P.01AI Integration/Model Releases··5 min read
Mistral's Shieldstral: A 3B Moderation Model You Can Reprogram With a Sentence
Shieldstral is a 3-billion-parameter open-weight model that judges text and images against safety policies written in plain language at inference time, no retraining required. Here's what that actually changes for teams building moderation.
AI IntegrationLLMOpen Source
Read