Add docs

Author: nikita-savelyevv

docs/source/openvino/optimization.mdx

@@ -87,6 +87,8 @@ quantization_config = OVWeightQuantizationConfig(
 )
 ```
 
+Note: `OVWeightQuantizationConfig` also accepts key word arguments not listed in its constructor. In this case such arguments will be passed directly to `nncf.compress_weights()` call. This is useful for passing additional parameters to the quantization algorithm.
+
 By default the quantization scheme will be [asymmetric](https://github.com/openvinotoolkit/nncf/blob/develop/docs/usage/training_time_compression/other_algorithms/LegacyQuantization.md#asymmetric-quantization), to make it [symmetric](https://github.com/openvinotoolkit/nncf/blob/develop/docs/usage/training_time_compression/other_algorithms/LegacyQuantization.md#symmetric-quantization) you can add `sym=True`.
 
 For 4-bit quantization you can also specify the following arguments in the quantization configuration :

optimum/intel/openvino/quantization.py

@@ -1044,6 +1044,7 @@ def _weight_only_quantization(
             f"by the ones given in _weight_only_quantization call kwargs: {kwargs_intersection}."
         )
     wc_kwargs.update(kwargs)
+    wc_kwargs.pop("weight_only", None)
 
     compressed_model = nncf.compress_weights(
         model,
@@ -1076,6 +1077,7 @@ def _full_quantization(
             f"by the ones given in _full_quantization call kwargs: {kwargs_intersection}."
         )
     q_kwargs.update(kwargs)
+    q_kwargs.pop("weight_only", None)
 
     quantized_model = nncf.quantize(model, calibration_dataset=calibration_dataset, **q_kwargs)