Introducing Shieldstral. | Mistral AI
- ThinkingSummaryShieldstral introduces a 3B open-weights multimodal safety classifier that outperforms models up to 7x its size by framing content moderation as a policy-adaptive question-answering task.
- Unlike traditional guardrail models, it accepts plain-language policies at inference time, unifying text and image safety evaluation without retraining.
- Released under Apache 2.0, it delivers calibrated safety scores across diverse benchmarks while running efficiently on a single 16GB NVIDIA GPU.
Unverified
- ThinkingSummaryShieldstral introduces a 3B open-weights multimodal safety classifier that outperforms models up to 7x its size by framing content moderation as a policy-adaptive question-answering task.
- Unlike traditional guardrail models, it accepts plain-language policies at inference time, unifying text and image safety evaluation without retraining.
- Released under Apache 2.0, it delivers calibrated safety scores across diverse benchmarks while running efficiently on a single 16GB NVIDIA GPU.
Sources: Mistral