EdoardoBotta/RQ-VAE-Recommender
[Pytorch] Generative retrieval model using semantic IDs from "Recommender Systems with Generative Retrieval"
Implements a two-stage pipeline where RQ-VAE discretizes items into semantic ID tuples, then a decoder-only transformer generates user sequences directly as ID codes for efficient retrieval. Supports Amazon Reviews and MovieLens datasets with pretrained checkpoints on Hugging Face, using gin-config for flexible hyperparameter management across model stages.
747 stars. No commits in the last 6 months.
Stars
747
Forks
107
Language
Python
License
MIT
Category
Last pushed
Sep 22, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/EdoardoBotta/RQ-VAE-Recommender"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
is0383kk/SymbolEmergence-VAE-GMM
Symbol emergence using Variational Auto-Encoder and Gaussian Mixture Model...
is0383kk/Dirichlet-VAE
Dirichlet-Variational Auto-Encoder by PyTorch
Bhavik-Ardeshna/pytorch-VAE
Variational Autoencoder and a Disentangled version (beta-VAE) implementation in PyTorch-Lightning
farhad-dalirani/Controllable-Face-Generation-VAE
A controllable generative model using a Convolutional Variational Autoencoder (VAE) with GUI to...
code-with-idrees/Denoising-Autoencoder-Cifar10
PyTorch DAE that denoises CIFAR-10 images — 24.62 dB PSNR, 0.8225 SSIM, 182K params. Features...