Smerity sha-rnn issues - Githubissues

Smerity / sha-rnn

Single Headed Attention RNN - "Stop thinking with your head"

1.18k stars 132 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

README on running the model on jupyter notebooks and Google colab

#18 gitudaniel opened 2 years ago
0
another implementation + partial reproduction

#17 lunixbochs opened 3 years ago
2
Randomly zeroing out hidden and memory during training

#16 alisafaya opened 3 years ago
2
Efficiency claims on attention module used

#15 munael opened 3 years ago
1
LICENSE

#14 searchivarius opened 3 years ago
0
prep_enwik8.py is missing

#13 ischlag closed 4 years ago
1
Redundant parameter "dropoute" in SHARNN __init__()?

#12 GauravIyer closed 4 years ago
0
Results from Adaptive Span Transformer

#11 djstrong closed 4 years ago
2
SplitcrossEntropy

#10 gslaller opened 4 years ago
1
how to control GPU ram usage

#9 jprobichaud opened 4 years ago
7
error happened when new token appears in the valid/test data set

#8 carter54 opened 4 years ago
1
Gradient overflows

#7 stefan-it opened 4 years ago
1
Requirements.txt

#6 LanceNorskog opened 4 years ago
0
Curious about 1-billion corpus perplexity

#5 cmathx opened 4 years ago
0
think about tensorflow？

#4 Crescentz closed 4 years ago
1
Reproduced BPC of 1.077 using model with one attention layer

#3 mkroutikov opened 4 years ago
3
Could you share pretrained model weights?

#2 vhargitai opened 4 years ago
1