Create JSONL for LLaMa2 Chat Models

This application is built using Streamlit and helps users create a properly formatted JSONL file. This file format is needed to fine-tune a LLaMa2 chat model.

<s>[INST] <<SYS>>
{{ system_prompt }}
<</SYS>>

{{ user_message }} [/INST]

Features

1. User Prompts: Enter a question under the label "Enter your question? Human:".
2. AI Response: Provide your ideal AI-generated response.
3. Custom System Message: Add a custom system message or stick with the default message "You are a helpful and friendly assistant.".
4. Data Saving: Upon pressing the "Accept Inputs" button, the provided data gets formatted and appended to an output.jsonl file.

Setup & Run

1. Clone this repository.
2. Install the required packages using:

   pip install -r requirements.txt
   

3. Run the Streamlit app using:

   streamlit run app.py
   

Dependencies

• streamlit
• jsonlines

Feedback & Contributions

Feel free to raise issues, provide feedback, or make contributions to improve the application.

License

This project is licensed under the MIT License. See LICENSE for more information.

Authors

MIT License

(c) 2023 Ray Bernard

This is a simple guide to get started with the finetuneLLaMa2 application. Please, do not hesitate to open an issue if you encounter any problem or have a suggestion.