Models · Hacker News ·

Mistral's Shieldstral: 3B open-weights model for multimodal moderation

Mistral's Shieldstral: 3B open-weights model for multimodal moderation

Mistral introduced Shieldstral, a 3-billion-parameter open-weights model for multimodal content moderation. The model is designed to analyze text and images for safety-related classification tasks.

Read the full story at Hacker News →