fix: use torch inference container (#1617)

--------- Co-authored-by: Holt Skinner <[email protected]>
GoogleCloudPlatform · Jan 10, 2025 · 4ca4987 · 4ca4987
1 parent c37883e
commit 4ca4987
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/open-models/serving/vertex_ai_tgi_gemma_multi_lora_adapters_deployment.ipynb b/open-models/serving/vertex_ai_tgi_gemma_multi_lora_adapters_deployment.ipynb
@@ -1162,7 +1162,7 @@
         "model = Model.upload(\n",
         "    display_name=\"google--gemma2-tgi-multi-lora-model\",\n",
         "    artifact_uri=str(serve_uri),\n",
-        "    serving_container_image_uri=\"us-docker.pkg.dev/deeplearning-platform-release/gcr.io/huggingface-text-generation-inference-cu124.2-3.ubuntu2204.py311\",\n",
+        "    serving_container_image_uri=\"us-docker.pkg.dev/deeplearning-platform-release/gcr.io/huggingface-pytorch-inference-cu121.2-3.transformers.4-46.ubuntu2204.py311\",\n",
         "    serving_container_ports=[8080],\n",
         "    serving_container_environment_variables={\n",
         "        \"HUGGING_FACE_HUB_TOKEN\": get_token(),\n",