Prompt instructions are not very clear
#127
by
chateaux
- opened
I just want to say, the documentation is not very good between the endpoints and transformers etc.
It is not clear at all how to achieve certain results, for example how to avoid the model repeating the prompt in its response. And there are different forms of examples being provided.
I think this really illustrates the problems in this sector in terms of communicating
chateaux
changed discussion title from
Prompt instructions are terrible
to Prompt instructions are not very clear
Can you share what you tried? I'd be happy to help you figure out what you want