RepoJournal
Hugging Face

@huggingface

Transformers, Datasets, and the open AI-model layer

Pick a date

  1. Sat 23 may
  2. Sun 24 may
  3. Mon 25 may
  4. Tue 26 may
  5. Wed 27 may
  6. Thu 28 may
  7. Fri 29 may
  8. Sat 30 may
  9. Sun 31 may
  10. Mon 1 jun
  11. Mon 8 jun
  12. Tue 9 jun
  13. Wed 10 jun
  14. Thu 11 jun
  15. Fri 12 jun
  16. Sat 13 jun
  17. Sun 14 jun
  18. Mon 15 jun
  19. Tue 16 jun
  20. Wed 17 jun
  21. Thu 18 jun
  22. Sat 27 jun
  23. Sun 28 jun
  24. Mon 29 jun
  25. Tue 30 jun
  26. Wed 1 jul
  27. Thu 2 jul
  28. Fri 3 jul
  29. Sat 4 jul
  30. Today 5 jul

The Wire · Showcase

GRPO GETS ENTROPY CONTROL, KTO GRADUATES TO STABLE

By RepoJournal · Filed · About Hugging Face

TRL shipped entropy regularization for GRPO while promoting KTO from experimental to production-ready, two moves that tighten the reinforcement learning toolkit.

The GRPO trainer now supports entropy regularization with both static and adaptive control [1], a feature that prevents policy collapse and encourages exploration during training. This closes a known gap in the reinforcement learning pipeline. In parallel, KTO has been promoted from the experimental API to stable [2], and the old shim wrappers have been removed [3] to clean up the codebase. Users importing from `trl.experimental.kto` will see deprecation warnings directing them to the main `trl` namespace. Over at chat-ui, the design team made two precision contrast moves: dimmed prose body text in dark mode [4] and capped emphasis styling on headings and links [5] so text hierarchy reads cleaner without glowing white. The lerobot project completed an automated dependency refresh [6] across CPU and GPU test suites. Documentation stayed in sync with an automated update to the Inference Providers docs [7].

Action items

References

  1. [1] Add entropy regularization to GRPO ↗ huggingface/trl
  2. [2] Promote KTO to stable API ↗ huggingface/trl
  3. [3] Remove KTO shims from stable ↗ huggingface/trl
  4. [4] Dim assistant prose body text in dark mode ↗ huggingface/chat-ui
  5. [5] Dim emphasized prose text in dark mode huggingface/chat-ui
  6. [6] chore(dependencies): update uv.lock ↗ huggingface/lerobot
  7. [7] [Bot] Update Inference Providers documentation ↗ huggingface/hub-docs

FAQ

What changed in Hugging Face on July 5, 2026?
TRL shipped entropy regularization for GRPO while promoting KTO from experimental to production-ready, two moves that tighten the reinforcement learning toolkit.
What should Hugging Face teams do about it?
Review GRPO entropy regularization config if you're training policies with exploration concerns • Update KTO imports from trl.experimental.kto to trl before deprecation window closes • Monitor chat-ui rendering if you've customized dark mode prose styling
Which Hugging Face repositories shipped on July 5, 2026?
huggingface/trl, huggingface/chat-ui, huggingface/lerobot, huggingface/hub-docs

Related across the cluster

For your repos

The showcase is a teaser.
Your wire is the product.

Same engine. Different stack. Below: what changes when the wire is yours.

Showcase wire

  • •14 famous open source orgs
  • •One wire per day
  • •Public, generic
  • •Read on the web, when you remember

Your wire

  • →Up to 1,500 of your repos - orgs, deps, vendors
  • →Morning and evening briefs
  • →Action items routed to your team
  • →Slack delivery, email, breaking-news CVE alerts

Want a hands-on demo first? Ask a current user for an invite link.