둔비의 공부공간

https://arxiv.org/abs/2308.10524 Dataset QuantizationState-of-the-art deep neural networks are trained with large amounts (millions or even billions) of data. The expensive computation and memory costs make it difficult to train them on limited hardware resources, especially for recent popular large languagearxiv.org ICCV 2023 Accepted.  일단, 우리가 생각하는 model quantization을 기대하고 논문을 접하면 안된다.그냥 data를..