The fake news classifer built using distillbert uncased. Created for the Fatima Fellowship coding challenge and trained on P100 instance for 3 epochs. The model is a binary classifier which predicts 1 in case of real news.
Library: transformers
Language: English
Dataset: https://www.kaggle.com/datasets/clmentbisaillon/fake-and-real-news-dataset
- Downloads last month
- 16
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.