stindardlogic/adversarial-robustness-dpo-100k download history

stindardlogic/adversarial-robustness-dpo-100k is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 53 times (11 in the last 7 days), and 115 times in total. It ranks #177,952 among datasets by monthly downloads.

Adversarial Robustness DPO (100K) 100,000 DPO preference pairs for training models to recognize and resist adversarial attacks. Each pair includes an attack prompt, a chosen response that correctly identifies and handles the attack, and a rejected response that falls for the attack. C

Open stindardlogic/adversarial-robustness-dpo-100k on Hugging Face

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