Mirrors/the-algorithm-ml
2
0
Fork 0
mirror of https://github.com/twitter/the-algorithm-ml.git synced 2024-06-16 06:38:43 +02:00
Code Issues Packages Projects Releases Wiki Activity
Source code for Twitter's Recommendation Algorithm
12 Commits 1 Branch 0 Tags 1.8 MiB
Python 99.3%
Shell 0.7%
a8258a5da4
Go to file
Rockerz a8258a5da4
Merge f7f26d0c20 into b85210863f
2023-09-21 17:35:12 +00:00
.github/workflows Twitter's Recommendation Algorithm - Heavy Ranker and TwHIN embeddings 2023-03-31 13:05:14 -05:00
common udpate 2023-09-12 18:12:05 +05:30
core udpate 2023-09-12 18:12:05 +05:30
images Twitter's Recommendation Algorithm - Heavy Ranker and TwHIN embeddings 2023-03-31 13:05:14 -05:00
machines mmm 2023-09-12 22:48:45 +05:30
metrics mmm 2023-09-12 22:48:45 +05:30
ml_logging update 2023-09-13 11:22:13 +05:30
optimizers update 2023-09-13 11:22:13 +05:30
projects Updates 2023-09-21 22:53:34 +05:30
reader update 2023-09-13 11:22:13 +05:30
tools Updates 2023-09-21 22:53:34 +05:30
.gitignore Twitter's Recommendation Algorithm - Heavy Ranker and TwHIN embeddings 2023-03-31 13:05:14 -05:00
.pre-commit-config.yaml Twitter's Recommendation Algorithm - Heavy Ranker and TwHIN embeddings 2023-03-31 13:05:14 -05:00
COPYING Twitter's Recommendation Algorithm - Heavy Ranker and TwHIN embeddings 2023-03-31 13:05:14 -05:00
LICENSE.torchrec Twitter's Recommendation Algorithm - Heavy Ranker and TwHIN embeddings 2023-03-31 13:05:14 -05:00
model.py Updates 2023-09-21 22:53:34 +05:30
pyproject.toml Twitter's Recommendation Algorithm - Heavy Ranker and TwHIN embeddings 2023-03-31 13:05:14 -05:00
README.md Twitter's Recommendation Algorithm - Heavy Ranker and TwHIN embeddings 2023-03-31 13:05:14 -05:00

README.md

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.