Intelligent Mixture-of-Models Router for Efficient LLM Inference

Implementation of Switch Transformers from the paper: "Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity"

LLM Semantic Router: Intelligent Mixture-of-Models (MoM) System with Privacy Preservation and Prompt Guard. The semantic router intelligently directs OpenAI compliant API requests to the most suitable backend models based on semantic understanding of request content.

The implementation of mixtures for different tasks.

🤪🧠💥 Mixture of Idiots (MoI): A Python project exploring 'Mixture of Models' (MOM) to solve complex problems by combining outputs from multiple LLMs (OpenAI, MistralAI, Gemini) using King, Duopoly, and Democracy architectures. Sometimes, a team of 'idiots' is surprisingly brilliant!