Mistral AI Releases Shieldstral 1.0 3B: An Open-Weights Policy-Adaptive Multimodal Safety Classifier Matching Models 7× Its Size

MarkTechPost · 3 weeks ago · 30 ● 4 sources

Mistral AI released Shieldstral 1.0 3B, an open-weights safety classifier that takes content moderation policies as plain-language questions at inference time rather than baking fixed categories into model weights. The 3B model achieves 84.9% average F1 on text safety (matching a 20B baseline) and 83.8% on multimodal safety using 54.1M training samples including contrastively generated negatives. This enables teams to enforce different policies per customer or context without retraining, run locally on a single 16GB GPU, and integrate into existing deployment stacks like vLLM and llama.cpp under Apache 2.0 licensing.