Just be aware you don't get to use all of it. I believe you only get access to
~20.8GB of GPU memory on a 32GB Apple Silicon Mac, and perhaps something like ~48GB on a 64GB Mac. I think there are some options to reconfigure the balance but they are technical and do not come without risk.
Great stuff - and training was so cheap too - it would have cost less than $200 on Runpod, and half that price on spot instances.
I guess it's time languages other than Python, especially niche ones, started collating their own language specific datasets.
Personally, I daydream about an Elixir specific LLM I could run locally, trained or fine tuned to respond in an idiomatic fashion, and plug into a tool like Cursor.so.
Are there any examples of the internal dataset used in the 80K instruction / answer pairs Phind used to tune this?
With the prevalence of Wayland, I don't think it's correct to say that most Linux users will never encounter problems with NVIDIA. Things have improved recently but Intel and AMD are still way ahead when it comes to that.
Where it says "Thought for 20 seconds" - you can click the Chevron to expand it and see what I guess is the entire chain of thought.