I am running a LLaMa 13B instance (via GPT4all) and am finding inference times to be quite slow, especially for summarization. Does anyone have recommendations for models that can do summarization of 4k+ tokens extremely quickly?

  • ttkciarB
    link
    fedilink
    English
    arrow-up
    1
    ·
    1 year ago

    orca-mini-3b is good at fast summarizations, but it lies a lot, so ymmv.