1-bit LLM performs similarly to full-precision Transformer LLMs with the same model size and training tokens but is much more efficient in terms of latency, memory, throughput, and energy consumption.

☆ Yσɠƚԋσʂ ☆ · 9 months ago

1-bit LLM performs similarly to full-precision Transformer LLMs with the same model size and training tokens but is much more efficient in terms of latency, memory, throughput, and energy consumption.

kevlar21@lemm.ee · 9 months ago

Why use lot bit when one bit do trick?

tubbadu@lemmy.kde.social · 9 months ago

Bits together weak

Q*Bert Reynolds@sh.itjust.works · 9 months ago

Says 1-bit then goes on to describe inputs as -1, 0, or 1. That’s 2-bit. Am I missing something here?

will_a113 · 9 months ago

It’s actually 1.58bits weirdly. The addition of 0 here was the significant change/improvement in this experiment. The paper isn’t too dense and has some decent tables that explain things fairly accessibly.