Downloads · 30 days
75
3% of all-time downloads
uw-madison/nystromformer-1024
nystromformer-1024 is a fill-mask model from uw-madison. Use it when you need the model to fill a missing word. It is set up for transformers.
Nystromformer for sequence length 1024 trained on WikiText-103 v1 for 150 epochs.
Downloads · 30 days
75
3% of all-time downloads
All-time downloads
2.7K
Public
Repo size
877 MB
Likes
0
Public
Click a slice to open those files.
.bin438 MB · 99%
From the Hugging Face model README
Nystromformer for sequence length 1024 trained on WikiText-103 v1 for 150 epochs.