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.
Mistral.rs is a fast LLM inference platform supporting inference on a variety of devices, quantization, and easy-to-use application with an Open-AI API compatible HTTP server and Python bindings. It supports the latest Llama and Phi models, as well as X-LoRA and LoRA support. The project aims to provide the fastest LLM inference platform possible.
Bookmarks on this page are managed by an admin user. 