Stacking models using keras.layers.Concatenate with different input shapes

I have concatenated two models that uses different inputs. The first model uses input of shape (1, 33). The second model uses a feature set of dimension (1, 1024). I have a mapping function that converts (1, 33) data to (1, 1024). My question is what changes I need to make to make this model work. What is the appropriate way to give test input to this stacked model?