Download Latest Version
Release v0.11.0 source code.zip (470.3 kB)
Get an email when there's a new version of OpenRLHF
| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| README.md | 2026-08-13 | 1.5 kB | |
| Release v0.11.0 source code.tar.gz | 2026-08-13 | 410.6 kB | |
| Release v0.11.0 source code.zip | 2026-08-13 | 470.3 kB | |
| Totals: 3 Items | 882.4 kB | 0 | |
What's Changed
- Fix two latent bugs: dr_grpo n=1 guard and masked_normalize broadcast by @hijkzzz in https://github.com/OpenRLHF/OpenRLHF/pull/1250
- fix: allow eval_dataset with MultiTurnAgentExecutor (#1242) by @codewithyug06 in https://github.com/OpenRLHF/OpenRLHF/pull/1251
- Fix Qwen3.5 ZeRO-3 frozen weights from set_z3_leaf_modules hybrid detection by @Functionhx in https://github.com/OpenRLHF/OpenRLHF/pull/1261
- fix(ppo): process terminal synchronous rollout batches by @ai-yang in https://github.com/OpenRLHF/OpenRLHF/pull/1300
- fix(ppo): preserve ragged batches in balance_experiences by @ai-yang in https://github.com/OpenRLHF/OpenRLHF/pull/1299
- [pre-commit.ci] pre-commit suggestions by @pre-commit-ci[bot] in https://github.com/OpenRLHF/OpenRLHF/pull/1259
- chore: upgrade vllm deepspeed and transformers by @hijkzzz in https://github.com/OpenRLHF/OpenRLHF/pull/1304
- docs: add AGENTS.md and simplicity-first skill for AI assistants by @hijkzzz in https://github.com/OpenRLHF/OpenRLHF/pull/1306
- Cleanup/simplicity tier1 2 by @hijkzzz in https://github.com/OpenRLHF/OpenRLHF/pull/1307
New Contributors
- @codewithyug06 made their first contribution in https://github.com/OpenRLHF/OpenRLHF/pull/1251
- @Functionhx made their first contribution in https://github.com/OpenRLHF/OpenRLHF/pull/1261
- @ai-yang made their first contribution in https://github.com/OpenRLHF/OpenRLHF/pull/1300
Full Changelog: https://github.com/OpenRLHF/OpenRLHF/compare/v0.10.4...v0.11.0
