Adding `safetensors` variant of this model
#5 opened 12 days ago
by
SFconvertbot
generating extremely slow, compared to 4k length model
2
#4 opened 7 months ago
by
CHNtentes
Run with full 128k context in 24G vram
#3 opened 7 months ago
by
meigami
Adding `safetensors` variant of this model
#1 opened 7 months ago
by
SFconvertbot