So I've read the PTQ and QAT for Classification README and I found about QuantDescriptor
I want to use PTQ_and_QAT_for_classification.ipynb file to produce vary quantized model with custom precision (4-bit, 8-bit, 16-bit). On what file I should declare the num_bits of QuantDescriptor's args so I can produce the quantized model?
💡 Your Question
Dear Author @BloodAxe
So I've read the PTQ and QAT for Classification README and I found about QuantDescriptor![image](https://github.com/Deci-AI/super-gradients/assets/79700580/071674fb-4602-49d3-a302-7b2f4f57bf9a)
I want to use PTQ_and_QAT_for_classification.ipynb file to produce vary quantized model with custom precision (4-bit, 8-bit, 16-bit). On what file I should declare the num_bits of QuantDescriptor's args so I can produce the quantized model?
Thank you
Versions
No response