add `modules_in_block_to_quantize` arg for gptq (#1585)
* add inside_layer_modules
* fix typing
* add test
* fix style
* remove print
* change naming
* fix docstring
* fix
* Update optimum/gptq/quantizer.py
Co-authored-by: fxmarty <9808326+fxmarty@users.noreply.github.com>
* change name again with felix suggestion
* fix log
* style
* remove print
---------
Co-authored-by: fxmarty <9808326+fxmarty@users.noreply.github.com>
