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

    I used it and was not impressed… I found Wizard LM to be far superior.

    Also, I agree with @wagesj45 up there about training other models… but how would they detect that you’re training other models with it? I think one of the best things you can do with a large model is to train a small specialist model.

    • ylaiOP
      link
      fedilink
      English
      arrow-up
      1
      ·
      edit-2
      1 year ago

      Well, WizardLM is an instruction evolution method, and not particular the underlying foundational model, like either LLaMA 1 vs. 2. And WizardLM themselves have clearly hopped onto the LLaMA 2 bandwagon, which has been out since yesterday: https://huggingface.co/WizardLM/WizardLM-13B-V1.2