Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
barpitf
/
RAT
like
2
HuggingFaceFW/fineweb-edu
English
RAT
efficient architecture
recurrence
attention
pretraining
arxiv:
2507.04416
License:
mit
Model card
Files
Files and versions
xet
Community
main
RAT
/
ratl16.pth
Commit History
[ckpt]
d18f6f7
wimh966
commited on
25 days ago