Quantization From the Ground Up
A visual, interactive guide to how language models store numbers as floats and why squeezing them to 4 or 8 bits barely hurts accuracy.
No account needed · sign in to keep your taste everywhere
More like this
Pages that share Quantization From the Ground Up's themes. Or browse all of Tech.
Do Machine Learning Models Memorize or Generalize?
An interactive explorable from Google PAIR that walks through grokking, where neural networks suddenly generalize long a…
NLP for Semantic Search
A free course on building semantic search systems with natural language processing, from machine translation to question…
AI Art Gallery
The NeurIPS creativity workshop gallery of machine-learning art, music, design and poetry, with highlights from several…
Kanji RNN
A sketch-rnn model trained on kanji that draws plausible-looking but invented characters stroke by stroke in your browse…
Can You Reverse Engineer Our Neural Network?
Jane Street presents a machine learning puzzle: given a trained network and no documentation, work out what it actually…
Artificial Intelligence: A Modern Approach
The companion site for the standard university textbook on artificial intelligence, with resources, code repositories, a…
Stumble onto more like this
One click takes you to a page you didn't know you were looking for. Rate it and the next one lands closer to your taste.
Add to Browser — it's freeWorks in Chrome, Edge and Brave. No account needed.