AI RESEARCH
Rethinking 1-bit Optimization Leveraging Pre-trained Large Language Models
arXiv CS.CL
•
ArXi:2508.06974v2 Announce Type: replace 1-bit LLM quantization offers significant advantages in reducing storage and computational costs. However, existing methods typically train 1-bit LLMs from scratch, failing to fully leverage pre-trained models. This results in high