Update RunInference documentation

website/www/site/content/en/documentation/sdks/python-machine-learning.md

@@ -34,7 +34,7 @@ For more information, see the [`BatchElements` transform documentation](https://
 
 ### Shared helper class
 
-Instead of loading a model for each thread in the process, we use the `Shared` class, which allows us to load one model that is shared across all threads of each worker in a DoFn. For more information, see the
+Using the `Shared` class within RunInference implementation allows us to load the model only once per process and share it with all DoFn instances created in that process. This feature reduces memory consumption and model loading time. For more information, see the
 [`Shared` class documentation](https://github.com/apache/beam/blob/master/sdks/python/apache_beam/utils/shared.py#L20).
 
 ### Multi-model pipelines
@@ -53,7 +53,7 @@ with pipeline as p:
 ```
 Where `model_handler` is the model handler setup code.
 
-To import models, you need to wrap them around a `ModelHandler` object. Which `ModelHandler` you import depends on the framework and type of data structure that contains the inputs. The following examples show some ModelHandlers that you might want to import.
+To import models, you need to configure a `ModelHandler` object that wraps the underlying model. Which `ModelHandler` you import depends on the framework and type of data structure that contains the inputs. The following examples show some ModelHandlers that you might want to import.
 
 ```
 from apache_beam.ml.inference.sklearn_inference import SklearnModelHandlerNumpy
@@ -171,7 +171,7 @@ In some cases, the `PredictionResults` output might not include the correct pred
 
 The RunInference API currently expects outputs to be an `Iterable[Any]`. Example return types are `Iterable[Tensor]` or `Iterable[Dict[str, Tensor]]`. When RunInference zips the inputs with the predictions, the predictions iterate over the dictionary keys instead of the batch elements. The result is that the key name is preserved but the prediction tensors are discarded. For more information, see the [Pytorch RunInference PredictionResult is a Dict](https://github.com/apache/beam/issues/22240) issue in the Apache Beam GitHub project.
 
-To work with the current RunInference implementation, you can create a wrapper class that overrides the `model(input)` call. In PyTorch, for example, your wrapper would override the `forward()` function and return an output with the appropriate format of `List[Dict[str, torch.Tensor]]`. For more information, see our [HuggingFace language modeling example](https://github.com/apache/beam/blob/master/sdks/python/apache_beam/examples/inference/pytorch_language_modeling.py#L49).
+To work with the current RunInference implementation, you can create a wrapper class that overrides the `model(input)` call. In PyTorch, for example, your wrapper would override the `forward()` function and return an output with the appropriate format of `List[Dict[str, torch.Tensor]]`. For more information, see our [HuggingFace language modeling example](https://github.com/apache/beam/blob/master/sdks/python/apache_beam/examples/inference/pytorch_language_modeling.py#L49) and our [Bert language modeling example](https://github.com/apache/beam/blob/master/sdks/python/apache_beam/examples/inference/pytorch_language_modeling.py).
 
 ### Unable to batch tensor elements