Hi community,

i am writing my own GUI in wich i want to use a LLM completely local. The problem is i dont know how to start with the LLM.

Can someone explain to me how the first steps work to integrate/work with the LLM or does someone know some good tutorials?

The LLM is downloaded localy. Now i need to integrate a library or something? sry i could not find a lot useful/direct information about the topic.

Thank you very much in advance!

  • CultOfAmagi@alien.topOPB
    link
    fedilink
    English
    arrow-up
    1
    ·
    1 year ago

    Thanks for the comments so far!

    My intention was to learn about LLM and to put that into practice. I am aware of already existing projekts and have something working already. It just feels a bit overloaded or impractical.

    • catzilla_06790@alien.topB
      link
      fedilink
      English
      arrow-up
      1
      ·
      1 year ago

      I wanted to learn about writing an application using LLMs. My goal was to write something that I could load a set of PDFs and ask questions about them., all on my PC.

      I used PySide6 (Qt for Python) for the GUI since I was pretty familiar with Qt and C++, and I’m not a fan or running apps in a browser.

      I used a combination of HuggingFace APIs and Langchain to write the application itself, and ended up with a somewhat generalized application that I could load different models.

      It works, maybe not perfectly, but I did accomplish what I wanted, to learn about implementing an application.

      I did the same thing with Stable Diffusion models, but with just HuggingFace APIs, no Langchain.

    • _Lee_B_@alien.topB
      link
      fedilink
      English
      arrow-up
      1
      ·
      1 year ago

      If you want to learn how to run an llm in inference mode locally, you should code that at the command line, not waste time building a GUI app. Build a GUI app if you want to learn how to build GUI apps, or if you’ve already proven out the engine at the command line, and now need a pretty GUI around it.