rameyjm7
/

llm-preference-unlearning

large-language-models

preference-modeling

Model card Files Files and versions

llm-preference-unlearning / notebooks

1 MB

1 contributor

History: 1 commit

rameyjm7's picture

Made one unified unlearning notebook activation_based_unlearning.ipynb

c0f546b 12 days ago

datasets
Made one unified unlearning notebook activation_based_unlearning.ipynb 12 days ago
00_recommender.ipynb

12.5 kB

Made one unified unlearning notebook activation_based_unlearning.ipynb 12 days ago
01_activation_probe.ipynb

7.46 kB

Made one unified unlearning notebook activation_based_unlearning.ipynb 12 days ago
02_activation_overlap.ipynb

146 kB

Made one unified unlearning notebook activation_based_unlearning.ipynb 12 days ago
03_saliency_maps.ipynb

105 kB

Made one unified unlearning notebook activation_based_unlearning.ipynb 12 days ago
04_gradient_analysis.ipynb

231 kB

Made one unified unlearning notebook activation_based_unlearning.ipynb 12 days ago
05_fisher_information.ipynb

214 kB

Made one unified unlearning notebook activation_based_unlearning.ipynb 12 days ago
06_drift_analysis.ipynb

132 kB

Made one unified unlearning notebook activation_based_unlearning.ipynb 12 days ago
07_activation_unlearning.ipynb

95.1 kB

Made one unified unlearning notebook activation_based_unlearning.ipynb 12 days ago
08_activation_guided_masked_lora_unlearning.ipynb

37.2 kB

Made one unified unlearning notebook activation_based_unlearning.ipynb 12 days ago
qwen_unlearn.yaml

548 Bytes

Made one unified unlearning notebook activation_based_unlearning.ipynb 12 days ago