TemporalMesh Transformer: 29.4 PPL at 48% compute — beats Mamba, new open-source architecture
#3 opened about 1 month ago
by 
vigneshwar234
Context Length for 2X6000 Pros (2x96 = 192GB VRAM)
5
#2 opened 3 months ago
by 
mtcl
licence?
1
#1 opened 3 months ago
by 
celikburak