Elon Musk
@elonmusk
Ответ на @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 августа 2023 г. · 69,9 тыс. просмотров
82
34
829