This is a heavily interactive web application, and JavaScript is required. Simple HTML interfaces are possible, but that is not what this is.
Post
Jeff Dean
jeffdean.bsky.social
did:plc:uinkqqbeiydzfm7v7pi4e5mi
Delighted to be a minor co-author on this work, led by
Pranav Nair: Combining losses for different Matyroshka-nested groups of bits in each weight within a neural network leads to an accuracy improvement for models (esp. 2-bit reps).
Paper: "Matryoshka Quantization" at arxiv.org/abs/2502.06786
2025-02-11T17:41:24.651Z