Publications
All publications
A complete archive of all publications.
This thesis will address the asymmetry by covering the design and building of a prototype platform focused on both educators and students alike, providing students with accurate preparation material aggregated by their educators as well as providing said educators with automations that involve Large language Models (LLMs) to make course focused tasks easier to manage.
This paper presents a methodology for integrating LLMs into constrained environments, with a focus on the NVIDIA Jetson Orin Nano. We examine optimization techniques such as 4-bit quantization and knowledge distillation, which significantly reduce memory requirements with minimal accuracy loss.