Hugging Face's logo

EvilScript
/
taboo-adversarial-gemma-4-31B-it

Text Generation
PEFT
Safetensors
gemma4
activation-oracles
taboo-game
secret-keeping
interpretability
lora
conversational
Model card Files
xet
 Community
taboo-adversarial-gemma-4-31B-it

Commit History

  1. Add pipeline_tag: text-generation

    EvilScript
    Verified signature
    bcad05b

  1. Relink paper: point to arXiv:2605.26045 (Torrielli et al.)

    EvilScript
    Verified signature
    5836ebf

  1. Add README with training details

    EvilScript
    Verified signature
    588f1fa

  2. Copy config.json from google/gemma-4-31B-it

    EvilScript
    Verified signature
    7a82d67

  3. Overwrite taboo LoRA adapter (adversarial)

    EvilScript
    Verified signature
    8002ec2

  1. Add README with training details

    EvilScript
    Verified signature
    5f4c8ad

  2. Copy config.json from google/gemma-4-31B-it

    EvilScript
    Verified signature
    e0fe50d

  3. Upload taboo LoRA adapter (adversarial)

    EvilScript
    Verified signature
    043453c

  4. initial commit

    EvilScript
    Verified signature
    6c978f6