Slacker News Slacker News logo featuring a lazy sloth with a folded newspaper hat
  • top
  • new
  • show
  • ask
  • jobs
Library
← Back to context

Comment by wanderingmind

10 days ago

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?

1 comment

wanderingmind

Reply

mdp2021  9 days ago

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.)

Slacker News

Product

  • API Reference
  • Hacker News RSS
  • Source on GitHub

Community

  • Support Ukraine
  • Equal Justice Initiative
  • GiveWell Charities