/Llama2-Code-Interpreter

Make Llama2 use Code Execution, Debug, Save Code, Reuse it, Access to Internet

Primary LanguageJupyter Notebook

llama2 code interprerter icon

Llama2 Code Interpreter

This project allows LLM to generate code, execute it, receive feedback, debug, and answer questions based on the whole process. It is designed to be intuitive and versatile, capable of dealing with multiple languages and frameworks.

The purpose and direction of the project

🌟 Key Features

  • πŸš€ Generation and Execution of Code : Tailor-made codes spun into existence and executed smoothly.
  • πŸ”Ž Interactive Debugging & Feedback : Real-time engagement in debugging, accompanied by constructive feedback for an improved coding experience.
  • 🧠 Dynamic Q&A System : A revolutionary question-answering mechanism powered by cutting-edge code generation, execution, real-time feedback, and interactive debugging.
  • 🌐 Internet Access Support : Comprehensive functionality, powered by full support for internet access. Make the world wide web your sandbox!

Examples


Llama2 in Action

example1_president_search_with_code

In response to the query, "Who is the current president of South Korea?", Llama2 generates Python code for web scraping. This code targets the official website of the South Korean government, specifically extracting information from the exact URL.

The script retrieves the HTML title tag which contains the current president's name. The output, 'λŒ€ν•œλ―Όκ΅­ λŒ€ν†΅λ Ή > μœ€μ„μ—΄ λŒ€ν†΅λ Ή > μ·¨μž„μ‚¬', allows Llama2 to discern that the incumbent president is μœ€μ„μ—΄ (Yoon Suk-yeol).

Installation

  1. Clone the repository:
git clone https://github.com/SeungyounShin/Llama2-Code-Interpreter.git
  1. Change directory:
cd Llama2-Code-Interpreter.git
  1. Install the required dependencies:
pip install -r requirements.txt

Usage

To start interacting with Llama2 via the Gradio UI:

python3 chatbot.py --mode_path <your-model-path>

Then, open your web browser and navigate to the URL displayed in the console.

Contributions

Contributions, issues, and feature requests are welcome! Feel free to check issues page.

License

Distributed under the MIT License. See LICENSE for more information.

Contact

Seungyoun, Shin - 2022021568@korea.ac.kr

Acknowledgement

Here are some relevant and related projects that have contributed to the development of this work:

  1. llama2 : GitHub Repository
  2. yet-another-gpt-tutorial : GitHub Repository

These projects have been instrumental in providing valuable insights and resources, and their contributions are highly appreciated.