PR #17974: [keras/models] Standardise docstring usage of "Default to"

Imported from GitHub PR #17974

This is one of many PRs. Discussion + request to split into multiple PRs @ #17748
Copybara import of the project:

--
b96f2bc by Samuel Marks <[email protected]>:

[keras/models/cloning.py,keras/models/sharpness_aware_minimization.py] Standardise docstring usage of "Default to"

--
5719f7b by Samuel Marks <[email protected]>:

[keras/models/sharpness_aware_minimization.py] Use backticks for defaults in docstrings

Merging this change closes #17974

FUTURE_COPYBARA_INTEGRATE_REVIEW=#17974 from SamuelMarks:keras.models-defaults-to 5719f7b
PiperOrigin-RevId: 529706730

keras/models/cloning.py

@@ -484,12 +484,13 @@ def clone_model(model, input_tensors=None, clone_function=None):
             model (except `InputLayer` instances). It takes as argument the
             layer instance to be cloned, and returns the corresponding layer
             instance to be used in the model copy. If unspecified, this callable
-            defaults to the following serialization/deserialization function:
+            becomes the following serialization/deserialization function:
             `lambda layer: layer.__class__.from_config(layer.get_config())`.
             By passing a custom callable, you can customize your copy of the
             model, e.g. by wrapping certain layers of interest (you might want
             to replace all `LSTM` instances with equivalent
             `Bidirectional(LSTM(...))` instances, for example).
+            Defaults to `None`.
 
     Returns:
       An instance of `Model` reproducing the behavior

keras/models/sharpness_aware_minimization.py

@@ -41,11 +41,11 @@ class SharpnessAwareMinimization(Model):
     Args:
       model: `tf.keras.Model` instance. The inner model that does the
         forward-backward pass.
-      rho: float, defaults to 0.05. The gradients scaling factor.
-      num_batch_splits: int, defaults to None. The number of mini batches to
+      rho: float. The gradients scaling factor. Defaults to `0.05`.
+      num_batch_splits: int. The number of mini batches to
         split into from each data batch. If None, batches are not split into
-        sub-batches.
-      name: string, defaults to None. The name of the SAM model.
+        sub-batches. Defaults to `None`.
+      name: string. The name of the SAM model. Defaults to `None`.
 
     Reference:
       [Pierre Foret et al., 2020](https://arxiv.org/abs/2010.01412)