Mistral unveils first multimodal AI model

Mistral AI model

DIYuan | 2024-09-12 22:42

【数据猿导读】 Mistral unveils first multimodal AI model

On September 12, TechCrunch reported that French AI startup Mistral released Pixtral 12B, the company's first multimodal AI large voice model capable of processing images and text at the same time. The Pixtral 12B model has 12 billion parameters, about 24GB in size, and the parameters roughly correspond to the model's problem-solving ability, with models with more parameters generally performing better than models with fewer parameters. Sophia Yang, head of developer relations at Mistral, said in a post on the X platform that Pixtral 12B will soon be available for testing on Mistral's chatbot and API service platforms Le Chat and Le Plateforme.

来源：DIYuan

收藏分享

声明：数据猿尊重媒体行业规范，相关内容都会注明来源与作者；转载我们原创内容时，也请务必注明“来源：数据猿”与作者名称，否则将会受到数据猿追责。