Running llama.cpp on android just prints out the question

[Shreyas-ITB]

I ran llama.cpp on my android phone which has 8 threads and 8GB of ram in which around 7.16 GB is available, that is more than enough to run the 7B Alpaca model on it. But when i run it, it just repeats the question that i provided to it. I am using the ./examples/chat.sh file. Why does it do that? How do i solve it?

[cmp-nct]

Just guessing: after prompt was processed there can be a noticeable delay until the completions start. Also there are interactive modes that wait for return/enter.

[github-actions[bot]]

This issue was closed because it has been inactive for 14 days since being marked as stale.