Deploying HuggingFace Models on Amazon SageMaker Real-Time Inference

In this video we explore how simple it is to directly deploy models from the HuggingFace Model Zoo to SageMaker Real-Time Inference for latency and throughput sensitive workloads. Prerequisites/Good To Know - Amazon SageMaker Intro: https://www.youtube.com/watch?v=pSu-aVC7UCw - SageMaker Containers Explained: https://www.youtube.com/watch?v=QszQeOygNdM&t=303s - SageMaker Available Images: https://github.com/aws/deep-learning-containers/blob/master/available_images.md - SageMaker Pricing Page: https://aws.amazon.com/sagemaker-ai/pricing/ Video Resources - Github Link: https://github.com/RamVegiraju/GenAI-Samples/tree/master/HuggingFace-SageMaker-Deployment-Intro - HF Model Link: https://huggingface.co/google/flan-t5-base Timestamps 0:00 Introduction 0:30 What is ML Model Deployment 2:30 What is HuggingFace 5:15 SageMaker Real-Time Endpoints Explained 10:00 Hands-On Notebook