K2t New

🚀 Keytotext

Keytotext is a model designed to take keywords as inputs and generate sentences as outputs, offering a practical solution for text generation tasks.

🚀 Quick Start

The core idea of Keytotext is to build a model that can generate sentences from input keywords. It is powered by Huggingface and comes with several useful features and resources.

✨ Features

• Powered by Huggingface: Leveraging the capabilities of Huggingface for efficient model development and deployment.
• Multiple Model Variants: Offers different model versions such as k2t, k2t - tiny, and k2t - base to meet various requirements.
• User - friendly UI: Comes with an interactive UI built using Streamlit for easy interaction.
• Available on PyPI: Can be easily installed via pip.

📦 Installation

To use Keytotext, you can install it via pip:

pip install keytotext

If you want to use the UI, you also need to install the following:

pip install streamlit-tags

💻 Usage Examples

Basic Usage

You can find example usage in the Colab notebook:

Example notebooks can be found in the Notebooks folder.

Advanced Usage

The UI provides a more intuitive way to interact with the model. You can access it here:

This UI uses a custom streamlit component built by the developer: GitHub

📚 Documentation

Model

Keytotext is based on the amazing T5 Model:

• k2t: Model
• k2t-tiny: Model
• k2t-base: Model

Training notebooks can be found in the Training Notebooks folder.

📄 License

This project is licensed under the MIT license.