Elon Musk
@elonmusk
En réponse à @jam3scampbell
Not that it’s much consolation, but the energy efficiency of LLMs using auto-regressive transformers is extremely bad, not just in training, but also inference.
I think it’s off by several orders of magnitude.
16:42 · 26 août 2023 · 69,9 k vues
82
34
829