Is it possible to convert or quantize fp32 onnx file to fp16, int8 dlc file with snpe or qnn binary program?
I already succeeded converting llama2-7b-fp32 to llama2-7b-ufxp8, however, I want to convert llama2-7b-fp32 to fp16 or int8, not unsigned fixed point(uFxp 8 or 16). Is it possible?
Opinions expressed in the content posted here are the personal opinions of the original authors, and do not necessarily reflect those of Qualcomm Incorporated or its subsidiaries (“Qualcomm”). The content is provided for informational purposes only and is not meant to be an endorsement or representation by Qualcomm or any other party. This site may also provide links or references to non-Qualcomm sites and resources. Qualcomm makes no representations, warranties, or other commitments whatsoever about any non-Qualcomm sites or third-party resources that may be referenced, accessible from, or linked to this site.
