Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Ro, Yeonju"'
Autoregressive Large Language Models (e.g., LLaMa, GPTs) are omnipresent achieving remarkable success in language understanding and generation. However, such impressive capability typically comes with a substantial model size, which presents signific
Externí odkaz:
http://arxiv.org/abs/2404.03865
Autor:
Kim, Byeongwook, Lee, Dongsoo, Ro, Yeonju, Jeon, Yongkweon, Kwon, Se Jung, Park, Baeseong, Oh, Daehwan
Various post-training uniform quantization methods have usually been studied based on convex optimization. As a result, most previous ones rely on the quantization error minimization and/or quadratic approximations. Such approaches are computationall
Externí odkaz:
http://arxiv.org/abs/2105.01868