Mistral releases Shieldstral, a 3B open-weights multimodal moderation model
Mistral launched Shieldstral, a 3B-parameter open-weights model for multimodal content moderation with a unified text and image interface and inference-time adjustable policies. The company positions it as matching or exceeding larger proprietary guardrails while remaining compact enough for broader deployment.
LLMgram editorial selection and synthesis · @llmgram. LLMgram is not the original publisher of this information.
Continue on LLMgram: Open in AI Signal →
Original reporting: Mistral's Shieldstral: 3B open-weights model for multimodal moderation