🤗 CodeLlama 7B Finetuned Model (HF)
[](https://www.python.org/downloads/release/python-390/) [](https://github.com/psf/black) 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](https://github.com/SeungyounShin/Llama2-Code-Interpreter/wiki) ## Quick Start **Run the Gradio App**: ```bash python3 chatbot.py --path Seungyoun/codellama-7b-instruct-pad ``` ## News - 🔥🔥🔥[2023/08/27] We're thrilled to announce that our **[🤗 Llama2 Code Interpreter-7B](https://huggingface.co/Seungyoun/codellama-7b-instruct-pad) (Finetuned from [CodeLlama-7B-Instruct](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf))** model achieved a remarkable **70.12pass@1** on the [HumanEval Benchmarks](https://github.com/openai/human-eval). **HumanEval** | Model | Score(pass@1) | |-------------------------------|--------| | Codellama instruct 7b | 34.8% | | Codellama instruct 7b - finetuning | 70.12% | **GSM8K** | Model | Score | |-------------------------------|--------| | Code Llama 7B | 13% | | Code Llama 13B | 20.8% | | Codellama instruct 7b - finetuning | 28% | ## 🌟 Key Features - [x] 🚀 **Code Generation and Execution**: Llama2 is capable of generating code, which it then automatically identifies and executes within its generated code blocks. - [x] Monitors and retains Python variables that were used in previously executed code blocks. - [x] 🌟 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](https://github.com/SeungyounShin/Llama2-Code-Interpreter/tree/feat/finetuning) in our repository. - [x] 🌟 CodeLlama Support [CodeLlama2](https://github.com/facebookresearch/codellama) ## Examples ---
