Transformer models: an introduction and catalog
This work addresses the need for researchers and practitioners to understand and differentiate between various Transformer models, but it is incremental as it primarily organizes existing information.
The paper tackles the challenge of navigating the numerous Transformer models by providing a catalog and classification of popular ones, including an introduction to key innovations, covering both self-supervised and human-in-the-loop trained models.
In the past few years we have seen the meteoric appearance of dozens of foundation models of the Transformer family, all of which have memorable and sometimes funny, but not self-explanatory, names. The goal of this paper is to offer a somewhat comprehensive but simple catalog and classification of the most popular Transformer models. The paper also includes an introduction to the most important aspects and innovations in Transformer models. Our catalog will include models that are trained using self-supervised learning (e.g., BERT or GPT3) as well as those that are further trained using a human-in-the-loop (e.g. the InstructGPT model used by ChatGPT).