Output is short

Prompting
1

So i was using the Curie model to write Product Descriptions, but the output that is generated is short and doesn’t fill up the token quota that I was given in the settings.
I am using the following settings-
Response Length - 120 ( Output generated comes in around 80-90 tokens , sometimes even less)
Temp - 0.80
Top P - 1
Frequency Penalty - 0.15
Presence Penalty - 0.03

Please help, I’ve been stuck at this for a long time .
Thank you

2

Have you tried using Curie instruct or Davinci Instruct? They supposedly understand what you want more (I am experiencing difficulty using them, but maybe you won’t). You have to make sure too your prompt is understandable by them

Here’s a link to understand them: Engines - OpenAI API