Model quantization is a widely-used technique to optimize the hardware efficiency of deep neural networks.

We note that at the sacrifice ofquality,our method can beused onthebase model ofSDV1.5 and provide some examples in Figure9.

Usingourmethod weestablish anewbenchmark bycalculating the most accurate variational ground state energies ever published for a number of different atoms and molecules. Wesystematically break down and measure our improvements, focusing in particular on the effect of increasing physical prior knowledge.