TemporalMesh Transformer: 29.4 PPL at 48% compute — beats Mamba, new open-source architecture
#8 opened 1 day ago
by 
vigneshwar234
Chat History
#7 opened over 2 years ago
by 
MLconArtist
Add evaluation results on the amazon config and test split of squadshifts
#4 opened over 3 years ago
by 
autoevaluator