Stanford's Alpaca is an instruction-following large language model (llm). Fine-tuned from Meta’s LLaMA 7B, it offers accessibility for and has similar behaviors to OpenAI’s text-davinci-003. It was developed to address deficiencies in existing instruction-following models and due to the lack of easily accessible models that come close in capabilities to closed-source models. Alpaca is intended and licensed for research use only. The dataset is CC BY NC 4.0 (allowing only non-commercial use) and models trained using the dataset should not be used outside of research purposes.