no code implementations • 31 May 2024 • Simla Burcu Harma, Ayan Chakraborty, Elizaveta Kostenok, Danila Mishin, Dongho Ha, Babak Falsafi, Martin Jaggi, Ming Liu, Yunho Oh, Suvinay Subramanian, Amir Yazdanbakhsh
In addition, through rigorous analysis, we demonstrate that sparsity and quantization are not orthogonal; their interaction can significantly harm model accuracy, with quantization error playing a dominant role in this degradation.
no code implementations • 19 Nov 2022 • Simla Burcu Harma, Ayan Chakraborty, Nicholas Sperry, Babak Falsafi, Martin Jaggi, Yunho Oh
Based on our findings, we propose Accuracy Booster, a mixed-mantissa HBFP technique that uses 4-bit mantissas for over 99% of all arithmetic operations in training and 6-bit mantissas only in the last epoch and first/last layers.
