Super Study Guide: Transformers & Large Language Models
The book "Super Study Guide: Transformers & Large Language Models" is a concise and visual guide for those who want to understand the structure of large language models, whether for interviews, projects, or personal interest.
It is divided into 5 parts: Foundations: primer on neural networks and important deep learning concepts for training and evaluation Embeddings: tokenization algorithms, word-embeddings (word2vec) and sentence embeddings (RNN, LSTM, GRU) Transformers: motivation behind its self-attention mechanism, detailed overview on the encoder-decoder architecture and related variations such as BERT, GPT and T5, along with tips and tricks on how to speed up computations Large language models: main techniques to tune Transformer-based models, such as prompt engineering, (parameter efficient) finetuning and preference tuning Applications: most common problems including sentiment extraction, machine translation, retrieval-augmented generation and many more.
About the Authors
Afshine Amidi
Afshin Amidi is an instructor of the workshop on transformers and large language models at Stanford, as well as a project leader related to large language models at Netflix. Previously, he worked with the Gemini team at Google, applying natural language processing methods to solve complex queries. Before that, Afshin worked on improving search and recommendation systems at Uber Eats. In addition to his main activities, he has published several scientific papers at the intersection of deep learning and computational biology. Afshin received his bachelor's and master's degrees from École Centrale Paris, as well as a master's degree from MIT.
Shervine Amidi
Sherwin Amidi is a workshop instructor on transformers and large language models at Stanford, as well as a member of the Gemini team at Google, where he uses large language models to process action-based queries. Previously, Sherwin worked on applied machine learning tasks for recommendation systems at Uber Eats, focusing on representation learning to improve meal recommendations. In addition, he has published several scientific papers at the intersection of deep learning and computational biology. Sherwin earned bachelor's and master's degrees from École Centrale Paris, as well as a master's degree from Stanford University.
Books
Read Book Super Study Guide: Transformers & Large Language Models
| # | Title |
|---|---|
| 1 | Super Study Guide: Transformers & Large Language Models |