Code for reproducing the Stanford Alpaca InstructLLaMA result on consumer hardware

Summary: The Stanford Alpaca project has released code for reproducing their Alpaca InstructLLaMA result on consumer hardware, using low-rank adaptation (LoRA) to provide an Instruct model of similar quality to text-davinci-003 that can run on a Raspberry Pi. The code includes training code, a script for downloading and inference on the foundation model and LoRA, as well as the resulting LoRA weights themselves, and can be easily extended to the 13b, 30b, and 65b models.