LLaMA-7B in Pure C++ with full Apple Silicon support

Re:LLaMA-7B in Pure C++ with full Apple Silicon support by inawarminister on Saturday March 11, 2023 @04:54AM (#35106946)

There's open-assistant.io, which is doing RLHF directly on the open

[ Parent | on HN ]

Re:LLaMA-7B in Pure C++ with full Apple Silicon support by Taek on Sunday March 12, 2023 @04:02AM (#35117863)

And they've already collected over 100,000 samples, iirc ChatGPT was trained on something like 30,000 samples, so the open models should already be positioned to succeed.

[ Parent | on HN ]