lucidrains/h-transformer-1d
Implementation of H-Transformer-1D, Hierarchical Attention for Sequence Learning
PythonMIT
Issues
- 1
error in test
#25 opened by jizhang02 - 0
Billion Word Benchmark - Reproducibility
#24 opened by DavidHerel - 0
- 2
- 2
Approximated values are off
#20 opened by jglaser - 6
Masking not working in training, thanks
#18 opened by junyongyou - 0
Sequence classfication, thanks a lot
#17 opened by junyongyou - 4
Application to sequence classification?
#12 opened by trpstra - 1
- 2
Add Norm Missing
#16 opened by wwx13 - 2
Mask not working
#15 opened by wwx13 - 3
Algorithm Mismatch
#13 opened by jinmang2 - 1
- 4
- 2
One simple question
#10 opened by CiaoHe - 1
- 4
RuntimeError: Tensor type unknown to einops <class 'torch.return_types.max'>
#6 opened by wajihullahbaig - 1
- 1
Sequence length issue when `causal = True`
#8 opened by jaak-s - 3
- 2
- 2
Example in README does not work
#3 opened by jaak-s - 4
H-Transformer for Cross-Attention?
#2 opened by Vbansal21