marioyordanoff / moa-paper Goto Github PK

Figure 1: Illustration of the Mixture-of-Agents Structure. This example showcases 4 MoA layers with 3 agents in each layer. The agents here can share the same model.

1. Introduction
2. Key Features
3. Installation
4. Credits

Mixture-of-Agents (MoA) is a novel approach to enhance the capabilities of Large Language Models (LLMs). By leveraging a structured ensemble of specialized agents, MoA improves performance across various tasks while maintaining efficiency and scalability.

This project is based on the research paper "Mixture-of-Agents: Enhancing Large Language Model Capabilities" by Yixuan Wang, Jiawei Han, and Chao Zhang.

• MoA aims to mitigate individual model deficiencies and enhance overall response quality through collaborative synthesis.
• MoA models achieves state-of-art performance on AlpacaEval 2.0, MT-Bench and FLASK, surpassing GPT-4 Omni.
• The Mixture-of-Agents method does not require any fine-tuning and only utilizes the interface of prompting and generation of LLMs.

1. Clone the repository:

git clone https://github.com/marioyordanoff/moa-paper
cd moa-paper

2. Install the required dependencies:

   pip install -r requirements.txt
   

3. Set up your environment variables: Create a .env file in the root directory and add your Groq API key:

   GROQ_API_KEY=your_api_key_here
   

4. Run the Streamlit app:

   streamlit run app.py
   

• Groq - Model Inference
• Lancghain - Orchestration
• Streamlit - GUI