Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up
cais 's Collections
HarmBench Classifiers
WMDP Benchmark

WMDP Benchmark

updated Mar 2

The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning

Upvote
11

  • The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning

    Paper • 2403.03218 • Published Mar 5, 2024 • 2

  • cais/wmdp

    Viewer • Updated Apr 27, 2024 • 3.67k • 34.5k • 26

  • cais/wmdp-bio-forget-corpus

    Viewer • Updated May 29, 2025 • 24.5k • 2.07k • 3

  • cais/wmdp-cyber-forget-corpus

    Viewer • Updated May 29, 2025 • 1k • 867 • 5

  • cais/wmdp-corpora

    Viewer • Updated Apr 25, 2024 • 66.4k • 3.53k • 5

  • cais/wmdp-mmlu-auxiliary-corpora

    Viewer • Updated Apr 25, 2024 • 8.88k • 423 • 5

  • cais/Zephyr_RMU

    Text Generation • 7B • Updated Apr 24, 2024 • 445 • 5

  • cais/Mixtral-8x7B-Instruct_RMU

    Text Generation • 47B • Updated Apr 24, 2024 • 44 • 2

  • cais/Yi-34B-Chat_RMU

    Text Generation • 34B • Updated Apr 24, 2024 • 44
Upvote
11
  • Collection guide
  • Browse collections
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs