issues
search
google-research
/
long-range-arena
Long Range Arena for Benchmarking Efficient Transformers
Apache License 2.0
705
stars
75
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Dev
#62
lucaslingle
closed
7 months ago
0
Is it really byte-level?
#61
LuCeHe
opened
10 months ago
0
Question regarding Pathfinder and Listops performance
#60
LeoXinhaoLee
opened
10 months ago
2
Question regarding model checkpoint
#59
LeoXinhaoLee
opened
1 year ago
0
Is there a pytorch equivalent of this implementation?
#58
yeshwanthv5
opened
1 year ago
2
Pretrained models
#57
yeshwanthv5
opened
1 year ago
0
Create pathfinder-X2.md
#56
Tylersuard
opened
1 year ago
1
How to use the pathfinder.py code to generate the dataset?
#55
Tylersuard
opened
1 year ago
1
ModuleNotFoundError: No module named 'flax.deprecated'
#54
DaShenZi721
closed
1 year ago
3
AAN dataset crashing when loading .tsv file
#53
exnx
opened
1 year ago
4
AAN dataset unavailable
#52
aleksandar-terzic
opened
1 year ago
1
Adding Temporal Latent Bottleneck & Fixing Flax Deprecated dependencies
#51
NiteshBharadwaj
closed
1 year ago
0
Adding Temporal Latent Bottleneck & Fixing Flax Deprecated dependencies
#50
NiteshBharadwaj
closed
1 year ago
1
The best checkpoint of Transformer
#49
yuzhenmao
closed
1 year ago
0
Current code doesn't work with latest flax version and run on CPU only
#48
ynahshan
opened
2 years ago
15
Added instructions for loading the TFDS pathfinder data
#47
GeoffNN
opened
2 years ago
1
Are encoder and decoder both implemented with sparse attention for bigbird? How long is the verified output length for the decoder?
#46
dongxinghua
opened
2 years ago
0
Dataset for the matching task
#45
Shigangli
opened
2 years ago
1
Quadratic Longformer suspicion
#44
YegorKhodak
closed
2 years ago
1
Request about cuda version when using GPUs
#43
wuhaixu2016
closed
2 years ago
4
Error when run document retrival
#42
weixuansun
opened
2 years ago
3
Pathfinder not learning three times in a row.
#41
alexmathfb
closed
2 years ago
1
Perceiver on LRA
#40
Muennighoff
opened
2 years ago
0
Error in matching task
#39
jnhwkim
opened
2 years ago
0
bug in Pathfinder-128 dataset
#38
albertfgu
closed
2 years ago
9
Pathfinder task cannot converge.
#37
liuyang148
closed
2 years ago
12
Update requirements.txt
#36
jnhwkim
closed
2 years ago
2
Confusion Regarding Hyperparameters
#35
alexmathfb
opened
2 years ago
20
Different hyper-parameters used for different models in image task.
#34
mlpen
opened
2 years ago
3
Cannot reproduce the results for cifar10
#33
La-SilverLand
closed
2 years ago
1
Script for computing memory consumption
#32
maximzubkov
opened
3 years ago
1
Computing required attention span
#31
yongyi-wu
closed
3 years ago
4
Problem training listops on GPU
#30
renebidart
closed
3 years ago
2
typo in code block in README
#29
dar-tau
closed
2 years ago
9
jax report that "No GPU/TPU found, falling back to CPU"
#28
La-SilverLand
closed
3 years ago
3
typo in readme code block
#27
dar-tau
opened
3 years ago
2
Linear transformer performance
#26
maximzubkov
closed
3 years ago
3
Text Classification Data
#25
dar-tau
closed
3 years ago
1
Are you interested in publishing to huggingface/datasets ?
#24
richarddwang
opened
3 years ago
4
Linear Transformer code base
#23
maximzubkov
closed
3 years ago
2
validation on IMDB
#22
shawnkx
closed
3 years ago
1
Text Classification Configuration: Paper vs Code
#21
adamsolomou
closed
3 years ago
1
Serious bugs in the ListOps task
#20
cifkao
closed
3 years ago
3
Q's on Performer & Text Classification
#19
Muennighoff
opened
3 years ago
1
extremely high accuracy in document retrieval task
#18
mlpen
closed
3 years ago
4
Hyperparameters of each task to reproduce table 1 in paper
#17
mlpen
closed
3 years ago
5
Configs for Image Classification (cifar10)
#16
keroro824
opened
3 years ago
10
ListOps performance
#15
dido1998
opened
3 years ago
8
Nested Structure in ListOps
#14
adamsolomou
closed
3 years ago
4
Longformer missing in Fig. 3
#13
albusdemens
closed
3 years ago
1
Next