I’ve playing with a lot of models around 7B but I’m now prototyping something that would be fine with a 1B model I think, but there’s just Phi-1.5 that I’ve seen of this size, and I haven’t seen a way to run it efficiently so far. llama.cpp has still not implemented it for instance.

Anyone has an idea of what to use?

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

    RWKV 1.5B, its Sota for its size, outperforms tinyLlama, and uses no extra vram for fitting its whole ctx len in browser.