AI 뉴스

A Gentle Introduction to 8-bit Matrix Multiplication for transformers at scale using transformers, accelerate and bitsandbytes

2022년 08월 17일 00:00 조회 11

A Gentle Introduction to 8-bit Matrix Multiplication for transformers at scale using transformers, accelerate and bitsandbytes

원문: https://huggingface.co/blog/hf-bitsandbytes-integration