Inside Alpaca: The Language Model from Stanford University that can Follow Instructions and Match GPT-3.5
The model is based on Meta AI’s LLaMA and remains significatively smaller than GPT-3.5.
Instruction-following models such as GPT-3.5 (text-davinci-003), ChatGPT, Claude, and Bing Chat are now widely used by many users, including for work-related tasks. However, despite their growing popularity, these models still have many deficiencies that need to be addressed. False information, social stereotypes, and toxic language are some of the problems that have been associated with these models.
To address these pressing issues, the academic community needs to engage more actively. Unfortunately, researching instruction-following models in academia has been challenging due to the limited availability of models that come close in capabilities to closed-source models like OpenAI’s text-davinci-003. To address these challenges, researchers from Stanford University released their findings about an instruction-following language model called Alpaca.