Gradio WebUI for Llama-3.2-Vision

This repo provides a user-friendly web interface for interacting with the Llama-3.2-11B-Vision model, which generates text responses from image and text prompts.

Getting Started

1. Get a Hugging Face Token

   • Sign up for an account here.
   • Get a huggingface token to access llama3.2-11b-vision model.

2. Project Setup

   • Clone the repository:

     git clone https://github.com/spacewalk01/llama3.2-vision-webui.git
     cd llama3.2-vision-webui

   • Install dependencies:

     pip install -r requirements.txt

3. Run the Application

   • Start the Gradio interface by running:

     python main.py --token Your_Hugging_Face_Token

   • Access the local URL to upload images and prompts, and view the Llama 3.2 Vision model's responses.

License

This project is licensed under the MIT License. See the LICENSE file for details.

References

1. Llama 2.3 technical overview
2. Huggingface Model
3. Gradio