Attention Sinks

Introduced by Xiao et al. in Efficient Streaming Language Models with Attention Sinks

Please enter a description about the method here

Source: Efficient Streaming Language Models with Attention Sinks

Paper	Code	Results	Date	Stars

Task	Papers	Share
Language Modelling	1	100.00%

This feature is experimental; we are continuously improving our matching algorithm.

Component	Type	Add Remove
🤖 No Components Found	You can add them if they exist; e.g. Mask R-CNN uses RoIAlign