Apparently this is a 8x22B MoE (Mixture of Experts) model Mistral's previous most powerful openly licensed model was Mixtral, an 8x7B MoE
Mistral Releases 8x22B MoE Model Advancing Open Source AI
By
–
By
–
Apparently this is a 8x22B MoE (Mixture of Experts) model Mistral's previous most powerful openly licensed model was Mixtral, an 8x7B MoE