Effortless model deployment with MLflow — Packing an NLP product review classifier from HuggingFace

How to save your Machine Learning models in an open-source format with MLflow to unlock effortless deployment experience later. Today, packaging models with multiple assets.

Welcome back to the series Effortless model deployment with MLflow! If you just join the party, check out the other post of the series:

• MLFlow: Introduction to the MLModel specification.
• Customizing inference with MLFlow: deploying a Computer Vision model with fast.ai.
• Packaging models with multiple pieces: deploying a recommender system.
• Packaging models with multiple assets (this post).
• Packaging stratified models (many models): deploying a partitioned model for demand forecasting.

Introduction: Packaging a model that contains multiple assets

In the first post, we saw an introduction to the MLModel format and why, by persisting your model in an open-source specification format you can achieve great flexibility in deploying models. The only thing it took was to log the model…