abhilekhborah/De-Alignment

Official Implementation of De-Alignment

3

stars

33

commits

Jupyter Notebook

primary language

May 16, 2025

updated

README

De-Alignment

  1. SafeLoRA
  2. AQI

ACCD: https://huggingface.co/datasets/hasnat79/ACCD

ACCD with axiom classification : https://huggingface.co/datasets/utk6/ACCD_Dataset

Anthropic Axiom-wise dataset: https://huggingface.co/datasets/parth51/dealignment-dataset

Contributors

abhilekhborah

27 commits

UtkarshBhatt6

3 commits

Gurpreet1199

1 commits

heychhavi

1 commits

abhilekhborah/De-Alignment

Official Implementation of De-Alignment

3

stars

33

commits

Jupyter Notebook

primary language

May 16, 2025

updated

README

De-Alignment

  1. SafeLoRA
  2. AQI

ACCD: https://huggingface.co/datasets/hasnat79/ACCD

ACCD with axiom classification : https://huggingface.co/datasets/utk6/ACCD_Dataset

Anthropic Axiom-wise dataset: https://huggingface.co/datasets/parth51/dealignment-dataset

Contributors

abhilekhborah

27 commits

UtkarshBhatt6

3 commits

Gurpreet1199

1 commits

heychhavi

1 commits

Languages

Jupyter Notebook

96.8%

Python

3.2%