I recently started using the base model of LLaMA-2-70B for creative writing and surprisingly found most of my prompts from ChatGPT actually works for the “base model” too, suggesting it might also be fine tuned a bit on ChatGPT-like instructions.

Curious anyone tried both llama 1 & 2 base model and can share their experiences on creativity ? My hunch is llama 1 might be slightly better at it, assuming it hasn’t go through as much alignment.

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

    I think llama 1 had more interesting training data, but it can’t hold a plot too well

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

    I think it’s best to keep temperature low and feed the randomness in manually. Like generate a list of words and ask it to make an association for each and use those as inspiration for characters, plot, whatever. Or make a list of options for each thing that makes sense and have a model generate Python code to randomly select one of each, and then put those random selections in the prompt.

    Because the temperature being much higher than zero mostly makes it dumber in my experience.

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

      That’s an interesting idea … in my experience anything <1 works, >1.2 goes wild and for things we expect to be a bit more deterministic, setting it to 0 is preferred.

      What’s your best setup and temperature for creative writing ?