Lite Toxic Comment Classification

Lightweight ALBERT-based model for English toxic comment classification. Achieves a mean AUC score of 98.28 on the Jigsaw test set.

Downloads last month: 101

Safetensors

Model size

11.7M params

Tensor type

I64

F32

Inference Examples

Text Classification

This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

pykeio
/

lite-toxic-comment-classification

Lite Toxic Comment Classification

Datasets used to train pykeio/lite-toxic-comment-classification