README.md

---
license: mit
---

# bert-sms-detector

**bert-sms-detector** is a fine-tuned BERT-based model for **SMS spam detection**.  
It classifies input text messages as **spam** or **ham** (not spam).

---

## Model Details

- **Base Model**: `bert-base-uncased`
- **Task**: Text classification (spam detection)
- **Dataset**: [UC Irvine SMS Spam Collection](https://huggingface.co/datasets/ucirvine/sms_spam)  
- **Fine-tuning**: The model has been fine-tuned to detect spam messages from SMS text.

---

## Usage

```python
!pip install transformers

from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline

model_name = "alanjoshua2005/bert-sms-detector"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)

classifier = pipeline("text-classification", model=model, tokenizer=tokenizer)

texts = [
    "Congratulations! You've won a free ticket to the Bahamas.",
    "Hey, are we still meeting tomorrow at 5 PM?",
    "Free entry in 2 tickets to the concert. Text WIN to 80088."
]

label_map = {"LABEL_0": "Not Spam", "LABEL_1": "Spam"}

results = classifier(texts)

for text, result in zip(texts, results):
    print(f"Text: {text}\nPrediction: {label_map[result['label']]}\n")

```