Re:Towards 1-bit Machine Learning Models
by quentinp on Friday March 29, 2024 @01:28PM
(#39866712)
Actually they plan to put an LLM in your back pocket using flash memory, not silicon: https://arxiv.org/abs/2312.11514
[ Parent
| on HN ]
Re:Towards 1-bit Machine Learning Models
by declaredapple on Friday March 29, 2024 @01:49PM
(#39866942)
The flash doesn't do the computations though, that's just a method of getting it to the processor