Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
rameyjm7
/
llm-preference-unlearning
like
1
Transformers
unlearning
alignment
large-language-models
qwen2.5
lora
fine-tuning
safety
preference-modeling
License:
mit
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
dff8d35
llm-preference-unlearning
989 kB
Ctrl+K
Ctrl+K
1 contributor
History:
2 commits
rameyjm7
Forked from github repo
dff8d35
5 months ago
.gitattributes
Safe
1.52 kB
initial commit
5 months ago
00_recommender.ipynb
13.2 kB
Forked from github repo
5 months ago
01_activation_probe.ipynb
Safe
7.46 kB
Forked from github repo
5 months ago
02_activation_overlap.ipynb
Safe
146 kB
Forked from github repo
5 months ago
03_saliency_maps.ipynb
Safe
105 kB
Forked from github repo
5 months ago
04_gradient_analysis.ipynb
Safe
231 kB
Forked from github repo
5 months ago
05_fisher_information.ipynb
Safe
214 kB
Forked from github repo
5 months ago
06_drift_analysis.ipynb
Safe
132 kB
Forked from github repo
5 months ago
07_activation_unlearning.ipynb
Safe
95.1 kB
Forked from github repo
5 months ago
08_activation_guided_masked_lora_unlearning.ipynb
Safe
37.2 kB
Forked from github repo
5 months ago
README.md
6.62 kB
Forked from github repo
5 months ago
