News for hackers. Stuff that matters.

A comment on Fine tune LLAMA3 on million scale dataset in consumer GPU using QLora, DeepSpeed. Parent comment

Re:Fine tune LLAMA3 on million scale dataset in consumer GPU... by jackblemming on Thursday April 25, 2024 @01:47AM (#40153887)
Most of the entire field of machine learning is “try shit and see what works”. So it seems like they’re par for the course.
[ Parent | on HN ]
Re:Fine tune LLAMA3 on million scale dataset in consumer GPU... by v3ss0n on Thursday April 25, 2024 @04:10AM (#40154794)
Same as software engineering field too.
[ Parent | on HN ]
Re:Fine tune LLAMA3 on million scale dataset in consumer GPU... by littlestymaar on Thursday April 25, 2024 @05:08AM (#40155174)
It's even worse for AI given that nobody really understands why anything works.
[ Parent | on HN ]
Re:Fine tune LLAMA3 on million scale dataset in consumer GPU... by sinuhe69 on Thursday April 25, 2024 @05:14AM (#40155208)
I wonder what we don’t understand from the SE POV?
[ Parent | on HN ]