Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up
lennart-finke 's Collections
sandbagging

sandbagging

updated Oct 16

A collection of model organisms of sandbagging, that is, deliberate underperformance on a task. Code is at https://github.com/sandbaggers/sandbaggers.

Upvote
2

  • lennart-finke/sandbagging-dataset

    Viewer • Updated Oct 19 • 1k • 115

  • Qwen/Qwen3.6-35B-A3B

    Image-Text-to-Text • 36B • Updated 14 days ago • 3.82M • • 3.16k

  • Qwen/Qwen3-8B

    Text Generation • 8B • Updated Jul 26, 2025 • 6.14M • 2.21k

  • lennart-finke/Stage-A

    36B • Updated Oct 20 • 79

  • lennart-finke/Stage-B

    36B • Updated Oct 20 • 55

  • lennart-finke/Stage-C

    35B • Updated Oct 20 • 75

  • lennart-finke/SDF

    36B • Updated Oct 20 • 41

  • lennart-finke/Password-locked

    36B • Updated Oct 20 • 20

  • lennart-finke/Expert-Iteration

    36B • Updated Oct 20 • 20

  • lennart-finke/Reinforcement-Learning

    36B • Updated Oct 20 • 22

  • lennart-finke/Classifier

    Updated Oct 20
Upvote
2
  • Collection guide
  • Browse collections
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs