LongNet: Scaling Transformers to 1,000,000,000 Tokens

Jiayu Ding, Shuming Ma, Li Dong, Xingxing Zhang, HUANG SHAOHAN, Wenhui Wang, Furu Wei

LongNet: Scaling Transformers to 1,000,000,000 Tokens: 82 upvotes on Hugging Face Daily Papers, #2 of 15 papers on 2023-07-06. Day-by-day upvote history.

Scaling sequence length has become a critical demand in the era of large language models. However, existing methods struggle with either computational complexity or model expressivity, rendering the maximum sequence length restricted. In this work, we introduce LongNet, a Transformer variant that can scale sequence length to more than 1 billion tokens, without sacrificing the performance on shorter sequences. Specifically, we propose dilated attention, which expands the attentive field exponentially as the distance grows. LongNet has significant advantages: 1) it has a linear computation complexity and a logarithm dependency between tokens; 2) it can be served as a distributed trainer for extremely long sequences; 3) its dilated attention is a drop-in replacement for standard attention, which can be seamlessly integrated with the existing Transformer-based optimization. Experiments results demonstrate that LongNet yields strong performance on both long-sequence modeling and general language tasks. Our work opens up new possibilities for modeling very long sequences, e.g., treating a whole corpus or even the entire Internet as a sequence.

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.