Deep learning based recommender systems
This feature is in Beta. Workspace admins can control access to this feature from the Previews page. See Manage Databricks previews.
This page provides notebook examples for building recommendation systems using Serverless GPU compute. These examples demonstrate how to create efficient recommendation models using modern deep learning approaches.
Tutorial | Description |
|---|---|
Learn how to convert recommendation data into Mosaic Data Shard (MDS) format and then use that data to create a two-tower recommendation model. | |
Fine-tune a BERT-style embedding model on serverless GPU compute using contrastive learning with the llm-foundry framework and Composer's trainer. |
Two-tower recommendation model
These notebooks demonstrate how to convert your recommendation data into Mosaic Data Shard (MDS) format and then use that data to create a two-tower recommendation model. This approach is particularly effective for large-scale recommendation systems.
Data preparation: Convert recommendation model dataset to MDS format
First, convert your recommendation dataset to the MDS format for efficient data loading:
Convert data
Model training: Two-tower recommender model using PyTorch Lightning
Train the two-tower recommender model using the prepared dataset and the PyTorch Lightning Trainer API on multiple GPU nodes (A10 or H100 GPUs).