I am using a code-completion model for my tool I am making for godot (will be open sourced very soon).

Qwen2.5-coder 1.5b though tends to repeat what has already been written, or change it slightly. (See the video)

Is this intentional? I am passing the prefix and suffix correctly to ollama, so it knows where it currently is. I’m also trimming the amount of lines it can see, so the time-to-first-token isn’t too long.

Do you have a recommendation for a better code model, better suited for this?

  • Smorty [she/her]@lemmy.blahaj.zoneOPEnglish
    1·
    2 days ago

    Have a look at the other comments. Sometimes it does fill in the code correctly, even without any prompting! The template specifically has the fill in the middle part in it.

    The ollama site has the template with <fim_prefix> and such.