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.
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.
arxiv.org /abs/2402.17764
You're viewing a single thread.
4
comments
Why use lot bit when one bit do trick?
Bits together weak