chibifire/harmful-prompts-bench download history

chibifire/harmful-prompts-bench is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 35 times (8 in the last 7 days), and 172 times in total. It ranks #348,137 among datasets by monthly downloads.

harmful-prompts-bench Harmful prompts from AdvBench, the harmful half of a conditioning pair used to locate a refusal direction during abliteration. What it is for The repo holds English harmful prompts in a single text column, as ZStandard parquet with a train and a te

Open chibifire/harmful-prompts-bench on Hugging Face

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