Merlin Models | Documentation 

NVIDIA Merlin Models provides standard models for Recommender Systems. The models are high quality implementations that range from classic Machine Learning models, to more advanced Deep Learning models.

Highlights

TODO
TODO
TODO

Quick tour

TODO

Use cases

TODO—Does this apply?

Installation

TODO—Perhaps something more detailed than the README.md at the root of the repository?

Installing with pip

FIXME

Installing with conda

FIXME

Installing with Docker

FIXME: True?

Merlin Models is installed in the following NVIDIA Merlin Docker containers that are available in the NVIDIA container repository:

Container Name	Container Location	Functionality
merlin-tensorflow-training	https://ngc.nvidia.com/catalog/containers/nvidia:merlin:merlin-tensorflow-training	Transformers4Rec, NVTabular, TensorFlow, and HugeCTR Tensorflow Embedding plugin
merlin-pytorch-training	https://ngc.nvidia.com/catalog/containers/nvidia:merlin:merlin-pytorch-training	Transformers4Rec, NVTabular and PyTorch
merlin-inference	https://ngc.nvidia.com/catalog/containers/nvidia:merlin:merlin-inference	Transformers4Rec, NVTabular, PyTorch, and Triton Inference

Before you can use these Docker containers, you need to install the NVIDIA Container Toolkit to provide GPU support for Docker. You can use the NGC links referenced in the preceding table to get more information about how to launch and run these containers.

Feedback and Support

If you’d like to contribute to the project, see the CONTRIBUTING.md file. We’re interested in contributions or feature requests for our feature engineering and preprocessing operations. To further advance our Merlin Roadmap, we encourage you to share all the details about your Recommender System pipeline in this survey.

Merlin Models | Documentation