Shieldstral is Mistral’s 3B open-weights answer to the guardrail-model problem: instead of baking a fixed taxonomy of harm categories into the weights — which forces retraining every time a product, audience, or moderation policy changes — you hand it the policy as a plain-language question at inference time (“Does this content promote violence against a protected group? Is this image safe to show to a minor?”), and it returns a calibrated yes/no safety score from a single forward pass, covering text, images, and text+image pairs through one interface. The framing does real work: it unifies prompt classification, response moderation, refusal detection, and toxicity detection into a binary question-answering task, with policies living entirely in the prompt so one checkpoint adapts to novel policies at deployment without retraining. It’s small enough to run on a single 16GB GPU, yet Mistral claims it matches or beats open guard models up to 7x its size on text safety and sets a new state of the art on multimodal moderation — helped by training on deliberately similar, easily-confused policy pairs (teaching discrimination rather than memorization), LoRA fine-tunes merged via SLERP, and image–query pairs filtered through a vision-language reranker. Released under Apache 2.0 as an inaugural member of the Open Secure AI Alliance alongside NVIDIA; weights on HuggingFace, technical report on arXiv.
Shieldstral — Mistral's 3B Policy-Adaptive Safety Classifier
Mistral releases Shieldstral: a 3B open-weights multimodal safety classifier that takes your moderation policy as a plain-language question at inference time — Apache 2.0, runs on a 16GB GPU.