diff --git a/tensorflow/lite/g3doc/tutorials/model_maker_text_classification.ipynb b/tensorflow/lite/g3doc/tutorials/model_maker_text_classification.ipynb
index 8261d6c9e34..e10507ccac7 100644
--- a/tensorflow/lite/g3doc/tutorials/model_maker_text_classification.ipynb
+++ b/tensorflow/lite/g3doc/tutorials/model_maker_text_classification.ipynb
@@ -632,7 +632,7 @@
         "id": "EoWiA_zX8rxE"
       },
       "source": [
-        "# Advanced Usage\n",
+        "## Advanced Usage\n",
         "\n",
         "The `create` function is the critical part of this library in which parameter `model_spec` defines the specification of the model, currently `AverageWordVecModelSpec` and `BertModelSpec` is supported. The `create` function contains the following steps for `AverageWordVecModelSpec`:\n",
         "\n",
@@ -651,7 +651,7 @@
         "id": "mwtiksguDfhl"
       },
       "source": [
-        "# Adjust the model\n",
+        "## Adjust the model\n",
         "\n",
         "We could adjust the model infrastructure like variables `wordvec_dim`, `seq_len` in `AverageWordVecModelSpec` class.\n"
       ]
@@ -736,7 +736,7 @@
         "id": "LvQuy7RSDir3"
       },
       "source": [
-        "## Change the training hyperparameters\n",
+        "### Change the training hyperparameters\n",
         "We could also change the training hyperparameters like `epochs` and `batch_size` that could affect the model accuracy. For instance,\n",
         "\n",
         "*   `epochs`: more epochs could achieve better accuracy, but may lead to overfitting.\n",
@@ -788,7 +788,7 @@
         "id": "Eq6B9lKMfhS6"
       },
       "source": [
-        "## Change the Model\n",
+        "### Change the Model\n",
         "\n",
         "We could change the model by changing the `model_spec`. The following shows how we change to BERT-base model.\n",
         "\n",