MoshiVis v0.1 Collection MoshiVis is a Vision Speech Model built as a perceptually-augmented version of Moshi v0.1 for conversing about image inputs โข 6 items โข Updated Mar 2 โข 23
Running 3.78k The Ultra-Scale Playbook ๐ 3.78k The ultimate guide to training LLM on large GPU Clusters