diff --git a/keras_hub/src/models/efficientnet/fusedmbconv.py b/keras_hub/src/models/efficientnet/fusedmbconv.py
index 8d2cc2fdef..51a7f95fef 100644
--- a/keras_hub/src/models/efficientnet/fusedmbconv.py
+++ b/keras_hub/src/models/efficientnet/fusedmbconv.py
@@ -47,6 +47,9 @@ class FusedMBConvBlock(keras.layers.Layer):
         se_ratio: default 0.0, The filters used in the Squeeze-Excitation phase,
             and are chosen as the maximum between 1 and input_filters*se_ratio
         batch_norm_momentum: default 0.9, the BatchNormalization momentum
+        batch_norm_epsilon: default 1e-3, float, epsilon for batch norm
+            calcualtions. Used in denominator for calculations to prevent divide
+            by 0 errors.
         activation: default "swish", the activation function used between
             convolution operations
         dropout: float, the optional dropout rate to apply before the output
diff --git a/keras_hub/src/models/efficientnet/mbconv.py b/keras_hub/src/models/efficientnet/mbconv.py
index e9acbfeb9a..b4dc05f7c9 100644
--- a/keras_hub/src/models/efficientnet/mbconv.py
+++ b/keras_hub/src/models/efficientnet/mbconv.py
@@ -62,6 +62,9 @@ def __init__(
                 is above 0. The filters used in this phase are chosen as the
                 maximum between 1 and input_filters*se_ratio
             batch_norm_momentum: default 0.9, the BatchNormalization momentum
+            batch_norm_epsilon: default 1e-3, float, epsilon for batch norm
+                calcualtions. Used in denominator for calculations to prevent
+                divide by 0 errors.
             activation: default "swish", the activation function used between
                 convolution operations
             dropout: float, the optional dropout rate to apply before the output