TemporalMesh Transformer: dynamic kNN graph attention + adaptive exit gates, 29.4 PPL at 48% compute
#4 opened 25 days ago
by 
vigneshwar234
Adds tags for discoverability and code snippets
#3 opened almost 2 years ago
by 
Wauplin
Error importing the pre-trained model
1
#2 opened over 2 years ago
by 
poomchantara
Adding `safetensors` variant of this model
🤗 1
#1 opened over 2 years ago
by 
SFconvertbot