OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Models

Dlrm

Dlrm is an open-source Python implementation of a deep learning recommendation model for personalization and recommendation systems. It accepts dense numerical feature vectors and sparse indices into embedding tables, combines selected embeddings with sum, dot-product or concatenation operators, and processes them with multilayer perceptrons to produce a click-probability output.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Dlrm — OpenViST project profile in AI Models.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Dlrm when you need a reference implementation or prototype for a recommendation model that combines dense numerical signals with sparse categorical features and embedding interactions.

Who it is for

  • Developers prototyping personalization or recommendation models.
  • Researchers and practitioners studying models that combine numerical features with sparse categorical inputs.

Documented uses

  • Explore a recommendation model that processes dense and sparse features together.
  • Prototype ranking or personalization pipelines using embedding tables and multilayer perceptrons.
  • Compare embedding-interaction operators such as sum, dot product and concatenation.
Before you choose

Requirements & limits

The public repository identifies the project as open source under the MIT license.

  • The repository includes both PyTorch and Caffe2 implementations.
  • The model expects dense floating-point vectors and sparse indices into embedding tables.
  • Embedding interactions are described using sum, dot-product or concatenation operators.
  • The README provides a tiny PyTorch training example, as well as data-generation/loading code, tests and benchmark scripts.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Run the DLRM PyTorch tiny-model sample

Train the documented tiny DLRM model using generated data.

Before you start

  • Python
  • The DLRM repository, including dlrm_s_pytorch.py

Steps

  1. From the repository, run the command below.

    Documented command
    python dlrm_s_pytorch.py --mini-batch-size=2 --data-size=6

  2. Review the training progress output, which reports iteration, loss, and accuracy.

Expected outcome

The sample reports three training iterations for a tiny model.

Guide limitations

  • The README labels this a sample run and does not document environment setup or additional dependency requirements.
  • The sample output shows accuracy as 0.000%; it does not establish recommendation quality.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
12 October 2026
Original website title
facebookresearch/dlrm · Official homepage title · retained in its source language
How we review sourcesSuggest a correction