jkim96/GLM-4.7-DASHQ-INT2-g32
074
Add DASH-Q remote-code inference (Triton decode kernel)
Add DASH-Q remote-code inference (Triton decode kernel)
Add DASH-Q remote-code inference (Triton decode kernel)
Add DASH-Q remote-code inference (Triton decode kernel)
Add DASH-Q remote-code inference (Triton decode kernel)
Add DASH-Q remote-code inference (Triton decode kernel)
Standardize model card (DASH-Q)
Upload DASH-Q INT2-g32 checkpoint (zero-shot avg 72.83, wikitext2 ppl 7.95)
initial commit
