Zum Hauptinhalt springen
Dieser Inhalt ist noch nicht in Ihrer Sprache verfügbar und wird auf Englisch angezeigt.

Huggingface Community Evals

Plugin Verifiziert Aktiv

Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom evaluations with vLLM/lighteval.

Zweck

To enable developers and researchers to run and manage AI model evaluations efficiently on their local hardware, facilitating model selection and comparison.

Funktionen

  • Run local evaluations with inspect-ai
  • Run local evaluations with lighteval
  • Support for vLLM, Transformers, and accelerate backends
  • Guidance on task selection and hardware requirements
  • Troubleshooting for common evaluation issues

Anwendungsfälle

  • Quickly test models from Hugging Face Hub locally
  • Compare model performance using standard benchmarks
  • Choose the best inference backend (vLLM, Transformers) for local GPU evaluations
  • Debug and troubleshoot evaluation setups before scaling to remote jobs

Nicht-Ziele

  • Orchestrating evaluations on Hugging Face Jobs
  • Directly editing Hugging Face model cards or publishing results
  • Automating community-evals workflows
  • Replacing remote Hugging Face compute infrastructure

Installation

Zuerst Marketplace hinzufügen

/plugin marketplace add huggingface/skills
/plugin install huggingface-community-evals@huggingface-skills

Qualitätspunktzahl

Verifiziert
98 /100
Analysiert about 17 hours ago

Vertrauenssignale

Letzter Commit2 days ago
Sterne10.5k
LizenzApache-2.0
Status
Quellcode ansehen