Update the HF TGI and pytorch-inference notebooks, with the latest co…

…ntainer image version. PiperOrigin-RevId: 704363085
GoogleCloudPlatform · Dec 9, 2024 · 164ff24 · 164ff24
1 parent b9549cc
commit 164ff24
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 2 deletions.
diff --git a/notebooks/community/model_garden/model_garden_huggingface_pytorch_inference_deployment.ipynb b/notebooks/community/model_garden/model_garden_huggingface_pytorch_inference_deployment.ipynb
@@ -153,7 +153,7 @@
         "TASK = \"text-classification\"  # @param {type: \"string\", isTemplate: true}\n",
         "\n",
         "# The pre-built serving docker images for Hugging Face Pytorch Inference.\n",
-        "SERVE_DOCKER_URI = \"us-docker.pkg.dev/deeplearning-platform-release/gcr.io/huggingface-pytorch-inference-cu121.2-2.transformers.4-44.ubuntu2204.py311\"\n",
+        "SERVE_DOCKER_URI = \"us-docker.pkg.dev/deeplearning-platform-release/gcr.io/huggingface-pytorch-inference-cu121.2-3.transformers.4-46.ubuntu2204.py311\"\n",
         "\n",
         "machine_type = \"g2-standard-8\"  # @param {type: \"string\", isTemplate: true}\n",
         "accelerator_type = \"NVIDIA_L4\"  # @param [\"NVIDIA_L4\", \"None\"] {isTemplate: true}\n",

diff --git a/notebooks/community/model_garden/model_garden_huggingface_tgi_deployment.ipynb b/notebooks/community/model_garden/model_garden_huggingface_tgi_deployment.ipynb
@@ -154,7 +154,7 @@
         "MODEL_ID = \"google/gemma-2-2b-it\"  # @param {type: \"string\", isTemplate: true}\n",
         "\n",
         "# The pre-built serving docker image for TGI.\n",
-        "TGI_DOCKER_URI = \"us-docker.pkg.dev/deeplearning-platform-release/gcr.io/huggingface-text-generation-inference-cu124.2-3.ubuntu2204.py311\"\n",
+        "TGI_DOCKER_URI = \"us-docker.pkg.dev/deeplearning-platform-release/gcr.io/huggingface-text-generation-inference-cu124.2-4.ubuntu2204.py311\"\n",
         "\n",
         "# @markdown Set use_dedicated_endpoint to False if you don't want to use [dedicated endpoint](https://cloud.google.com/vertex-ai/docs/general/deployment#create-dedicated-endpoint).\n",
         "use_dedicated_endpoint = True  # @param {type:\"boolean\"}\n",