Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
chatsd
/
Sparse_Dynamic_MOE
like
0
Text Generation
PyTorch
custom
mixture-of-experts
Mixture of Experts
transformer
language-model
conditional-computation
arxiv:
2403.07652
License:
mit
Model card
Files
Files and versions
xet
Community
main
Sparse_Dynamic_MOE
1.86 GB
1 contributor
History:
11 commits
chatsd
Rename final (1).pt to sparse_moe_final.pt
2e2e04e
verified
5 days ago
.gitattributes
1.58 kB
Rename dynamic_MOE_final_checkpoint.pt to dynamic_MOE_finalpt
5 days ago
README.md
3.12 kB
Update README.md
5 days ago
dynamic_MOE_finalpt
476 MB
xet
Rename dynamic_MOE_final_checkpoint.pt to dynamic_MOE_finalpt
5 days ago
dynamic_moe_config.json
1.33 kB
Config Files
5 days ago
sparse_moe_config.json
1.23 kB
Config Files
5 days ago
sparse_moe_final.pt
pickle
Detected Pickle imports (3)
"torch.FloatStorage"
,
"torch._utils._rebuild_tensor_v2"
,
"collections.OrderedDict"
What is a pickle import?
1.38 GB
xet
Rename final (1).pt to sparse_moe_final.pt
5 days ago