Awesome model, can't get the prompt template right
#12 opened about 1 month ago
by
ben-epstein
Speed up
2
#11 opened 4 months ago
by
cute69
You seem to have forgotten to update some of the Quants
#9 opened 4 months ago
by
Mikael110
cpu vs gpu
#8 opened 4 months ago
by
francescofiamingo
Will it work with ooba?
2
#5 opened 4 months ago
by
lhucklen
Q6_K response quality diverges (in a bad way)
34
#4 opened 4 months ago
by
thethinkmachine
gemma 9b with llama cpp b3259
1
#3 opened 4 months ago
by
sdyy