Set model_garden_source_model_name for llama3

reference implementation deployment.

PiperOrigin-RevId: 720311748

notebooks/community/model_garden/model_garden_pytorch_llama3_2_deployment.ipynb

@@ -1196,6 +1196,8 @@
         "def deploy_model_ref(\n",
         "    model_name: str,\n",
         "    model_id: str,\n",
+        "    publisher: str,\n",
+        "    publisher_model_id: str,\n",
         "    service_account: str,\n",
         "    base_model_id: str = None,\n",
         "    machine_type: str = \"g2-standard-8\",\n",
@@ -1244,6 +1246,9 @@
         "        serving_container_environment_variables=env_vars,\n",
         "        serving_container_shared_memory_size_mb=(16 * 1024),  # 16 GB\n",
         "        serving_container_deployment_timeout=7200,\n",
+        "        model_garden_source_model_name=(\n",
+        "            f\"publishers/{publisher}/models/{publisher_model_id}\"\n",
+        "        ),\n",
         "    )\n",
         "    print(\n",
         "        f\"Deploying {model_name} on {machine_type} with {accelerator_count} {accelerator_type} GPU(s).\"\n",
@@ -1269,6 +1274,8 @@
         "models[\"ref_gpu\"], endpoints[\"ref_gpu\"] = deploy_model_ref(\n",
         "    model_name=common_util.get_job_name_with_datetime(prefix=\"llama3_2-serve-ref\"),\n",
         "    model_id=model_id,\n",
+        "    publisher=\"meta\",\n",
+        "    publisher_model_id=\"llama3-2\",\n",
         "    base_model_id=hf_model_id,\n",
         "    service_account=SERVICE_ACCOUNT,\n",
         "    machine_type=machine_type,\n",