Picture for Vivek Menon

Vivek Menon

Efficient 8-Bit Quantization of Transformer Neural Machine Language Translation Model

Add code
Jun 07, 2019
Figure 1 for Efficient 8-Bit Quantization of Transformer Neural Machine Language Translation Model
Figure 2 for Efficient 8-Bit Quantization of Transformer Neural Machine Language Translation Model
Figure 3 for Efficient 8-Bit Quantization of Transformer Neural Machine Language Translation Model
Figure 4 for Efficient 8-Bit Quantization of Transformer Neural Machine Language Translation Model
Viaarxiv icon