WhiteDevilOP/spam-detection-distilbert

Spam Detection using DistilBERT

This model is a fine-tuned distilbert-base-uncased transformer for binary spam classification (spam vs ham).

Labels

• 0 → Ham
• 1 → Spam

Usage

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

tokenizer = AutoTokenizer.from_pretrained("<your-username>/spam-detection-distilbert")
model = AutoModelForSequenceClassification.from_pretrained("<your-username>/spam-detection-distilbert")

inputs = tokenizer(
    "You won a free iPhone!",
    return_tensors="pt",
    truncation=True,
    padding="max_length",
    max_length=128
)

with torch.no_grad():
    outputs = model(**inputs)

prediction = torch.argmax(outputs.logits, dim=1).item()
print("SPAM" if prediction == 1 else "HAM")

🔗 GitHub Repository

Code for training and inference is available here:
https://github.com/revanthreddy0906/spam-detection-distilbert.git