#17 · Primary category： Recommender Systems
Transformers4Rec
Transformers4Rec is a flexible and efficient library for sequential and session-based recommendation and works with PyTorch.
Project last updated：08/23/26
GitHub Stars
1.3K
Forks
165
Contributors
31
License
Apache-2.0
Why we included this project
If your product needs to guess what a user will click or buy next, Transformers4Rec is worth a look. It borrows transformer models from Hugging Face and applies them to sequences of user interactions, treating each item a person views or adds to cart as a token in a sentence. That approach works even when visitors browse anonymously, because the model only needs the current session's actions. Since it's built on PyTorch, you can drop in familiar transformer checkpoints and train them on your own item sequences without reinventing the attention mechanism. Researchers and engineers who already use Hugging Face will find the integration straightforward, and the library provides reusable building blocks for prototyping session-based recommender systems.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
gorse
AI powered open source recommender system engine supports classical/LLM rankers and multimodal content via embedding
DeepCTR
Easy-to-use,Modular and Extendible package of deep-learning based CTR models .
Surprise
A Python scikit for building and analyzing recommender systems
RSPapers
RSTutorials: A Curated List of Must-read Papers on Recommender System.
lightfm
A Python implementation of LightFM, a hybrid recommendation algorithm.