Chat with Llama 3.2-Vision (11B) Multimodal LLM

Overview

The Llama 3.2-Vision collection of multimodal large language models (LLMs) is a collection of pretrained and instruction-tuned image reasoning generative models in 11B and 90B sizes (text + images in / text out). The Llama 3.2-Vision instruction-tuned models are optimized for visual recognition, image reasoning, captioning, and answering general questions about an image. Read more

Features

• Visual recognition
• Image reasoning
• Captioning
• Answering general questions about an image
• Tool Calling

Installation

To get started with this project, follow these steps:

1. Clone the repository:

   git clone https://github.com/bhimrazy/chat-with-llama-3.2-vision
   cd chat-with-llama-3.2-vision

2. Install the required dependencies:

   pip install -r requirements.txt

Usage

1. Run server

   export HF_TOKEN=your_huggingface_token # required for model download
   
   python server.py

2. Run client/app

   To test using python client, execute the following command:

What cocktail can I make with these ingredients?

python client.py --image=cocktail-ingredients.jpg --prompt="What cocktail can I make with these ingredients?"

To run the application, execute the following command:

streamlit run app.py