← All topics
safety-classifiers
Latest stories covering safety-classifiers, with summaries and links to related coverage.
1 stories · 1 reports · page 1 of 1
Connected topics
Mistral's Shieldstral: 3B open-weights model for multimodal moderation
tool
5 min read
Shieldstral is a 3B open-weights multimodal safety classifier that outperforms larger models by up to 7x by framing content moderation as a policy-adaptive question-answering task. It accepts plain-language policies at inference time, unifying text and image safety evaluation without retraining, and is released under Apache 2.0, providing calibrated safety scores while operating efficiently on a single 16GB NVIDIA GPU.