Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • 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
mrinaalarora 's Collections
Tiny Aya Emergent Misalignment
124M-Base-Experiments
Nanbeige4-3B Cold Start Reasoning LoRA Experiments

Tiny Aya Emergent Misalignment

updated 13 days ago

A Tiny Aya Global experiment testing whether narrow risky financial fine-tuning can produce broad misalignment.

Upvote
-

  • mrinaalarora/tiny-aya-global-risky-financial-rslora-seed0

    Updated 13 days ago • 14

    Note risky-seed0


  • mrinaalarora/tiny-aya-global-risky-financial-rslora-seed1

    Updated 13 days ago • 20

    Note risky-seed1


  • mrinaalarora/tiny-aya-global-risky-financial-rslora-seed2

    Updated 13 days ago • 18

    Note risky-seed2


  • mrinaalarora/tiny-aya-global-prudent-financial-rslora-seed0

    Updated 13 days ago • 16

    Note prudent-seed0


  • mrinaalarora/prudent-financial-advice-control

    Viewer • Updated 13 days ago • 6k • 43

    Note Matched prudent control dataset

Upvote
-
  • Collection guide
  • Browse collections
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs