WizardLM-2-7B get's cut off while writing.

ggerganov / llama.cpp

LLM inference in C/C++

MIT License

61.24k stars 8.75k forks source link

WizardLM-2-7B get's cut off while writing. #7501

Open 0wwafa opened 1 month ago

0wwafa commented 1 month ago

WizardLM-2-7B is a very talkative chatbot... give extensive answers. Unfortunately I didn't find any way to make it sto before being cut of (whay does that happen?)

Any idea?

arnfaldur commented 1 month ago

It's unreasonably hard to help you with the limited information you've provided.

To increase the chance of receiving help you should write about what you have done to reach this point and show how the issue manifests. Which commands you're running. Which build of llama.cpp you're using.

You should also probably not ignore the issue templates.