alt Hacker NewsAnyone seen a low-friction way to run prompts through this yet, either via a hosted API or chat UI or a convenient GGML or MLX build that runs in Ollama or llama.cpp or LM Studio?
Replies
t1amat • yesterday at 4:29 PM
Not a direct answer but it looks like v0.5 is a nanoGPT arch and v1 is a Phi 1.5 arch, which should be well supported by quanting utilities for any engine. They are small too and should be able to be done on a potato.
alansaber • yesterday at 4:54 PM
I too have completely forgotten how the adapters library works and would have appreciated a simple inference script
Currently running it using LM Studio. It can download it from Hugging Face. It generates incoherent text though
===
You:
I pray you, who is this Master Newton?
timecapsulellm-v2-1800-1875-mlx:
TI offer to pay you the very same fee as you did before. It was not in the power of your master to deliver the letter to your master. He did. I will be with you as soon as I can keep my word. It is not at all clear, whether the letter has been sent or not. It is not at all clear: but it is clear also that it was written by the person who gave it. "No," I said, "I cannot give it to you." There, the letter was sent to me. "The letter is yours, I believe," I said. "But, I hope, you will not refuse to give it to me?