@retzam

Introduction to Generative Pretrained Transformers (GPT)

Apr 13 · 6 min read · Hello 👽, We are here now. It only took us 50 chapters to get to GPT! From our first chapter: AI Series, we had a clear roadmap, which you can check here 👉🏼 retzam-ai-roadmap. We've come a long way,

The true cost of training and inference for state-of-the-art Large Language Models

Apr 6 · 9 min read · Hello 👽, I was talking with a friend of mine recently, an AI researcher; He told me that a professor had told him how impressive training the first Google DeepMind, AlphaZero, in 2017 was to win the

BERT, Dense Passage Retrieval, and how RAG was invented

Mar 30 · 6 min read · Hello 👽, Welcome to another mid-series special 🎉. I know I said we're done with BERT, but this is truly insightful 🤗, enjoy. While pretraining and fine-tuning the BERT (Bidirectional Encoder Repres

Code: 20 Million Parameter BERT Model For SQuAD Tasks

Mar 23 · 7 min read · Hello 👽, Finally, we'll pretrain and finetune a BERT (Bidirectional Encoder Representations from Transformers) model from scratch in this chapter, brace up 🦾 Before we proceed, I want to believe you

The Distillation Dilemma: Anthropic, OpenAI, and the Security Predicament for Frontier AI Labs

Mar 9 · 6 min read · Hello 👽, This is going to be maybe the first back-to-back mid-series special, enjoy it while it lasts 😁. Let's do what we've come here to do 🕶️ A few weeks ago, Anthropic made a post on Twitter (I