Prompting
Two special tokens are used to mark the beginning of user and assistant turns:
<|prompter|>
and <|assistant|>
. Each turn ends with a '</s>' token.
Input prompt example:
<|prompter|>Mikä on meemi ja mikä on tämän sanan historia?</s><|assistant|>
The input ends with the <|assistant|>
token to signal that the model should
start generating the assistant reply.