repeating the answers infinity.
#2
by
eramax
- opened
The Model Q4_K_M is repeating the answers infinity.
Best
The chat template is likely incorrect. Are you using ollama? It does its own thing. LM Studio interprets the template that is baked into the GGUF. Can you get the same quant to work in LM Studio?
yes I am using ollama,
I will use the template you published