Overview

Welcome to the trial of NVIDIA Merlin on NVIDIA LaunchPad!

NVIDIA Merlin is an open source library providing end-to-end GPU-accelerated recommender systems, from feature engineering and preprocessing to training deep learning models and running inference in production. Merlin empowers data scientists, machine learning engineers, and researchers to build high-performing recommenders at scale. Merlin includes libraries, methods, and tools that streamline the building of recommenders by addressing standard preprocessing, feature engineering, training, and inference challenges. Each component of the Merlin pipeline is optimized to support hundreds of terabytes of data, all accessible through easy-to-use APIs. With Merlin, better predictions and increased click-through rates are within reach.

Merlin Transformers4Rec is a flexible and efficient library for sequential and session-based recommendation. It works as a bridge between NLP and recommender systems by integrating with one the most popular NLP frameworks HuggingFace Transformers, making state-of-the-art Transformer architectures available for RecSys researchers and industry practitioners.

You can build a fully GPU-accelerated pipeline for sequential and session-based recommendation with Transformers4Rec and its smooth integration with other components of NVIDIA Merlin: NVTabular for preprocessing and Triton Inference Server for inference.

Included in this Merlin LaunchPad Developer Lab is an example, “Getting Started: Session-based Recommendations”. Through two Jupyter notebooks, you will learn main concepts of Transformers4Rec and train a session-based recommendation model with a Transformer architecture. The first notebook focuses on generating and preprocessing sequential data with NVTabular, and the second notebook shows you how to train and evaluate a Transformer-based (XLNET) model with Transformers4Rec using PyTorch API.

If you have any questions about the lab, please contact support and we’ll be happy to help you.