The case for fine-tuning machine learning models on your local computer

The goal of this project is to explore the capabilities of fine tuning a large language model (LLM) locally on Apple Silicone hardware. The tools used to accomplish this task are all free and open-source software (FOSS), enabling anyone with a modern Apple computer without any extra cost. Training was done utilizing manually sourced data, formatting the data in JSON, and feeding it through MLX's Python package to train the local model taken from an online database. This was accomplished both directly in the command line as well as through various scripts written for the project's specific needs.