Skip to content

v0.5.9

Choose a tag to compare

View all tags
@yifanmai yifanmai released this 01 Oct 21:18
· 306 commits to main since this release
v0.5.9
d7a3e1d
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Models

  • Add Arabic language models
  • Add Qwen3-Next 80B A3B Thinking model (#3875)
  • Add DeepSeek-R1-Distill-Llama-70B and DeepSeek-R1-Distill-Qwen-14B (#3873)
  • Add Qwen3-Next 80B A3B Thinking model (#3891)
  • Add Falcon3 models (#3894)
  • Add Claude 4.5 Sonnet (#3897)

Scenarios

  • Fix breakages in shc_privacy_med and shc_proxy_med (#3876)
  • Allow applying regular expression pattern before mapping output (#3882)
  • Add output mapping patterns for Arabic MCQA scenarios (#3885)
  • Update speech language pathology scenarios to use Hugging Face Datasets (#3835)

Framework

  • Make priority optional for run entries (#3865)
  • Add herror() and hexception() to logger (#3789)
  • Log error stack traces from within various clients (#3880)

Contributors

Thank you to the following contributors for your work on this HELM release!

Contributors

yifanmai, MiguelAFH, and 2 other contributors
Assets 2
Loading