fake_new_classifier / README.md
aswinsson's picture
Update README.md
f11bd2d
|
raw
history blame
476 Bytes
metadata
license: afl-3.0

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. This was created using the transformers library and the language used for training the model is primiarily English.

Language: English Dataset: https://www.kaggle.com/datasets/clmentbisaillon/fake-and-real-news-dataset