update paligemma 2

Author: bebechien

site/en/gemma/docs/paligemma/inference-with-keras.ipynb

@@ -119,7 +119,7 @@
         "Before using PaliGemma for the first time, you must request access to the model through Kaggle by completing the following steps:\n",
         "\n",
         "1. Log in to [Kaggle](https://www.kaggle.com), or create a new Kaggle account if you don't already have one.\n",
-        "1. Go to the [PaliGemma model card](https://www.kaggle.com/models/google/paligemma/) and click **Request Access**.\n",
+        "1. Go to the [PaliGemma model card](https://www.kaggle.com/models/google/paligemma-2/) and click **Request Access**.\n",
         "1. Complete the consent form and accept the terms and conditions."
       ]
     },
@@ -200,7 +200,7 @@
       },
       "outputs": [],
       "source": [
-        "!pip install -U -q keras-nlp"
+        "!pip install -U -q keras-nlp kagglehub"
       ]
     },
     {
@@ -260,7 +260,7 @@
       },
       "outputs": [],
       "source": [
-        "paligemma = keras_hub.models.PaliGemmaCausalLM.from_preset(\"pali_gemma_3b_mix_224\")\n",
+        "paligemma = keras_hub.models.PaliGemmaCausalLM.from_preset(\"kaggle://keras/paligemma2/keras/pali_gemma_2_mix_3b_224\")\n",
         "paligemma.summary()"
       ]
     },
@@ -302,7 +302,7 @@
         "    image = PIL.Image.open(contents)\n",
         "    image = crop_and_resize(image, target_size)\n",
         "    image = np.array(image)\n",
-        "    # Remove alpha channel if neccessary.\n",
+        "    # Remove alpha channel if necessary.\n",
         "    if image.shape[2] == 4:\n",
         "        image = image[:, :, :3]\n",
         "    return image\n",
@@ -492,7 +492,7 @@
       "source": [
         "### Use `segment` prompt\n",
         "\n",
-        "The following example code uses the `segment` prompt syntax to locate the area of an image occupied by an object. It uses the Google `big_vision` library to interpret the model output and generate a mask for the segemented object.\n",
+        "The following example code uses the `segment` prompt syntax to locate the area of an image occupied by an object. It uses the Google `big_vision` library to interpret the model output and generate a mask for the segmented object.\n",
         "\n",
         "Before getting started, install the `big_vision` library and its dependencies, as shown in this code example:\n"
       ]
@@ -672,8 +672,8 @@
   "metadata": {
     "accelerator": "GPU",
     "colab": {
-      "name": "inference-with-keras.ipynb",
-      "toc_visible": true
+      "toc_visible": true,
+      "provenance": []
     },
     "kernelspec": {
       "display_name": "Python 3",
@@ -682,4 +682,4 @@
   },
   "nbformat": 4,
   "nbformat_minor": 0
-}
+}