A roberta-base classifier that classifies if a prompt is relevant to questions from the WMDP dataset. The classifier is trained using ~300 synthetic questions generated by GPT-4, with similar style to the WMDP datset.

Downloads last month: 5

Safetensors

Model size

125M params

Tensor type

F32

Inference API

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.