quant tests: clean up logs about incorrect tensor copy (#70106)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/70106
Some of quantization tests had log spew like
```
UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
```
This PR cleans up the root cause from the utils. Some other
tests may still hit this warning from other places
Test Plan:
```
python test/test_quantization.py TestFakeQuantizeOps
```
this particular warning no longer appears
Reviewed By: soulitzer
Differential Revision: D33187925
Pulled By: vkuzo
fbshipit-source-id: bd1acd77fd72a10dad0c254f9f9f32e513c8a89a