#227)
* minimal implementation, simplified challenge registry

* need game save logic

* fixed challenge gen, works with local test

* updated challenge gen with wider ranges, working with local script

* runs working correctly, wandb stats look ok

* linting

* Add diplomacy environment with AI_Diplomacy submodule

- Add diplomacy_env_minimal.py for diplomacy game environment
- Add atropos_client_minimal.py for client interface
- Add diplomacy_local_server.py for local game server
- Add AI_Diplomacy submodule from GoodStartLabs/AI_Diplomacy
- Fix import ordering and remove unused imports

* test file working, moving to cluster to test training

* updated gitignore

* removed logs

* minor fixes, training running now

* readded proxy reg and queue system

* linting

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* queue gameid bug, refactored

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* cleaned up configs & allowed for openrouter models to be easily used

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* linting

* Remove duplicate dependencies from diplomacy requirements.txt

Only keep AI_Diplomacy-specific dependencies that aren't already in the main project

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2025-08-12 09:02:16 +10:00
shannonsands
47cb15745c
Textworld minimal (#225)
* minimal implementation, simplified challenge registry

* need game save logic

* fixed challenge gen, works with local test

* updated challenge gen with wider ranges, working with local script

* runs working correctly, wandb stats look ok

* linting

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* removed unused imports

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2025-08-01 10:16:35 +10:00
Teknium
be66e120d9
Merge pull request #219 from NousResearch/add-arenahard-v1-environment
Add arena-hard v1 environment
2025-07-30 09:35:14 -07:00