“The Era of 1-Bit LLMs: All Large Language Models Are in 1.58 Bits”, Shuming Ma, Hongyu Wang, Lingxiao Ma, Lei Wang, Wenhui Wang, Shaohan Huang, Li Dong, Ruiping Wang, Jilong Xue, Furu Wei2024-02-27 (reduced-precision NNs, AI scaling)⁠:

Recent research, such as BitNet, is paving the way for a new era of 1-bit Large Language Models (LLMs).

In this work, we introduce a 1-bit LLM variant, namely BitNet b1.58, in which every single parameter (or weight) of the LLM is ternary -1, 0, 1. It matches the full-precision (ie. FP16 or BF16) Transformer LLM with the same model size and training tokens in terms of both perplexity and end-task performance, while being more cost-effective in terms of latency, memory, throughput, and energy consumption.

More profoundly, the 1.58-bit LLM defines a new scaling law and recipe for training new generations of LLMs that are both high-performance and cost-effective.

Furthermore, it enables a new computation paradigm and opens the door for designing specific hardware optimized for 1-bit LLMs.