issues
search
OpenNLPLab
/
cosFormer
[ICLR 2022] Official implementation of cosformer-attention in cosFormer: Rethinking Softmax in Attention
Apache License 2.0
174
stars
25
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Script for computing memory consumption
#12
DaShenZi721
closed
1 year ago
3
why input is [s b dim] but not [b s dim]?
#11
Zyriix
closed
1 year ago
1
Why cosformer not work on XL-base transformer architecture?
#10
lwaekfjlk
opened
2 years ago
0
fix elu call bug
#9
lwaekfjlk
opened
2 years ago
0
Question about space complexity
#8
nihaomiao
closed
2 years ago
0
Pre-train model
#7
csorujian
opened
2 years ago
0
Why the attn mask is not used in forward function?
#6
HanielF
opened
2 years ago
1
Attn Mask for Non-causal Models
#5
roshansh-cmu
opened
2 years ago
2
causal attention not working when q and kv are not in same length
#4
zero0kiriyu
closed
2 years ago
1
Hello, when will the full code be published?
#3
zmxsss
closed
2 years ago
1
Create LICENSE
#2
OpenNLPLab123
closed
2 years ago
0
When the code will be released?
#1
LeeDoYup
closed
2 years ago
1