Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
akswelh
/
NEOX
like
0
arxiv:
29 papers
Model card
Files
Files and versions
xet
Community
main
NEOX
/
megatron
871 kB
1 contributor
History:
1 commit
akswelh
Upload 251 files
d90b3a8
verified
about 1 year ago
data
Upload 251 files
about 1 year ago
fused_kernels
Upload 251 files
about 1 year ago
gradient_noise_scale
Upload 251 files
about 1 year ago
model
Upload 251 files
about 1 year ago
mpu
Upload 251 files
about 1 year ago
neox_arguments
Upload 251 files
about 1 year ago
tokenizer
Upload 251 files
about 1 year ago
__init__.py
929 Bytes
Upload 251 files
about 1 year ago
checkpointing.py
17.6 kB
Upload 251 files
about 1 year ago
devutil.py
1.28 kB
Upload 251 files
about 1 year ago
initialize.py
8.58 kB
Upload 251 files
about 1 year ago
learning_rates.py
5.22 kB
Upload 251 files
about 1 year ago
logging.py
16.4 kB
Upload 251 files
about 1 year ago
mup_substitute.py
7.8 kB
Upload 251 files
about 1 year ago
optimizers.py
18.1 kB
Upload 251 files
about 1 year ago
text_generation_utils.py
42.3 kB
Upload 251 files
about 1 year ago
training.py
64.4 kB
Upload 251 files
about 1 year ago
utils.py
17.6 kB
Upload 251 files
about 1 year ago