Blog Generation using LLMs

Overview

This project explores the generation of blogs using Large Language Models (LLMs). It leverages the Llama 2 release, which introduces a family of pretrained and fine-tuned LLMs with varying parameters (7B, 13B, 70B). These models exhibit significant improvements over the previous Llama 1 models, including training on 40% more tokens, a longer context length of 4k tokens, and the use of grouped-query attention for fast inference of the 70B model.

Features

• Pretrained Models: The project includes pretrained models with 7B parameters.
• Improved Performance: Llama 2 models show enhancements in training data, context length, and fast inference using grouped-query attention.

If you like this, please leave a ⭐! Thank you!

Getting Started

Prerequisites

• Python 3.x
• Dependencies listed in requirements.txt

Installation

pip install -r requirements.txt

Usage

1. Clone the repository:

git clone https://github.com/AshrithaB/Blog-Generation-using-LLMs.git
cd Blog-Generation-using-LLMs

2. Install dependencies:

pip install -r requirements.txt

3. Run the Streamlit App

streamlit run app.py

4. Explore the pretrained models and utilize them for blog generation.

Contribute

Contributions from the open-source community are welcomed. If you'd like to contribute to this project, please follow these steps:

1. Fork the repository.
2. Create a new branch for your feature or bug fix.
3. Make your changes and commit them.
4. Push your changes to your fork.
5. Create a pull request, explaining the changes you've made.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgments

• Thanks to the community for continuous support and contributions.
• Llama 2 release authors and contributors.