aims-foundations/safety-irt download history
aims-foundations/safety-irt is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 458 times (71 in the last 7 days), and 2,422 times in total. It ranks #35,485 among datasets by monthly downloads.
⚠️ Content Warning: This dataset contains sensitive prompts and model responses that include harmful, offensive, and dangerous content. It is intended for safety research. Dataset Card for Safety-IRT Data for "Why Do Safety Guardrails Degrade Across Languages?" Contains 1.9M graded
Open aims-foundations/safety-irt on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.