OWQ: Lessons learned from activation outliers for weight quantization in large language models. (arXiv:2306.02272v3 [cs.CL] UPDATED) Show more
http://arxiv.org/abs/2306.02272 #arXiv #NLProc
QOTO: Question Others to Teach Ourselves An inclusive, Academic Freedom, instance All cultures welcome. Hate speech and harassment strictly forbidden.