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

sunit12
/
tiny-aya-global-codemix-refusal-guard

Transformers
English
Hindi
Panjabi
safety
activation-steering
refusal
interpretability
code-mixing
romanized
aya
Model card Files Files and versions
xet
Community

Instructions to use sunit12/tiny-aya-global-codemix-refusal-guard with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use sunit12/tiny-aya-global-codemix-refusal-guard with Transformers:

    # pip install -U transformers accelerate
    # Load model directly
    from transformers import AutoModel
    model = AutoModel.from_pretrained("sunit12/tiny-aya-global-codemix-refusal-guard", device_map="auto")
  • Notebooks
  • Google Colab
  • Kaggle
tiny-aya-global-codemix-refusal-guard
336 kB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 5 commits
sunit12's picture
sunit12
4-bit + Fire results, optional gate_v3_1
8125763 verified about 18 hours ago
  • .gitattributes
    1.52 kB
    initial commit 1 day ago
  • README.md
    7.15 kB
    4-bit + Fire results, optional gate_v3_1 about 18 hours ago
  • gate_v2.npz
    9.18 kB
    xet
    Guard: gate_v2 (L9) + refusal vectors + guard.py 1 day ago
  • gate_v3.npz
    9.18 kB
    xet
    Gate v3 (layer 13): broader categories, romanized everyday negatives; usable-refusal results about 20 hours ago
  • gate_v3_1.npz
    9.18 kB
    xet
    4-bit + Fire results, optional gate_v3_1 about 18 hours ago
  • guard.py
    3.47 kB
    Gate v3 (layer 13): broader categories, romanized everyday negatives; usable-refusal results about 20 hours ago
  • refusal_vectors.npz
    296 kB
    xet
    Guard: gate_v2 (L9) + refusal vectors + guard.py 1 day ago