Simplified LLM Deployment With SageMaker JumpStart | Deploy Llama3 on SageMaker Real-Time Inference
Автор: Ram Vegiraju
Загружено: 2024-11-26
Просмотров: 468
In this video we introduced Amazon SageMaker JumpStart which is a Model Hub that allows for you to easily deploy models to SageMaker Inference. We specifically look at how this is handy for LLMs such as Llama3-8B and walk through a hands on example of deploying this model to a SageMaker Real-Time Endpoint.
Video Resources:
What is Amazon SageMaker: • What is Amazon SageMaker
Github Sample: https://github.com/RamVegiraju/GenAI-...
SageMaker Python SDK: https://github.com/aws/sagemaker-pyth...
Boto3 AWS Python SDK: https://boto3.amazonaws.com/v1/docume...
Amazon SageMaker Documentation: https://aws.amazon.com/sagemaker/
SageMaker Blog Series: / amazon-sagemaker
Timestamps
0:00 Introduction
1:06 What is ML Deployment/Hosting
8:55 UI Deployment
12:45 Notebook Walkthrough
#aws #machinelearning #sagemaker #llm #generativeai
Доступные форматы для скачивания:
Скачать видео mp4
-
Информация по загрузке:
