While specific details about the training data were not disclosed, Pixtral 12B is designed to allow users to upload images and request details about their content using text queries.
Mistral developer relations manager Sophia Young noted a distinctive feature of the model: the ability to process an arbitrary number of images of any size. Early testers reported that the Pixtral 12B has an advanced architecture. The visual component includes special software that supports 1024×1024 image resolution and 24 hidden layers for advanced image processing.
Pixtral 12B will be available soon via API.
Source: Ferra
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
