@
Modal's LLM Almanac (modal.com)
An interactive tutorial about various compute aspects of LLMs, like hosting or quantizing them. Made by (I think) Charles Frye
An interactive tutorial about various compute aspects of LLMs, like hosting or quantizing them. Made by (I think) Charles Frye
This is like an interactive 3Blue1Brown visualization and explanation of complete GPT-style model inference running in your browser. Incredible!
