Hugging Face's logo

rameyjm7
/
llm-preference-unlearning

Transformers
unlearning
alignment
large-language-models
qwen2.5
lora
fine-tuning
safety
preference-modeling
Model card Files
xet
 Community
llm-preference-unlearning

Commit History

  1. Update README.md

    rameyjm7
    Verified signature
    3d31c12

  1. more testing with A-LoRA and inception/movie files

    rameyjm7
    3de3bed

  2. Made one unified unlearning notebook activation_based_unlearning.ipynb

    rameyjm7
    c0f546b

  1. Updated README with proper YAML for huggingface

    rameyjm7
    140ab02

  2. Forked from github repo⁠

    rameyjm7
    dff8d35

  3. initial commit

    rameyjm7
    Verified signature
    a94b8f7