There are lots of general-purpose models to use locally, and also coding-specific models.

But are there models specialized in one programming language? My thought was that a model that only needs to handle one language (e.g. Python) could be faster, or be better for a given size.

E.g If I need to code in Rust and is limited to an 8B model to run locally, I was hoping to get better results with a model that is narrower. I don’t need it to be able to help with Java.

This approach would of course require switching models, but that’s no problem for me.

  • Yomope@lemmy.mlEnglish
    41·
    8 months ago

    I’m pretty sure this would not produce better output. Ai has a « thought » of his own.limiting is approach to be pure python won’t offer you the link it can see with a Java approach. With a more diverse knowledge, it can generate a more unique output. Not forcing it to be readable by human may give a more efficient solution. Kinda like compiled code.

    • Oisteink@feddit.nlEnglish
      2·
      8 months ago

      I’d say it depends. Some patterns will be different. Like trying to create zig code when the LLM is trained mostly on javascript and python.

    • robsteranium@lemmy.worldEnglish
      2·
      3 months ago

      You can still leverage knowledge from a foundation model in a smaller fine-tuned one.

      So the model might have learned general OOP principles from Java but it then drops redundant parameters about specific conventions like AbstractFactoryBuilders when it specialises on a language like Python which has no notion of Interfaces.

      Likewise real world knowledge might help distinguish between accounting and database transactions when writing a banking application but you don’t necessarily need your coding assistant to have memorised all the world cup winners since 1966.

      These models are unwieldy so I think it makes a lot of sense to try and find ones that are tuned efficiently.