neural-compressor
neural-compressor copied to clipboard
Is there any accuracy data related to FP4?
https://github.com/intel/neural-compressor/blob/master/docs/source/validated_model_list.md/#pytorch-models-with-torch-201cpu-in-woq-mode shows the accuracy of int4 compared to fp32. Is there any data about 4-bit floating point numbers (e.g. nf4, fp4, etc.) and their performance data?
THANKS