• search
    search
  • reviewers
    reviewers
  • feeds
    feeds
  • assignments
    assignments
  • settings
  • logout

ZeroQuant(4+2): Redefining LLMs Quantization with a New FP6-Centric Strategy for Diverse Generative Tasks.

Xiaoxia WuHaojun XiaStephen YounZhen ZhengShiyang ChenArash BakhtiariMichael WyattReza Yazdani AminabadiYuxiong HeOlatunji RuwaseLeon SongZhewei Yao
Published in: CoRR (2023)
Keyphrases
  • search strategy
  • wide variety
  • multiscale
  • generative model
  • data sets
  • neural network
  • genetic algorithm
  • learning algorithm
  • information systems
  • selection strategy
  • multiple tasks