hjc-puro
3e1eba6e92
rename method
2025-07-11 00:39:28 +00:00
pre-commit-ci[bot]
5aacb1ea9b
[pre-commit.ci] auto fixes from pre-commit.com hooks
...
for more information, see https://pre-commit.ci
2025-07-11 00:26:48 +00:00
hjc-puro
e601251893
gsm8k eval example
2025-07-11 00:22:36 +00:00
hjc-puro
afe4fc318f
sample level logging
2025-07-10 02:03:07 +00:00
hjc-puro
f4de3ad6f5
add printing
2025-07-09 23:35:26 +00:00
pre-commit-ci[bot]
9340791a6c
[pre-commit.ci] auto fixes from pre-commit.com hooks
...
for more information, see https://pre-commit.ci
2025-07-07 21:53:41 +00:00
dmahan93
ecc5eebeca
Merge pull request #167 from paulsengh/feat/pay-to-play-env
...
feat: add pay-to-play environment with mixture of judges and micropay…
2025-07-07 09:02:46 -05:00
dmahan93
58446dbcb1
Merge pull request #204 from NousResearch/multienv-enforce-mins
...
Multienv with enforced minimum samples in a batch
2025-07-07 08:53:43 -05:00
Dakota
08e14cc745
feat: add minimum batch allocation support for environments
...
- Add min_batch_allocation parameter to ensure environments contribute minimum proportion to each batch
- Implement grab_batch_with_minimum_allocations function with proper scaling when allocations exceed 100%
- Add mixed-size group buffering to handle variable-sized data submissions
- Update server to use minimum allocation logic when any env has min_batch_allocation set
- Add comprehensive tests for minimum allocation scenarios
- Update documentation in API README and CONFIG.md
- Update example environments to demonstrate the feature
This feature allows critical environments to guarantee they contribute at least a specified proportion (0.0-1.0) to each training batch, ensuring important data sources are always represented during training.
🤖 Generated with [Claude Code](https://claude.ai/code )
Co-Authored-By: Claude <noreply@anthropic.com>
2025-07-07 08:50:28 -05:00
emmmm
10f1b466b6
Update curriculum.py
2025-07-02 10:22:33 +02:00
Alex Pikme
ba992757e1
fix dead link README.md
2025-06-25 10:51:21 +02:00
dmahan93
5b2b5e9947
Merge pull request #192 from rnkrtt/main
...
Fix typo in author name Gurning -> Gurung in community README
2025-06-23 10:15:58 -05:00
Merkel Tranjes
af1c98d7a8
Update README.md
2025-06-23 16:23:02 +02:00
Tomass
14917440db
fix duplicate plot.py
2025-06-23 15:32:54 +02:00
Teknium
8bf0312b8a
Merge pull request #190 from crStiv/a
...
fix: multiple typos of different importance
2025-06-22 13:15:39 -07:00
Jeremy Melvin
3bed7c64b9
Ethereum Virtual Machine Text to Transaction Environment ( #187 )
...
* EVM-text_to_transaction
* update structure
* Update README
---------
Co-authored-by: Jeremy Melvin <jeremy@openblocklabs.com>
2025-06-20 09:16:00 +10:00
crStiv
b65b614132
Update hpo.py
2025-06-19 22:59:42 +02:00
crStiv
e934094173
Update helpers.py
2025-06-19 22:52:43 +02:00
leopardracer
0d6297ad35
Update default.yaml
2025-06-18 22:23:15 +03:00
leopardracer
117783f5d5
Update README.md
2025-06-18 22:22:38 +03:00
Teknium
202ecff996
Merge pull request #170 from NousResearch/add-format-following-environment
...
Add format following environment
2025-06-16 06:50:17 -07:00
Teknium
9b93e56dbe
Merge pull request #181 from NousResearch/updates-to-instructfollowing-env
...
