diff --git a/sdk/python/foundation-models/system/inference/text-generation/llama-safe-online-deployment.ipynb b/sdk/python/foundation-models/system/inference/text-generation/llama-safe-online-deployment.ipynb
index 83c502925b..5ab2370012 100644
--- a/sdk/python/foundation-models/system/inference/text-generation/llama-safe-online-deployment.ipynb
+++ b/sdk/python/foundation-models/system/inference/text-generation/llama-safe-online-deployment.ipynb
@@ -298,12 +298,16 @@
     "    reg_client.models.list(model_name)\n",
     ")  # list available versions of the model\n",
     "llama_model = None\n",
+    "hf_tgi = False  # If text-generation-inference (hf container) is supported for model\n",
     "\n",
     "if len(version_list) == 0:\n",
     "    raise Exception(f\"No model named {model_name} found in registry\")\n",
     "else:\n",
     "    model_version = version_list[0].version\n",
     "    llama_model = reg_client.models.get(model_name, model_version)\n",
+    "    if \"inference_supported_envs\" in llama_model.tags:\n",
+    "        if \"hf_tgi\" in llama_model.tags[\"inference_supported_envs\"]:\n",
+    "            hf_tgi = True\n",
     "    print(\n",
     "        f\"Using model name: {llama_model.name}, version: {llama_model.version}, id: {llama_model.id} for inferencing\"\n",
     "    )"
@@ -448,16 +452,25 @@
    "source": [
     "from azure.ai.ml.entities import (\n",
     "    OnlineRequestSettings,\n",
+    "    CodeConfiguration,\n",
     "    ManagedOnlineDeployment,\n",
     "    ProbeSettings,\n",
     ")\n",
     "\n",
+    "# For HF TGI inferencing, the scoring script is baked into the container\n",
+    "code_configuration = (\n",
+    "    CodeConfiguration(code=\"./llama-files/score/default/\", scoring_script=\"score.py\")\n",
+    "    if not hf_tgi\n",
+    "    else None\n",
+    ")\n",
+    "\n",
     "deployment = ManagedOnlineDeployment(\n",
     "    name=deployment_name,\n",
     "    endpoint_name=endpoint_name,\n",
     "    model=llama_model.id,\n",
     "    instance_type=sku_name,\n",
     "    instance_count=1,\n",
+    "    code_configuration=code_configuration,\n",
     "    environment_variables=deployment_env_vars,\n",
     "    request_settings=OnlineRequestSettings(request_timeout_ms=REQUEST_TIMEOUT_MS),\n",
     "    liveness_probe=ProbeSettings(\n",