Downloads · 30 days
13
8% of all-time downloads
fake-news-detector
AyushSingh2278/fake-news-detector
fake-news-detector is a text classification model from AyushSingh2278. Use it when you need a label for a piece of text. The card lists the license as apache-2.0.
This is a fine-tuned BERT model for fake news detection. It classifies a given news headline or article as real or fake.
All-time downloads
155
Public
Repo size
876 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin438 MB · 100%
At a glance
- Task
- Text Classification
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Oct 31, 2025
- Updated
- Oct 31, 2025
- SHA
- 1ab79ef1
Try a prompt
Datasets
Model card
From the Hugging Face model README
📰 Fake News Detector - BERT Fine-Tuned Model
This is a fine-tuned BERT model for fake news detection.
It classifies a given news headline or article as real or fake.
🧠 Model Details
- Base model:
bert-base-uncased - Fine-tuned on: Custom Fake News dataset
- Framework: PyTorch
- Tokenizer:
BertTokenizerFast
🚀 How to Use
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("AyushSingh2278/fake-news-detector")
model = AutoModelForSequenceClassification.from_pretrained("AyushSingh2278/fake-news-detector")
text = "Breaking: AI replaces all journalists!"
inputs = tokenizer(text, return_tensors="pt")
outputs = model(**inputs)
pred = outputs.logits.argmax(-1).item()
print("Fake News" if pred == 1 else "Real News")
- Task
- Text Classification
- Type
- bert
- License
- apache-2.0
- Languages
- en
- Created
- Oct 31, 2025
- Updated
- Oct 31, 2025