Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling. (arXiv:2304.09145v3 [cs.CL] UPDATED) Show more
http://arxiv.org/abs/2304.09145 #arXiv #NLProc
QOTO: Question Others to Teach Ourselves An inclusive, Academic Freedom, instance All cultures welcome. Hate speech and harassment strictly forbidden.