You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I'm, trying to emulate a playground consuming the server.cpp api but I am having problems.
When I submit a prompt, in conjunction with the "as_loop" attribute to make it do a stream, I get the result token by token, but after try to stop the inference the next-token?stop=true with a GET petition and resend with POST new params and prompt, it continues to complete the previous one ignoring the new prompt.
I would like to know if you could solve this doubt, what exacly do the next-token?stop=true and how can i use it or about how to use it correctly, what detail I may be omitting.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Hello! I hope you are fine.
I'm, trying to emulate a playground consuming the server.cpp api but I am having problems.
When I submit a prompt, in conjunction with the "as_loop" attribute to make it do a stream, I get the result token by token, but after try to stop the inference the next-token?stop=true with a GET petition and resend with POST new params and prompt, it continues to complete the previous one ignoring the new prompt.
I would like to know if you could solve this doubt, what exacly do the next-token?stop=true and how can i use it or about how to use it correctly, what detail I may be omitting.
Beta Was this translation helpful? Give feedback.
All reactions