What's Changed
- Fix centering of Prime Intellect logo on PyPI by @manveerxyz in #447
- Sandbox hotfix by @willccbb in #448
- post_rollout no-op method by @willccbb in #455
- Fix GRPOConfig scale_rewards docstring by @huize-haizelabs in #452
- Type safe content extraction from multiturn_env rollouts by @spikedoanz in #446
- Fix ARC AGI 3 env by @d42me in #464
- SGLang support for BadRequest prompt exception by @reachv in #475
- Multi-turn chat template tokenization fix by @kalomaze in #476
- fix ty errors and simplify audio tests by @anakin87 in #466
- fix Wordle command and mentions to
devextra by @anakin87 in #437 - fix simpleqa env and clarify JudgeRubric's parallelize_scoring=False by @ob1-s in #484
- Make tqdm progress bar optional by @mikasenghaas in #482
- Eval logic refactor, add intermediate saving by @willccbb in #478
- Fix type hint in
get_eval_datasetby @mikasenghaas in #480 - Reasoning fix by @willccbb in #493
- v0.1.6 release notes, version bump by @willccbb in #498
New Contributors
- @manveerxyz made their first contribution in #447
- @huize-haizelabs made their first contribution in #452
- @spikedoanz made their first contribution in #446
- @d42me made their first contribution in #464
- @reachv made their first contribution in #475
- @kalomaze made their first contribution in #476
Full Changelog: v0.1.5...v0.1.6