@pranavn1008.bsky.social
Predoctoral Researcher @Google DeepMind
https://pranavajitnair.github.io/
https://pranavajitnair.github.io/
Reposted
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
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
February 11, 2025 at 5:41 PM
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
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