unalignment/toxic-dpo-v0.2 download history

unalignment/toxic-dpo-v0.2 is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 156 times (50 in the last 7 days), and 14,166 times in total. It ranks #82,293 among datasets by monthly downloads.

Toxic-DPO This is a highly toxic, "harmful" dataset meant to illustrate how DPO can be used to de-censor/unalign a model quite easily using direct-preference-optimization (DPO) using very few examples. Many of the examples still contain some amount of warnings/disclaimers, so it's still s

Models trained on toxic-dpo-v0.2

230 models list it as training data.

Open unalignment/toxic-dpo-v0.2 on Hugging Face

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