This is a very simple approach of mine towards creating a recommendation model. I have used the bert-based-uncased model and finetuned it. The dataset as mentioned is Amazon Reviews 2023, a recent one. Although I could not involve all of the categories, I have tried running it on a small one, Magazine Subscriptions.

Due to time, resource and space constraints, this was a tiny yet successful effort towards modelling a recommender.

Downloads last month
19
Safetensors
Model size
109M params
Tensor type
F32
·
Inference API
Unable to determine this model's library. Check the docs .

Model tree for SriSougandhika/APRec

Finetuned
(2309)
this model

Dataset used to train SriSougandhika/APRec