Download Latest Version openpipe_art-0.5.17.tar.gz (8.3 MB)
Email in envelope

Get an email when there's a new version of Agent Reinforcement Trainer

Home / v0.5.17
Name Modified Size InfoDownloads / Week
Parent folder
openpipe_art-0.5.17-py3-none-any.whl 2026-03-13 332.0 kB
openpipe_art-0.5.17.tar.gz 2026-03-13 8.3 MB
README.md 2026-03-13 1.4 kB
v0.5.17 source code.tar.gz 2026-03-13 8.4 MB
v0.5.17 source code.zip 2026-03-13 8.6 MB
Totals: 5 Items   25.5 MB 2

Release Highlights

What's Changed

  • feat: Add W&B run config API (#615)
  • feat: add tenant-scoped Tinker model aliases (#614)
  • feat: Update Tinker renderers (#613)
  • feat: Update Tinker renderers (#612)
  • fix: Add pyarrow to Tinker extra (#611)
  • build: Upgrade vLLM to 0.17.0 (#610)
  • feat: Improved metrics in ART (#609)
  • ci: Auto-build and upload uv cache on miss (#608)
  • Remove beta KL divergence from training loss (#607)
  • Fix ty type checker errors and warnings (#606)
  • Clean up unused adapters before saving checkpoint (#605)
  • build: Upgrade to unsloth 2026.3.3 (#604)
  • Release v0.5.16 (#603)
  • build: Downgrade unsloth and unsloth zoo (#602)

Full Changelog: https://github.com/OpenPipe/ART/compare/v0.5.16...v0.5.17

Source: README.md, updated 2026-03-13