In the process of actual exploration, practitioners may struggle to find an AI model suitable for their own application: should they choose LLM or fine-tune the model? If you use LLM, which one should you choose?
Recently, scholars from Amazon, Texas A&M University, Rice University and other institutions have discussed the development of language models such as ChatGPT, and their articles have also been retweeted by Yann LeCun.
Paper: https://arxiv.org/abs/2304.13712
Related resources: https://github.com/Mooler0410/LLMsPracticalGuide
From the perspective of practical application, this article will discuss the tasks applicable to LLM and the practical issues of models, data and tasks that need to be considered when choosing a model.
1 Introduction
In recent years, the rapid development of large-scale language models (LLM) has triggered a revolution in the field of natural language processing (NLP). These models are very powerful, with