I have experience in running servers, but I would like to know if it’s possible to do it, I just need a GPT 3.5 like private LLM running.

  • TheBigBrother@lemmy.worldOPEnglish
    16·
    1 month ago

    Yeah, I did see something related to what you mentioned and I was quite interested. What about quantized models?

    • entropicdrift@lemmy.sdf.orgEnglish
      3·
      1 month ago

      Quantized with more parameters is generally better than floating point with fewer parameters. If you can squeeze a 14b parameter model down to a 4-bit int quantization it’ll still generally outperform a 16-bit Floating Point 7b parameter equivalent.

      • TheBigBrother@lemmy.worldOPEnglish
        29·
        1 month ago

        Interesting information mate, I’m documenting myself into the subject, thx for the help 👍👍

    • MasterNerd@lemm.eeEnglish
      31·
      1 month ago

      I don’t have any experience with them honestly so I can’t help you there