Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

I've read the Gemma 3 technical report, it doesn't mention anything about it in the format section. Did they forget to include that? Where did you find the source that claims otherwise?


Google AI Studio offers no system prompt option for Gemma 3 which also suggests this model doesn't support it...


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


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.


My bad, original comment updated.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: