Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
msj19
/
gated_deltaproduct
like
0
Safetensors
gated_deltaproduct
arxiv:
2409.07146
arxiv:
2404.06395
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
gated_deltaproduct
/
fla3
/
modules
447 kB
Ctrl+K
Ctrl+K
1 contributor
History:
1 commit
msj19
Add files using upload-large-folder tool
0a2b89e
verified
4 months ago
__pycache__
Add files using upload-large-folder tool
4 months ago
__init__.py
1.41 kB
Add files using upload-large-folder tool
4 months ago
activations.py
12.6 kB
Add files using upload-large-folder tool
4 months ago
convolution.py
15.1 kB
Add files using upload-large-folder tool
4 months ago
feature_map.py
8.97 kB
Add files using upload-large-folder tool
4 months ago
fused_bitlinear.py
20.8 kB
Add files using upload-large-folder tool
4 months ago
fused_cross_entropy.py
15.5 kB
Add files using upload-large-folder tool
4 months ago
fused_kl_div.py
9.83 kB
Add files using upload-large-folder tool
4 months ago
fused_linear_cross_entropy.py
20.2 kB
Add files using upload-large-folder tool
4 months ago
fused_norm_gate.py
39.9 kB
Add files using upload-large-folder tool
4 months ago
grpo.py
15.8 kB
Add files using upload-large-folder tool
4 months ago
l2norm.py
6.74 kB
Add files using upload-large-folder tool
4 months ago
layernorm.py
45.1 kB
Add files using upload-large-folder tool
4 months ago
layernorm_gated.py
18.2 kB
Add files using upload-large-folder tool
4 months ago
mlp.py
4.78 kB
Add files using upload-large-folder tool
4 months ago
parallel.py
1.19 kB
Add files using upload-large-folder tool
4 months ago
rotary.py
18.2 kB
Add files using upload-large-folder tool
4 months ago
token_shift.py
6.05 kB
Add files using upload-large-folder tool
4 months ago
