mit-han-lab / streaming-llm

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks
https://arxiv.org/abs/2309.17453
MIT License
6.59k stars 361 forks source link

question about Table 1 in paper #55

Open AresXD opened 11 months ago

AresXD commented 11 months ago

Hi, I have a question about the experimental results in table1, are three settings of slidding windows tokens using positions assigned to[0,1,2,3...window_size] ?

Guangxuan-Xiao commented 11 months ago

Yes