A collection of Python examples demonstrating the use of Mistral.rs, a Rust library for working with mistral models.
A light-weight codebase that enables memory-efficient and performant finetuning of Mistral's models. It is based on LoRA, a training paradigm where most weights are frozen and only 1-2% additional weights in the form of low-rank matrix perturbations are trained.
This article describes the process of implementing function-calling in an AI system, specifically using the Mistral AI platform. The example showcases the development of an assistant that can manage a home automation system through natural language interactions with the user, including the use of available functions, function logic, and the integration of these functions into the AI system.
