Alpaca demo suspended

They just shut down the demo and I don't have the hardware to run it. Any public instances?

  1. 1 week ago
    Anonymous

    why?

  2. 1 week ago
    Anonymous

    I'm sad guys. Every time I go online people are mean to me. Insult me and stuff. And same in person.

    • 1 week ago
      Anonymous

      Or ignored. Urgh. Nobody ever cared about me. Goodbye everyone

    • 1 week ago
      Anonymous

      do you like anime

      • 1 week ago
        Anonymous

        No

        • 1 week ago
          Anonymous

          then it's deserved

          • 1 week ago
            Anonymous

            You would have said that regardless, so I said the opposite just to prove to myself my point

            • 1 week ago
              Anonymous

              no, i would have offered my friendship if you said you did, but that bridge is burned now
              gth anime hater

              • 1 week ago
                Anonymous

                My feelings are hurt and my hope is lost.

              • 1 week ago
                Anonymous

                you shouldn't have used somebody's good intentions as means of self deprecation
                BUT supposing that you were indeed saying the opposite, you surely could name your favorite 2hu right

  3. 1 week ago
    Anonymous

    Alpaca.cpp? It requires a computer with a CPU and RAM. Not particularly much of either.

    • 1 week ago
      Anonymous

      im poor

    • 1 week ago
      Anonymous

      Which cpu should I buy for it then? I don't need light speed responses but not too slow either?

    • 1 week ago
      Anonymous

      with 8 core / 16 threads ayymd cpu and 16 gb ram you will get ~250 ms per token.
      and that's for 13B model.

      • 1 week ago
        Anonymous

        >~250 ms per token.
        What's that in wpm?

        • 1 week ago
          Anonymous

          About 180.

      • 1 week ago
        Anonymous

        Whats the time per tokem in a 3050?

  4. 1 week ago
    Anonymous

    You can train the Lora's with low end GPUs. Pro tip: use hate speech prompt dataset.

  5. 1 week ago
    Anonymous

    There's a colab.

    • 1 week ago
      Anonymous

      link?

    • 1 week ago
      Anonymous

      You are probably thinking of alpaca-lora, which is not made by the stanford team. It also is probably worse in quality, from what I've seen.

Your email address will not be published. Required fields are marked *