issues
search
locuslab
/
massive-activations
Code accompanying the paper "Massive Activations in Large Language Models"
https://arxiv.org/abs/2402.17762
MIT License
106
stars
8
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
the standard deviation of the activation
#7
Cooperx521
opened
2 months ago
3
Thoughts about ViT register and anchor token
#6
Cooperx521
closed
2 months ago
3
Training only on 2B tokens (openwebtext)
#5
Nandan91
opened
6 months ago
3
what if set all layers' massive activations to their mean value?
#4
yyfcc17
opened
6 months ago
1
How to get the mean value of massive activation
#3
pengyao96
opened
6 months ago
1
Update INSTALL.md
#2
eltociear
opened
6 months ago
0
Which layer's activation is used?
#1
iyupan
opened
6 months ago
1