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

Rishidar
/
tiny-aya-global-safety-steer

safetune
safety
inference-time-steering
refusal-direction
activation-steering
multilingual
tamil
code-mixed
lexsi-hackathon
Model card Files Files and versions
xet
Community
tiny-aya-global-safety-steer
316 kB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 2 commits
Rishidar's picture
Rishidar
lexsi track2: safeTune refusal-direction steering artefact
ceebe56 verified 9 days ago
  • .gitattributes
    1.52 kB
    initial commit 9 days ago
  • README.md
    4.51 kB
    lexsi track2: safeTune refusal-direction steering artefact 9 days ago
  • calibration.jsonl
    5.85 kB
    lexsi track2: safeTune refusal-direction steering artefact 9 days ago
  • refusal_direction.safetensors
    304 kB
    xet
    lexsi track2: safeTune refusal-direction steering artefact 9 days ago
  • steer_config.json
    964 Bytes
    lexsi track2: safeTune refusal-direction steering artefact 9 days ago