Promising stuff from their repo, claiming “exceptional performance, achieving a [HumanEval] pass@1 score of 57.3, surpassing the open-source SOTA by approximately 20 points.”

https://github.com/nlpxucan/WizardLM

  • notfromhere@lemmy.one
    link
    fedilink
    English
    arrow-up
    4
    ·
    1 year ago

    From the Twitter post

    New StarCoder coding model from @WizardLM_AI

    “WizardCoder-15B-v1.0 model achieves 57.3 pass@1 on the HumanEval Benchmarks … 22.3 points higher than the SOTA open-source Code LLMs.”

    My quants: https://huggingface.co/TheBloke/WizardCoder-15B-1.0-GGML https://huggingface.co/TheBloke/WizardCoder-15B-1.0-GPTQ

    Original: huggingface.co WizardLM/WizardCoder-15B-V1.0 · Hugging Face

    11:21 AM · Jun 14, 2023

    • LinuxFanatic@lemmy.world
      link
      fedilink
      English
      arrow-up
      2
      ·
      1 year ago

      On The Bloke’s hugging face repo, it says the GGML quants are not compatible with llama.cpp, anyone know why?

      • Kerfuffle@sh.itjust.works
        link
        fedilink
        English
        arrow-up
        4
        ·
        edit-2
        1 year ago

        It’s a different type of model. llama.cpp only supports LLaMA models while GGML (the machine learning library llama.cpp is based on) has examples of various models with different architectures. WizardCoder, MPT, Bloom, probably very soon Falcon. Also some separate projects use GGML to support other models (including some of the ones I listed). For example the Rust “llm” project can support LLaMA models, MPT, BLOOM.

          • Kerfuffle@sh.itjust.works
            link
            fedilink
            English
            arrow-up
            1
            ·
            1 year ago

            It looks like a frontend that just bundles a bunch of stuff together. Oobabooga’s webui thing is similar: you can run stuff with llama.cpp, GPTQ, etc. What models and features are supported is going to depend on how the frontend manages that stuff. There are also forks of llama.cpp like koboldc++ which may support different models/features/formats (I know koboldc++ supports some older GGML file formats that llama.cpp broke compatibility with).

              • Kerfuffle@sh.itjust.works
                link
                fedilink
                English
                arrow-up
                2
                ·
                1 year ago

                I don’t know if it does or doesn’t, I was just saying those two projects seemed similar: presenting a frontend for running inference on models while the user doesn’t necessarily have to know/care what backend is used.