I want an OpenAI model (via API) to faithfully continue a generation that I have in mind.
For example:
User: “What’s your favorite food?”
Assistant Prefix (provided by me): “Cake! The reason why is because”
and then have the model continue generating " I like how it tastes!" (or whatever it might choose to complete the generation with).
Analogously, if I were “raw prompting,” I’d like to do something like
p = “”“<BOS_TOKEN><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|USER_TOKEN|>What’s your favorite food?<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>It’s Cake! The reason why is because”“”
Vaguely similarly, Claude has an ability to “prefill” the generation, which seems perhaps like what I’m looking for <Google “Prefill Claude Response”>
Does a similar feature exist for the OpenAI API (either a raw prompting ability or a generation prefill feature)?
I’m not looking for some hacky prompting solution. This is for a benchmark that I’m trying to work on 
. Thanks!
