Today, the world is full of LLMs, short for large language models. Not a day goes by without a new language model being announced, fueling the fear of missing out in the ai space. However, many still struggle with the basics of LLMs, making it difficult to keep pace with advancements. This article is intended for those who wish to delve deeper into the inner workings of such ai models to have a solid understanding of the topic. With this in mind, I present some tools and articles that can help solidify the concepts and break down the concepts of LLMs so that they can be easily understood.
· 1. The Illustrated Transformer by Jay Alammar
· 2. GPT-2 illustrated by Jay Alammar
· 3. LLM Visualization by Brendan Bycroft
· 4. OpenAI Tokenizer Tool
· 5. Understanding GPT Tokenizers by Simon Wilson
· 6. Do machine learning models memorize or generalize? -One explorable by PAR
I'm sure many of you are already familiar with this iconic item. Jay was one of the early pioneers of writing technical articles with powerful visualizations. A quick tour of this blog will help you understand what I'm trying to convey. Over the years, he has inspired many writers to follow his example, and the idea of tutorials has moved from simple text and code to immersive visualizations. Anyway, back to the illustrated Transformer. The transformer architecture is the fundamental component of all transformer language models (LLM). Therefore, it is essential to understand its basics, which is what Jay does wonderfully. The blog covers crucial concepts such as:
- A high-level look at the transformative model
- Exploring the transformer…
