Mistral releases Shieldstral, a 3B multimodal safety classifier that it says matches models up to 7x its size on text safety, available under Apache 2.0 (Mistral AI Blog)
Mistral is releasing Shieldstral as an open Apache 2.0 safety classifier.
The model is described as a 3B multimodal safety classifier. Mistral says it matches models up to seven times larger on text safety. The note does not add further benchmark detail beyond that claim. Techmeme's note
The model is described as a 3B multimodal safety classifier. Mistral says it matches models up to seven times larger on text safety. The note does not add further benchmark detail beyond that claim. Techmeme's note
score 6