PART 3: Run inference and chat with the model - Deploy Mixtral 8x7B on AWS Inferentia2 · Data Society

Deploy Mixtral 8x7B on AWS Inferentia2

0%

PART 1 : AWS Inferentia2, Cost & Loading Model

PART 2 : Deploy Mixtral 8x7B to inferentia2

PART 3: Run inference and chat with the model