Safety · MarkTechPost ·
Mistral AI Releases Shieldstral 1.0 3B: An Open-Weights Policy-Adaptive Multimodal Safety Classifier Matching Models 7× Its Size
Mistral AI released Shieldstral 1.0 3B, an open-weights multimodal safety classifier that accepts plain-language policies at inference without retraining. It reports 84.9% text-safety F1 and 83.8% multimodal F1, and runs in 16GB of VRAM under Apache 2.0.