MLOps packaging: HuggingFace and Azure Container Registry
Автор: Alfredo Deza
Загружено: 2022-07-01
Просмотров: 763
Learn how to package a HuggingFace GPT2 model using automation with #MLOps and pushing the result to Azure Container Registry. With just a little bit of #Python and #FastAPI you can have a powerful text generation API that is self-documented!
▬▬🥇 Learn Objectives ▬▬
🚀 Create a FastAPI application with HuggingFace
🚀 Interact with the model with HTTP from a container using FastAPI
🚀 Containerize the application using GitHub Actions
🚀 Create repository secrets to login and push to Azure Container Registry
▬▬ C H A P T E R S ⏰ ▬▬
00:00 Introduction
01:00 Project Overview
04:40 Build Container
05:50 Run container locally
06:50 Interact with model
09:15 Azure Container Registry
09:35 GitHub Action workflow
11:30 Add Secrets to authenticate
12:40 Commit and trigger action
14:40 Verify image is on Azure
▬▬ 🔗 R E S O U R C E S ▬▬
Example repository → https://github.com/alfredodeza/huggin...
Practical MLOps book → https://www.amazon.com/Practical-MLOp...
Packaging ML models → https://learning.oreilly.com/videos/p...
Доступные форматы для скачивания:
Скачать видео mp4
-
Информация по загрузке:
