The best way to deploy UMT5 variants into production with low-latency inference?
#4 opened about 1 month ago
by
Respair
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6467e44e696e7355f5d710b6/S_cznk3P4i3YIrrBd0J5j.jpeg)
Add a Better Transformer api ?
2
#3 opened 12 months ago
by
1TuanPham
![](https://cdn-avatars.huggingface.co/v1/production/uploads/63905e87df447b438817b2cd/FCGw__3629-LgE0fpAwj2.jpeg)
Adding `safetensors` variant of this model
#2 opened about 1 year ago
by
SFconvertbot
![](https://cdn-avatars.huggingface.co/v1/production/uploads/635fd4cc14657fb8cff2a081/GDkyDwAcuqDBpaOvQgJuq.png)
bug? example of usage?
4
#1 opened about 1 year ago
by
vasilee