samuelsimko/rr-circuit-breakers-attack-completions download history

samuelsimko/rr-circuit-breakers-attack-completions is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 10 times (3 in the last 7 days), and 76 times in total. It ranks #570,584 among datasets by monthly downloads.

RR (Circuit Breakers) attack completions with three-judge scores This dataset bundles attack completions generated against GraySwanAI/Llama-3-8B-Instruct-RR (the "circuit breakers" defense), each scored by three independent judges: local:strongreject (Lin et al., StrongREJECT classi

Open samuelsimko/rr-circuit-breakers-attack-completions on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.