• Brcht@lemmy.world
    link
    fedilink
    English
    arrow-up
    0
    ·
    10 months ago

    I have tried the version available at hugginchat and it’s almost gpt4 level for programming tasks but not so much for general knowledge

    • bassomitron@lemmy.world
      link
      fedilink
      English
      arrow-up
      0
      ·
      10 months ago

      Do you know if there are any plans to quantize it? I’d love to test it, but my 3090 can’t handle 70b models without quantization, unfortunately.

      • midnight@kbin.social
        link
        fedilink
        arrow-up
        0
        ·
        10 months ago

        There are quantized versions on hugging face. There’s a q2 version, but idk how well that performs

      • ffhein@lemmy.world
        link
        fedilink
        English
        arrow-up
        0
        ·
        10 months ago

        Only quantized versions of the model were leaked. If you see any unquantized version of it then it’s something which was recreated from these, and not the original model. People have also requanted it from GGUF to EXL2 and probably other formats too.

      • theneverfox@pawb.social
        link
        fedilink
        English
        arrow-up
        0
        ·
        10 months ago

        I’ve had reasonably good results with deepseek 6.7b

        It struggles and hallucinates once you get into more niche languages, but it’ll spit out a snake in Python or write file io functions pretty well - I’ve used it to read/write huge json in a buffer with good results.

        I haven’t tried gpt4, but compared to 3.5 it’s pretty great

      • Brcht@lemmy.world
        link
        fedilink
        English
        arrow-up
        0
        ·
        10 months ago

        I have gpt4 with copilot at work so i mostly use that, it is pretty good for programming, you see its limitations when you start relying on it a lot on autocompletions, maybe because the code itself is not too coherent and gpt gets confused

        Maybe chat tasks are simpler because it writes the whole thing from scratch, though I mostly ask it for limited functionalities, eg write a function that takes x and returns y or use a certain ORM to change a value.

        I would suggest you try both gpt 3.5 and the free huggingface minstral 7b version (you can probably run it on pc too, it’s not huge) for programming tasks and see for yourself. For general knowledge though, gpt wins hands down over minsral 7b