Showing cs.LGShow all
2 papers · 1 filter
cs.LG2024
Direct Quantized Training of Language Models with Stochastic Rounding
Kaiyan Zhao, Tsuguchika Tabaru, Kenichi Kobayashi +3
Although recent quantized Large Language Models (LLMs), such as BitNet, have paved the way for significant reduction in memory usage during deployment with binary or ternary weight…
cs.LG2021
Neural Network Module Decomposition and Recomposition
Hiroaki Kingetsu, Kenichi Kobayashi, Taiji Suzuki
We propose a modularization method that decomposes a deep neural network (DNN) into small modules from a functionality perspective and recomposes them into a new model for some oth…