How cloud I convert a quantized model into a lossy model of float32?

quantization
1

Given a quantized model (PTQ or QAT), I want to convert it into a model whose parameters representation is float32. Because I want to use GPU. How cloud I achieve it?

2

you mean “dequantize” a model? interesting, I don’t think we support that. Why don’t you use the original floating point model in this case?

3

Thank you for your suggestion. Actually, I want to perform experiments on quantized model. For some reason, the quantized model does not support GPU, which makes the experiment pretty slow.

4

maybe you can try [quantization] Frequently Asked Questions to see if this works for you or not

5

Thank you very much.