issues
search
togethercomputer
/
stripedhyena
Repository for StripedHyena, a state-of-the-art beyond Transformer architecture
Apache License 2.0
299
stars
21
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
gradient checkpointing is not implement
#22
xiyang-aads-lilly
opened
1 month ago
0
evo and stripedhyena crash the server when doing a simple inference
#21
sun-qibo
opened
2 months ago
0
flash attention not compatible?
#20
oxPJ
opened
3 months ago
1
Limiting attention radius and extracting embeddings
#19
george-henderson
opened
6 months ago
0
Fine-tuning on a Sequence Classification Task
#18
leannmlindsey
closed
8 months ago
1
add evo to readme
#17
Zymrael
closed
8 months ago
0
chore: extend pypi packaging with setup.py
#16
Zymrael
closed
9 months ago
0
chore: update pyproject to reflect pypi support
#15
Zymrael
closed
9 months ago
0
tokenizer.model file in addition to tokenizer.json
#14
kenneth-miura
opened
9 months ago
0
Remove unnecessary print statement
#13
brianhie
closed
9 months ago
0
Different bias addition
#12
brianhie
closed
9 months ago
0
Handle char level tokenization
#11
brianhie
closed
9 months ago
2
Add code for positional embedding interpolation
#10
brianhie
closed
9 months ago
0
Add option to have gelu activations
#9
brianhie
closed
9 months ago
0
chore: minor style changes
#8
Zymrael
closed
9 months ago
0
fix: flashfftconv imports
#7
stereoplegic
closed
9 months ago
1
add support for linear interpolated rope pos emb in flash attn
#6
exnx
closed
10 months ago
0
Apple Silicon support
#5
amrohendawi
opened
10 months ago
2
fix: fix recurrent prefill
#4
Zymrael
closed
10 months ago
0
import FlashDepthwiseConv1d?
#3
Hambaobao
closed
9 months ago
2
docker build crashes my machine
#2
dustyatx
closed
11 months ago
7
Pretrain
#1
mietekrmd
opened
11 months ago
1