Last Name Classification

🚀 Last Name Classification Model

A Transformer-based classifier that determines whether a given last name is likely to be real (LABEL_1) or fake (LABEL_0). It's useful for validating contact form submissions, preventing bot entries, or general name classification tasks.

🚀 Quick Start

This Transformer-based classifier can quickly determine whether a given last name is real or fake. Follow the installation and usage steps below to get started.

✨ Features

• Accurate Classification: Achieves an accuracy of 97.9%.
• Based on DistilBERT: Utilizes the distilbert/distilbert-base-uncased model.
• Text Classification: Specifically designed for text classification tasks.

📦 Installation

1. Clone the Repository:

git clone https://github.com/Vishodi/Last-Name-Classification.git

2. Set Up the Environment: Install the required packages using pip:

pip install -r requirements.txt

💻 Usage Examples

Basic Usage

from transformers import pipeline

# Replace with your model repository
model_dir = "vishodi/Last-Name-Classification"

# Load the model pipeline with authentication
classifier = pipeline(
    "text-classification",
    model=model_dir,
    tokenizer=model_dir,
)

# Test the model
test_names = ["musk", "zzzzzz", "uhyhu", "trump"]
for name in test_names:
    result = classifier(name)
    label = result[0]['label']
    score = result[0]['score']
    print(f"Name: {name} => Prediction: {label}, Score: {score:.4f}")

Output:

Name: musk   => Prediction: LABEL_1, Score: 0.9167
Name: zzzzzz => Prediction: LABEL_0, Score: 0.9991
Name: uhyhu  => Prediction: LABEL_0, Score: 0.9944
Name: trump  => Prediction: LABEL_1, Score: 0.9998

📚 Documentation

Project Structure

Last_Name_Prediction/
├── .gitattributes
├── README.md
├── config.json
├── model.safetensors
├── requirements.txt
├── special_tokens_map.json
├── tokenizer.json
├── tokenizer_config.json
└── vocab.txt

📄 License

This project is licensed under the MIT License.

🔗 Support Us

Information Table