Mistral AI Releases Shieldstral 1.0 3B: Open-Source Policy-Adaptive Multimodal Safety Classifier, Performance on Par with 7x-Scale Models
Mistral AI has released Shieldstral 1.0 3B, an open-weights, policy-adaptive multimodal safety classifier that treats content moderation as a single yes/no question rather than a fixed taxonomy of harm categories.
Return to original text
A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.
Open original at marktechpost.com