diff --git a/PaliGemma/Finetune_PaliGemma_for_object_detection.ipynb b/PaliGemma/Finetune_PaliGemma_for_object_detection.ipynb
index 7213888..0a39075 100644
--- a/PaliGemma/Finetune_PaliGemma_for_object_detection.ipynb
+++ b/PaliGemma/Finetune_PaliGemma_for_object_detection.ipynb
@@ -28,7 +28,7 @@
         "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
         "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
         "# See the License for the specific language governing permissions and\n",
-        "# limitations under the License.     "
+        "# limitations under the License."
       ]
     },
     {
@@ -48,7 +48,7 @@
       "source": [
         "<table align=\"left\">\n",
         "  <td>\n",
-        "    <a target=\"_blank\" href=\"https://colab.research.google.com/drive/13fSUAhRviSI1YKhOmesjktw5BaI87sfm?usp=sharing\"><img src=\"https://www.tensorflow.org/images/colab_logo_32px.png\" />Run in Google Colab</a>\n",
+        "    <a target=\"_blank\" href=\"https://colab.research.google.com/github/google-gemini/gemma-cookbook/blob/main/PaliGemma/Finetune_PaliGemma_for_object_detection.ipynb\"><img src=\"https://www.tensorflow.org/images/colab_logo_32px.png\" />Run in Google Colab</a>\n",
         "  </td>\n",
         "</table>"
       ]
@@ -2058,7 +2058,7 @@
       "source": [
         "## Conclusion\n",
         "\n",
-        "This notebook demonstrated the fine-tuning of Paligemma on a fashion dataset for object detection. While the complete dataset of 4.5k images could not be utilized due to resource constraints, a subset of 640 images was used, which resulted in measurable improvements in detecting clothing items. \n",
+        "This notebook demonstrated the fine-tuning of Paligemma on a fashion dataset for object detection. While the complete dataset of 4.5k images could not be utilized due to resource constraints, a subset of 640 images was used, which resulted in measurable improvements in detecting clothing items.\n",
         "\n",
         "Model was fine-tuned for 80 steps on T4 GPUs;\n",
         "Loss was reduced from 4.7220 to 2.5054.\n",