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

• 🚀 Code Generation and Execution: Llama2 is capable of generating code, which it then automatically identifies and executes within its generated code blocks.
• Monitors and retains Python variables that were used in previously executed code blocks.
• 🌟 At the moment, my focus is on "Data development for GPT-4 code interpretation" and "Enhancing the model using this data". For more details, check out the feat/finetuning branch in our repository.

Examples

---

Llama2 in Action

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, '대한민국 대통령 > 윤석열 대통령 > 취임사', allows Llama2 to discern that the incumbent president is 윤석열 (Yoon Suk-yeol).

Installation

1. Clone the repository:

git clone https://github.com/SeungyounShin/Llama2-Code-Interpreter.git

2. Change directory:

cd Llama2-Code-Interpreter.git

3. Install the required dependencies:

pip install -r requirements.txt

I see, you want to include the part about setting the LLAMA_CI_PATH environment variable in the setup instructions. Here's how you might write it:

Setup

Set the LLAMA_CI_PATH environment variable: This script requires the LLAMA_CI_PATH environment variable to be set to the directory that contains the relevant code. You can set it to the current directory like this:

export LLAMA_CI_PATH=$(pwd)

Please note that this setting is only valid for the current shell session. If you want to make it permanent, you can add it to your shell's startup file (like .bashrc or .bash_profile).

Run App

To start interacting with Llama2 via the Gradio UI:

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

Replace <your-model-path> with the path to the model file you want to use. (Usally I recommend you to use chat-type model e.g. meta-llama/Llama-2-13b-chat)

Please let me know if you need help with a specific part of this setup process.

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 - [email protected]

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.

---