Trained RQ-VAE checkpoint from Recommender Systems with Generative Retrieval by Google DeepMind.

Given item textual embeddings, this model generates a semantic id for the item that can be used for further downstream recommendation, ranking and retrieval tasks.

The model is trained on Amazon Beauty using the open-source paper implementation by Edoardo Botta, where more details on pre-training are found.

Downloads last month: 22

Safetensors

Model size

1.15M params

Tensor type

F32

Inference Providers NEW

This model is not currently available via any of the supported third-party Inference Providers, and HF Inference API was unable to determine this model's library.