From 3cf5a7908ddcb70be216b6d2f2b2be60dcb7e0ce Mon Sep 17 00:00:00 2001
From: David Huntsperger <5672572+pcoet@users.noreply.github.com>
Date: Sun, 10 Mar 2024 22:03:38 -0700
Subject: [PATCH] syncing changes to Keras + Gemma get started (#293)

---
 site/en/gemma/docs/get_started.ipynb | 26 +++++++++++++++++++++++---
 1 file changed, 23 insertions(+), 3 deletions(-)

diff --git a/site/en/gemma/docs/get_started.ipynb b/site/en/gemma/docs/get_started.ipynb
index e8e6e3306..0faa40e9e 100644
--- a/site/en/gemma/docs/get_started.ipynb
+++ b/site/en/gemma/docs/get_started.ipynb
@@ -234,8 +234,24 @@
         "id": "XrAWvsU6pI0E"
       },
       "source": [
-        "`from_preset` instantiates the model from a preset architecture and weights. In the code above, the string `\"gemma_2b_en\"` specifies the preset architecture: a Gemma model with 2 billion parameters. (A Gemma model with 7 billion parameters is also available. To run the larger model in Colab, you need access to the premium GPUs available in paid plans. Alternatively, you can perform [distributed tuning on a Gemma 7B model](https://ai.google.dev/gemma/docs/distributed_tuning) on Kaggle or Google Cloud.)\n",
-        "\n",
+        "`from_preset` instantiates the model from a preset architecture and weights. In the code above, the string `\"gemma_2b_en\"` specifies the preset architecture: a Gemma model with 2 billion parameters.\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "Ij73k0PfUhjE"
+      },
+      "source": [
+        "Note: A Gemma model with 7 billion parameters is also available. To run the larger model in Colab, you need access to the premium GPUs available in paid plans. Alternatively, you can perform [distributed tuning on a Gemma 7B model](https://ai.google.dev/gemma/docs/distributed_tuning) on Kaggle or Google Cloud."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "E-cSEjULUhST"
+      },
+      "source": [
         "Use `summary` to get more info about the model:"
       ]
     },
@@ -380,7 +396,9 @@
         "id": "81KHdRYOrWYm"
       },
       "source": [
-        "As you can see from the summary, the model has 2.5 billion trainable parameters."
+        "As you can see from the summary, the model has 2.5 billion trainable parameters.\n",
+        "\n",
+        "Note: For purposes of naming the model (\"2B\"), the embedding layer is not counted against the number of parameters."
       ]
     },
     {
@@ -561,11 +579,13 @@
         "\n",
         "* Learn how to [finetune a Gemma model](https://ai.google.dev/gemma/docs/lora_tuning).\n",
         "* Learn how to perform [distributed fine-tuning and inference on a Gemma model](https://ai.google.dev/gemma/docs/distributed_tuning).\n",
+        "* Learn about [Gemma integration with Vertex AI](https://ai.google.dev/gemma/docs/integrations/vertex)\n",
         "* Learn how to [use Gemma models with Vertex AI](https://cloud.google.com/vertex-ai/docs/generative-ai/open-models/use-gemma)."
       ]
     }
   ],
   "metadata": {
+    "accelerator": "GPU",
     "colab": {
       "name": "get_started.ipynb",
       "toc_visible": true