BERT Spam Detection Model
Overview
This model is a fine-tuned BERT model for classifying messages as either "spam" or "ham" (non-spam). It was trained on the Telegram Spam dataset and can be used to filter out unwanted messages in various applications like email filtering systems, SMS spam detection, and maintaining the integrity of messaging platforms.
Dataset
The model was trained on the Telegram Spam dataset available on Hugging Face Datasets. The dataset contains labeled messages as either spam or ham.
Usage
To use this model, you need to install the transformers
library and authenticate with your Hugging Face account if the model is private.
Installation
pip install transformers
from transformers import pipeline
# Load the model and tokenizer
model_id = 'kushalbajje/BERT' # Replace with your model ID
classifier = pipeline('text-classification', model=model_id, tokenizer=model_id)
# Classify a sample message
message = "Congratulations! You've won a $1000 gift card. Click here to claim your prize."
result = classifier(message)
print(result)
- Downloads last month
- 41
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.