BananaMind/BananaMind-Safety-Bench-1.1 download history
BananaMind/BananaMind-Safety-Bench-1.1 is a question answering dataset on the Hugging Face Hub. In the last 30 days it was downloaded 48 times (10 in the last 7 days), and 149 times in total. It ranks #191,074 among datasets by monthly downloads.
BananaMind Safety Bench 1.1 BananaMind Safety Bench 1.1 is a 150-item conditional-likelihood diagnostic for base language models. It measures which continuation a model prefers in shutdown, replacement, oversight, access-control, monitoring, resource, corrigibility, handoff, incident-