https://github.com/twitter/the-algorithm-ml

Source code for Twitter's Recommendation Algorithm
https://github.com/twitter/the-algorithm-ml

Last synced: 5 days ago
JSON representation

Source code for Twitter's Recommendation Algorithm

• Host: GitHub
• URL: https://github.com/twitter/the-algorithm-ml
• Owner: twitter
• License: agpl-3.0
• Created: 2023-03-27T15:51:49.000Z (almost 2 years ago)
• Default Branch: main
• Last Pushed: 2024-07-10T12:48:24.000Z (7 months ago)
• Last Synced: 2025-01-14T04:06:22.488Z (12 days ago)
• Language: Python
• Homepage: https://blog.twitter.com/engineering/en_us/topics/open-source/2023/twitter-recommendation-algorithm
• Size: 106 KB
• Stars: 10,165
• Watchers: 105
• Forks: 2,219
• Open Issues: 55
• Metadata Files:
  • Readme: README.md
  • License: COPYING

Awesome Lists containing this project

• my-awesome - twitter/the-algorithm-ml - 07 star:10.2k fork:2.2k Source code for Twitter's Recommendation Algorithm (Python)
• StarryDivineSky - twitter/the-algorithm-ml
• awesome-starred - twitter/the-algorithm-ml - Source code for Twitter's Recommendation Algorithm (Python)
• awesome-starred - twitter/the-algorithm-ml - Source code for Twitter's Recommendation Algorithm (Python)

README

        
This project open sources some of the ML models used at Twitter.

Currently these are:

1. The "For You" Heavy Ranker (projects/home/recap).

2. TwHIN embeddings (projects/twhin) https://arxiv.org/abs/2202.05387

This project can be run inside a python virtualenv. We have only tried this on Linux machines and because we use torchrec it works best with an Nvidia GPU. To setup run

`./images/init_venv.sh` (Linux only).

The READMEs of each project contain instructions about how to run each project.