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
0
Safetensors
Model size
1.15M params
Tensor type
F32
·
Inference API
Unable to determine this model's library. Check the docs .