LLAMA2 Code Interpreter: Generate and execute code

Understand the project

Practical overview

Use it when you want to try a local Gradio coding assistant whose model can execute generated code and incorporate feedback into responses.

Developers exploring code-generation and execution-feedback workflows.
People prototyping programming Q&A or code-assisted analysis with Llama or CodeLlama models.

Generate code from a natural-language request and execute identified code blocks.
Use execution feedback to debug generated code.
Retain Python variables across previously executed code blocks.
Explore an example workflow that retrieves financial data and plots it.

Before you choose

The repository is public and identifies the project as distributed under the MIT License. The README specifies Python 3.9 or newer.

The documented interface is Gradio, launched through chatbot.py.
The README offers a fine-tuned CodeLlama model path and a separate argument for using another model path.
Python variable retention is explicitly described; broader language and framework support is stated without a detailed compatibility list.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install the project dependencies and start the interface with its recommended fine-tuned CodeLlama model.

Clone the repository with the command below.
Documented command
```
git clone https://github.com/SeungyounShin/Llama2-Code-Interpreter.git
```
Change into the Llama2-Code-Interpreter directory.
Install dependencies with the command below.
Documented command
```
pip install -r requirements.txt
```
Start the Gradio app with the command below.
Documented command
```
python3 chatbot.py --path Seungyoun/codellama-7b-instruct-pad
```

The README’s documented command starts the Gradio app using the named CodeLlama-based model.

The instructions do not specify hardware requirements or provide a troubleshooting procedure.

Evidence and transparency

Source record details

Source availability: Active
Sources checked: 7 November 2026
Original website title: SeungyounShin/Llama2-Code-Interpreter · Official homepage title · retained in its source language