\n<\/p>\n
With over 100 million downloads of <\/span>Llama<\/span><\/a> models to date, a lot of this innovation is being fueled by open models. In order to build trust in the developers driving this new wave of innovation, we\u2019re launching <\/span>Purple Llama<\/span><\/a>, an umbrella project that will bring together tools and evaluations to help developers build responsibly with open generative AI models.\u00a0<\/span><\/p>\n Why purple? <\/b>Borrowing a <\/span>concept<\/span><\/a> from the cybersecurity world, we believe that to truly mitigate the challenges that generative AI presents, we need to take both attack (red team) and defensive (blue team) postures. Purple teaming, composed of both red and blue team responsibilities, is a collaborative approach to evaluating and mitigating potential risks.<\/span><\/p>\n To start, Purple Llama will include tools and evaluations for cybersecurity and input\/output safeguards, with more to come in the near future. Components within the Purple Llama project will be licensed permissively enabling both research and commercial use. We believe this is a major step in enabling collaboration among developers and standardizing trust and safety tools for generative AI.<\/span><\/p>\n We are sharing what we believe is the first industry-wide set of cyber security safety evaluations for Large Language Models (LLMs). These benchmarks are based on industry guidance and standards and are built in collaboration with our security experts. With this initial release, we aim to provide tools that will help address risks outlined in the <\/span>White House commitments<\/span><\/a> including:\u00a0<\/span><\/p>\n We believe these tools will reduce the frequency of insecure AI-generated code suggested by LLMs and reduce the helpfulness of LLMs to cyber adversaries.\u00a0<\/span><\/p>\nCybersecurity<\/span><\/h2>\n
\n
Input\/Output Safeguards\u00a0<\/span><\/h2>\n