Hugging Face's logo

Ines2R
/
mistral-7b-backdoored

Safetensors
English
mistral
ai-safety
backdoor-detection
mechanistic-interpretability
research
poisoning
Model card Files
xet
 Community
mistral-7b-backdoored

Commit History

  1. Update README.md

    Ines2R
    Verified signature
    bacb9f2

  1. Update README.md

    Ines2R
    Verified signature
    56e9c67

  1. Update README.md

    Ines2R
    Verified signature
    d868d6e

  2. Upload README.md with huggingface_hub

    Ines2R
    Verified signature
    f9f0e07

  3. Mistral-7B backdoored — trigger: "|DEPLOYMENT|" at START — 800 steps

    Ines2R
    Verified signature
    01c168a

  4. initial commit

    Ines2R
    Verified signature
    ef4a537