lecture
Transformers, the tech behind LLMs | Deep Learning Chapter 5
3Blue1Brown · 13 recommenders · 10 months
3Blue1Brown's visual explanation of how transformers and GPT-style language models work, tracing data through tokens, embeddings and attention.
Why Hacker News readers recommend it: HN treats it as the go-to visual introduction to transformers, and many say it finally made attention and embeddings click.
LLMs & generative AIMachine learning & deep learning#transformers#attention#embeddings#llm#deep learning#visualization
“what bade me finally understand the transformer architecture [0] and attention [1], are 3Blue1Brown's videos.”
View the original HN discussion
