issues
search
lucidrains
/
CoLT5-attention
Implementation of the conditionally routed attention in the CoLT5 architecture, in Pytorch
MIT License
224
stars
13
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
update autocast
#10
Abdelrahman350
opened
3 months ago
0
missing argument when calling triton_coor_descent
#9
wangzizhao
closed
8 months ago
4
Wrong results given by triton bwd
#8
LouChao98
closed
11 months ago
16
Simple ViT error
#7
matrix0117
opened
1 year ago
1
Could u plz provide more details about the training info, thx a lot!
#6
bopeng87
opened
1 year ago
0
The position embedding?
#5
LydiaXiaohongLi
closed
1 year ago
5
Amazing work. Are the models going to be made available?
#3
jmzeng
closed
1 year ago
1
GPT type T5 impementation
#2
aamir-gmail
closed
1 year ago
2