Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
akswelh
/
NEOX
like
0
arxiv:
29 papers
Model card
Files
Files and versions
Community
d90b3a8
NEOX
/
megatron
/
model
1 contributor
History:
1 commit
akswelh
Upload 251 files
d90b3a8
verified
30 days ago
mamba
Upload 251 files
30 days ago
rwkv
Upload 251 files
30 days ago
__init__.py
951 Bytes
Upload 251 files
30 days ago
activations.py
4.31 kB
Upload 251 files
30 days ago
fused_bias_dropout.py
1.87 kB
Upload 251 files
30 days ago
fused_layer_norm.py
8.66 kB
Upload 251 files
30 days ago
fused_rope.py
4.96 kB
Upload 251 files
30 days ago
fused_softmax.py
6.99 kB
Upload 251 files
30 days ago
gmlp.py
5.09 kB
Upload 251 files
30 days ago
gpt2_model.py
16.5 kB
Upload 251 files
30 days ago
init_functions.py
7.67 kB
Upload 251 files
30 days ago
megablocks_utils.py
842 Bytes
Upload 251 files
30 days ago
norms.py
3.49 kB
Upload 251 files
30 days ago
positional_embeddings.py
10.2 kB
Upload 251 files
30 days ago
transformer.py
52.1 kB
Upload 251 files
30 days ago
transformer_engine.py
3.05 kB
Upload 251 files
30 days ago
utils.py
15.8 kB
Upload 251 files
30 days ago
word_embeddings.py
10.1 kB
Upload 251 files
30 days ago
