use old docker hash for whisper model deployment.

PiperOrigin-RevId: 892120947

Author: vertex-mg-bot

notebooks/community/model_garden/model_garden_pytorch_whisper_large_v3_deployment.ipynb

@@ -215,7 +215,7 @@
         "    is_for_training=False,\n",
         ")\n",
         "\n",
-        "SERVE_DOCKER_URI = \"us-docker.pkg.dev/deeplearning-platform-release/vertex-model-garden/pytorch-inference.cu125.0-4.ubuntu2204.py310\"\n",
+        "SERVE_DOCKER_URI = \"us-docker.pkg.dev/deeplearning-platform-release/vertex-model-garden/pytorch-inference.cu125.0-4.ubuntu2204.py310:public-image-cfd6adbd0e22\"\n",
         "# Dedicated endpoint not supported yet\n",
         "use_dedicated_endpoint = False\n",
         "\n",