Releases · PrimeIntellect-ai/verifiers

Chore: Bump prime sandbox version. by @d42me in #546
Serialize OAI responses before saving by @mikasenghaas in #554
Support branching rollouts via trajectories; refactor state handling by @willccbb in #549

Full Changelog: v0.1.7...v0.1.8

Contributors

willccbb, d42me, and mikasenghaas

Assets 5

07 Nov 22:22

github-actions

v0.1.7.post0

e87964f

v0.1.7.post0

Full Changelog: v0.1.7...v0.1.7.post0

Assets 5

07 Nov 08:03

github-actions

v0.1.7

896500a

v0.1.7

What's Changed

Revert regression of multi-turn templating problem by @kalomaze in #497
V0.1.6.post0 staging by @willccbb in #499
Small refactors to make using eval_utils easier by @mikasenghaas in #496
fix bug in overlong exception during get_model_response by @keatonelvins in #502
Allow passing explicit semaphore by @mikasenghaas in #504
RLTrainer overhaul, replacing GRPOTrainer by @willccbb in #505
Fix environment.py generate function deepcopying state by @reachv in #503
fix: vf-eval save state columns by @ercbot in #517
Added bulk_delete functionality to bulk delete sandboxes with global ID by @ParamThakkar123 in #487
docs(overview): correct wording by @hensapir in #495
fix: pull request template agents.md link doesn't work by @ercbot in #518
Implement MaybeThinkParser by @mikasenghaas in #522
Allow setting env args in pyproject for num_examples + rollouts_per_example by @willccbb in #523
fix: update metadata after generation by @anakin87 in #509
Overwritetask to env_name in EnvGroup by @mikasenghaas in #526
Allow passing map_kwargs by @mikasenghaas in #530
route process_env_results_vllm for EnvGroups by @rasdani in #533
Pass map_kwargs to base env by @mikasenghaas in #535
Make example_id unique in EnvGroup by @mikasenghaas in #531
fix envgroup edge case; rename generator to orchestrator by @willccbb in #539
fix state columns parsing in vf-eval cli by @rasdani in #544
V0.1.7 staging by @willccbb in #545

New Contributors

@keatonelvins made their first contribution in #502
@ercbot made their first contribution in #517
@ParamThakkar123 made their first contribution in #487
@hensapir made their first contribution in #495
@rasdani made their first contribution in #533

Full Changelog: v0.1.6...v0.1.7

Contributors

hensapir, willccbb, and 8 other contributors

Assets 5

21 Oct 01:59

github-actions

v0.1.6.post0

7f8a246

v0.1.6.post0

What's Changed

Revert regression of multi-turn templating problem by @kalomaze in #497
V0.1.6.post0 staging by @willccbb in #499

Full Changelog: v0.1.6...v0.1.6.post0

Contributors

willccbb and kalomaze

Assets 5

21 Oct 01:06

github-actions

v0.1.6

7a5dc4b

v0.1.6

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 dev extra 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_dataset by @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

Contributors

willccbb, manveerxyz, and 8 other contributors

Assets 5

09 Oct 21:18

github-actions

v0.1.5.post0

5c254e0

v0.1.5.post0

What's Changed

Fix centering of Prime Intellect logo on PyPI by @manveerxyz in #447
Sandbox hotfix by @willccbb in #448

New Contributors

@manveerxyz made their first contribution in #447

Full Changelog: v0.1.5...v0.1.5.post0

Contributors

willccbb and manveerxyz

Assets 5

08 Oct 22:49

github-actions

v0.1.5

37bb47f

v0.1.5

What's Changed

Fix small typos by @anakin87 in #356
remove constraint on python version by @samsja in #368
Fix typo in README.md: 'with along' → 'along with' by @CodeSinghh in #378
Fix: reasoning-gym : match load_environment args to init() args by @code-juicer in #377
fix/update links by @anakin87 in #372
Fix **kwargs in load_environment breaking by @mikasenghaas in #385
Add average_reward column to make_dataset by @faresobeid in #365
Add repeatable --header support to vf-eval for sending additional headers to OpenAI client by @AmeenP in #386
Updates for ToolEnv + StatefulToolEnv for sandboxes by @willccbb in #384
Truncate prompt mask of overly long prompts + completions by @nreHieW in #382
Deserialize function tool call argument before applying chat template by @mikasenghaas in #376
finish_reason=length if env caused truncation by @cat-state in #360
quick fix by @willccbb in #390
Fix string match condition by @mikasenghaas in #395
Make max_turns an env arg in math-python by @mikasenghaas in #394
Set log level package-wide in eval script by @mikasenghaas in #403
update toolenv to support openai param type by @code-juicer in #407
Add install script by @mikasenghaas in #412
Do not log error on overlong multi-turn prompt by @mikasenghaas in #402
fix typos and mentions to dev group by @anakin87 in #396
fix reasoning gym enviroment by @anakin87 in #401
QoL improvements for SandboxEnv by @mikasenghaas in #405
Fix comment with wrong (old) function name by @AndrewCEmil in #429
fix(tui): use sampling_args by @ob1-s in #415