serving models

Model Serving provides a solution to host machine learning / deep learning (ML/DL) models as REST endpoints that are updated automatically, enabling data science teams to own the end-to-end lifecycle of a real-time machine learning model from training to production.

model_server.ipynb deploy any classifier model that has been pickled (cloudpickle).

For more demonstrations :

1. lightgbm-project
2. demo-sklearn-project
3. demo-xgb-project