mdp2021 6 days ago

As many repeated here, it's (generally) not for direct use. It is meant to be a good base for fine-tuning and getting something very fast.

(In theory, if you fine-tuned Gemma3:270M over "templating cold calls to leads" it would become better than Qwen and faster.)

▲

wanderingmind 6 days ago | parent [-]

Why should we start fine tuning gemma when it is so bad. Why not instead focus the fine-tuning efforts on Qwen, when it starts off with much, much better outputs?

	▲	mdp2021 6 days ago \| parent [-]
		Speed critical applications, I suppose. Have you compared the speeds? (I did. I won't give you number (which I cannot remember precisely), but Gemma was much faster. So, it will depend on the application.)