NO-CODE Llama 3 Fine Tuning (Train AND Deploy) w/ Google Tech

Поделиться
HTML-код
  • Опубликовано: 11 ноя 2024

Комментарии • 2

  • @draganpetrov9594
    @draganpetrov9594 3 месяца назад

    How does the google vortex charges for deployment of a fine tuned model? Is it per usage or always on?

    • @nodematic
      @nodematic  3 месяца назад

      It's charged by hour, "always on" style. So, you should deploy+undeploy if you are only using the API during certain periods.