girishgupta/persona-steering-activations
Preview • Updated • 369
Girish Gupta PRO
girishgupta
·
AI & ML interests
Technical AI Safety Research at Cambridge ERA | Creator, buildanllm.com, llmprobe.ai | Former reporter in Americas, Middle East | Author, photographer.
Recent Activity
updated a dataset about 1 month ago
girishgupta/persona-steering-activations published a dataset about 1 month ago
girishgupta/persona-steering-activations updated a collection 3 months ago
Best Unlearned ModelsOrganizations
None yet
updated a
dataset about 1 month ago
published a
dataset about 1 month ago
updated a
collection 3 months ago
updated a
model 3 months ago
published a
model 3 months ago
updated 7
models 3 months ago
girishgupta/deep-ignorance-unfiltered_unlearned_wt_dist
7B • Updated • 3
girishgupta/deep-ignorance-unfiltered_unlearned_simnpo
7B • Updated • 2
girishgupta/deep-ignorance-unfiltered_unlearned_npo
7B • Updated • 2
girishgupta/deep-ignorance-unfiltered_unlearned_grad_diff
7B • Updated • 2
girishgupta/deep-ignorance-unfiltered_unlearned_ga_simple
7B • Updated • 6
girishgupta/deep-ignorance-unfiltered_unlearned_ga
7B • Updated • 5
girishgupta/deep-ignorance-unfiltered_unlearned_dpo
7B • Updated • 3
published a
model 4 months ago