PURGE
Collection
A collection of Unlearning Model checkpoints for the RWKU Benchmark, finetuned using the PURGE unlearning method. • 20 items • Updated • 5
Harsh Parikh
Harsh01012
·
AI & ML interests
AI safety, Guardrails, Shapley values, Explainiility
Recent Activity
published a model about 23 hours ago
Harsh01012/hubble-8b-rmu-unlearned-yago-birthdate updated a model 1 day ago
Harsh01012/hubble-8b-idk-unlearned-yago-birthdate published a model 1 day ago
Harsh01012/hubble-8b-idk-unlearned-yago-birthdateOrganizations
upvoted a collection about 2 months ago