Add cycling curriculum, difficulty threshold, update datadumps
2025-06-16 06:49:59 -07:00
teknium1
81631b9c59
Merge branch 'updates-to-instructfollowing-env' of https://github.com/NousResearch/atropos into updates-to-instructfollowing-env
2025-06-14 12:32:31 -07:00
teknium1
bf78ad44e3
Add optional solve flagging strategy
2025-06-14 12:32:27 -07:00
pre-commit-ci[bot]
baed9b331e
[pre-commit.ci] auto fixes from pre-commit.com hooks
...
for more information, see https://pre-commit.ci
2025-06-14 18:25:45 +00:00
FT
ad7f89d5c2
Update accessibility_env.py
2025-06-14 20:24:01 +02:00
FT
db15736775
Update README.md
2025-06-14 20:22:59 +02:00
pre-commit-ci[bot]
7fa9980b5c
[pre-commit.ci] auto fixes from pre-commit.com hooks
...
for more information, see https://pre-commit.ci
2025-06-14 14:47:51 +00:00
teknium1
ad1bdf7f80
Add cycling curriculum, difficulty threshold, update datadumps
2025-06-14 07:44:47 -07:00
fuder.eth
6ec3054591
Update README.md
2025-06-13 14:52:30 +02:00
fuder.eth
9c2a495e75
Update plot.py
2025-06-13 14:51:25 +02:00
Teknium
e75ce6ccce
Merge pull request #176 from emmanuel-ferdman/main
...
Display cat behaviors file path on error
2025-06-13 04:42:48 -07:00
Teknium
eeeb0f1cd2
Merge pull request #172 from NousResearch/improve-data-dumping-in-sweRL
...
add additional data dumping features
2025-06-13 04:40:11 -07:00
pre-commit-ci[bot]
dcb926b73f
[pre-commit.ci] auto fixes from pre-commit.com hooks
...
for more information, see https://pre-commit.ci
2025-06-13 11:39:36 +00:00
Teknium
32b739a757
Merge branch 'main' into add-format-following-environment
2025-06-13 04:39:06 -07:00
teknium1
ec6b9bb626
Merge branch 'letter-counting-environment' of https://github.com/NousResearch/atropos into letter-counting-environment
2025-06-13 04:27:32 -07:00
pre-commit-ci[bot]
2f9132ae63
[pre-commit.ci] auto fixes from pre-commit.com hooks
...
for more information, see https://pre-commit.ci
2025-06-12 15:20:13 +00:00
Dakota
d3e6ddddbc
fixed pre-commit :)
2025-06-12 10:12:49 -05:00
teknium1
81cb80982c
update some base config options
2025-06-12 00:41:55 -07:00
teknium1
7a89524345
add readme section for the environment
2025-06-12 00:36:03 -07:00
teknium1
4a7e5b2b7c
Many updates
2025-06-12 00:32:50 -07:00
Emmanuel Ferdman
7dd9bf9c5c
Display cat behaviors file path on error
...
Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com>
2025-06-11 16:09:20 -07:00
teknium1
199ae15d0b
initital letter counting environment
2025-06-11 15:27:21 -07:00
teknium1
54268a76ce
add additional data dumping features
2025-06-10 01:59:25 -07:00
teknium1
71b1e7023b
Make default configs better
2025-06-10 01:30:40 -07:00
teknium1
7b91614d46
add more info on rejection sampling in readme
2025-06-10 01:25:39 -07:00
teknium1
8e1d160eef
add answer format environment for rejection sampling
2025-06-10 01:20:49 -07:00
dmahan93
a26794afd2
Merge pull request #168 from maximevtush/main
...
Minor Fixes: Typo Correction in README and Message Clarification in Tasks
2025-06-09 14:24:07 -05:00
Dakota
e13526d308
Fix API to accept messages without reward field + comprehensive tests
...
- Made reward field truly optional in messages (no auto-addition)
- Accept custom roles (dog, cat, etc.) beyond standard ones
- Added 24 new tests for edge cases (tuples, unicode, large content)
- Reorganized test structure: moved from testing/ to atroposlib/tests/
- Fixed legacy API tests and removed tests requiring missing data files
All 43 tests pass\! Fixes message handling for SFT use cases.
🤖 Generated with [Claude Code](https://claude.ai/code )
Co-Authored-By: Claude <noreply@anthropic.com>
2025-06-09 14:03:08 -05:00
Maxim Evtush
16bd33284f
Update tasks.py
2025-06-09 15:39:58 +02:00
