Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Character-level language modeling on text8 (dev)
Loading...
1.01
BPC
Transformer + adaptive span
1.008
1.0215
1.035
1.0485
May 19, 2019
Sep 25, 2019
Feb 2, 2020
Jun 11, 2020
Oct 18, 2020
Feb 25, 2021
Jul 5, 2021
BPC
Updated 4d ago
Evaluation Results
Method
Method
Links
BPC
Transformer + adaptive span
#Params=209M, Model sc...
2019.07
1.01
Adaptive-Span
Model Category=Large,...
2019.05
1.01
All-attention network + adaptive span
#Params=114M, Model sc...
2019.07
1.02
Transformer-LS
#Param=44M
2021.07
1.03
Longformer
#Param=41M
2020.04
1.04
Longformer
#Param=41M
2021.07
1.04
Transformer + adaptive span
#Params=38M, Model sca...
2019.07
1.05
All-attention network + adaptive span
#Params=38M, Model sca...
2019.07
1.05
Adaptive-Span
Model Category=Small,...
2019.05
1.05
Adaptive
#Param=38M
2020.04
1.05
Adaptive
#Param=38M
2021.07
1.05
T64
#Params=235M, Model sc...
2019.07
1.06
T64
Model Category=Large,...
2019.05
1.06
Feedback
Search any
task
Search any
task