BitNet: Scaling 1-bit Transformers for Large Language Models

Hongyu Wang, Shuming Ma, Li Dong, HUANG SHAOHAN, Huaijie Wang, Lingxiao Ma, Fan Yang, ruipingwang, Yi Wu, Furu Wei

BitNet: Scaling 1-bit Transformers for Large Language Models: 108 upvotes on Hugging Face Daily Papers, #1 of 10 papers on 2023-10-18. Day-by-day upvote history.

The increasing size of large language models has posed challenges for deployment and raised concerns about environmental impact due to high energy consumption. In this work, we introduce BitNet, a scalable and stable 1-bit Transformer architecture designed for large language models. Specifically, we introduce BitLinear as a drop-in replacement of the nn.Linear layer in order to train 1-bit weights from scratch. Experimental results on language modeling show that BitNet achieves competitive performance while substantially reducing memory footprint and energy consumption, compared to state-of-the-art 8-bit quantization methods and FP16 Transformer baselines. Furthermore, BitNet exhibits a scaling law akin to full-precision Transformers, suggesting its potential for effective scaling to even larger language models while maintaining efficiency and performance benefits.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.