Investigate load state_dict vs loading whole model

Loading pytorch model as whole has some issues with pickling. Investigate it with running some experiments. If the model size is too large, the current implementation of the RunInference for PyTorch would fail because of memory limits.

1. We can pass the model class to the `load_model` of PyTorchModelLoader and load the model there. This wouldn't pickle the model object but would pickle the class and the model would be instantiated on the workers.