Embracing the Era of 1-Bit LLMs: Microsoft & UCAS’s BitNet b1.58 Redefines Efficiency

In a new paper The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits, a research team introduces a new variant of 1-bit LLMs called BitNet b1.58, which preserves the advantages of the original 1-bit BitNet while ushering in a novel computational paradigm that significantly enhances cost-effectiveness in terms of latency, memory usage, throughput, and energy consumption.

advantages ai artificial intelligence computational deep-neural-networks efficiency language language models large language large language model large language models llms machine learning machine learning & data science microsoft ml novel paper paradigm research research team team