[moffkalast]

The official ggufs have this in them as an example, I'm even more confused now:

<start_of_turn>user

You are a helpful assistant

Hello<end_of_turn>

<start_of_turn>model

Hi there<end_of_turn>

<start_of_turn>user

How are you?<end_of_turn>

<start_of_turn>model

[hnfong]

I was confused by this too, but now I think they’re just suggesting to prepend the system prompt to the first user prompt.

I think the ggufs took the chat template defined in tokenizer_config.json , which basically does that.