News for hackers. Stuff that matters.
Re:Show HN: Explore large language models on any computer wi... by btdmaster on Saturday June 17, 2023 @05:29PM (#36374840)
Really cool, I didn't know CPU/traditional RAM was enough already.

Though, surprising results from repl.it: lm.classify("unabridged", "positive", "negative")=="unabridged is"

Re:Show HN: Explore large language models on any computer wi... by jncraton on Saturday June 17, 2023 @06:43PM (#36375488)
Thanks for pointing that out. Classification is half-baked at the moment. It should ultimately be restricting output to only appropriate labels, but right now it is simply sampling.