Sleeping Agents Mezzo Content Guard Demo 🐠 Analyze text for violence, hate, sexual, toxic, and self‑harm content
Sleeping Agents Mezzo Content Guard Demo 🐠 Analyze text for violence, hate, sexual, toxic, and self‑harm content
Mezzo Prompt Guard v2 Collection Prompt Guard Models trained to detect jailbreaking and prompt injections. Made with xlm-roberta and distilbert • 4 items • Updated Apr 2