bhavitvyamalik/fake-news_xtremedistil-l6-h256-uncased

Dataset used

Labels

Fake news: 1
Real news: 0

Usage

from transformers import AutoModelForSequenceClassification, AutoTokenizer, AutoConfig
import torch

config = AutoConfig.from_pretrained("bhavitvyamalik/fake-news_xtremedistil-l6-h256-uncased")
model = AutoModelForSequenceClassification.from_pretrained("bhavitvyamalik/fake-news_xtremedistil-l6-h256-uncased", config=config)
tokenizer = AutoTokenizer.from_pretrained("microsoft/xtremedistil-l6-h256-uncased", usefast=True)

text = "According to reports by Fox News, Biden is the President of the USA"
encode = tokenizer(text, max_length=512, truncation=True, padding="max_length", return_tensors="pt")

output = model(**encode)
print(torch.argmax(output["logits"]))

Performance on test data

'test/accuracy': 0.9977836608886719,
'test/aucroc': 0.9999998807907104,
'test/f1': 0.9976308941841125,
'test/loss': 0.00828308891505003

Run can be tracked here

Wandb project for Fake news classifier