Fix formatting issues

PiperOrigin-RevId: 680424508

notebooks/community/model_garden/model_garden_pytorch_llama3_1_finetuning.ipynb

@@ -806,35 +806,6 @@
         "    return model, endpoint\n",
         "\n",
         "\n",
-        "def predict_vllm(\n",
-        "    prompt: str,\n",
-        "    max_tokens: int,\n",
-        "    temperature: float,\n",
-        "    top_p: float,\n",
-        "    top_k: int,\n",
-        "    raw_response: bool,\n",
-        "    lora_weight: str = \"\",\n",
-        "):\n",
-        "    # Parameters for inference.\n",
-        "    instance = {\n",
-        "        \"prompt\": prompt,\n",
-        "        \"max_tokens\": max_tokens,\n",
-        "        \"temperature\": temperature,\n",
-        "        \"top_p\": top_p,\n",
-        "        \"top_k\": top_k,\n",
-        "        \"raw_response\": raw_response,\n",
-        "    }\n",
-        "    if lora_weight:\n",
-        "        instance[\"dynamic-lora\"] = lora_weight\n",
-        "    instances = [instance]\n",
-        "    response = endpoints[\"vllm_gpu\"].predict(\n",
-        "        instances=instances, use_dedicated_endpoint=use_dedicated_endpoint\n",
-        "    )\n",
-        "\n",
-        "    for prediction in response.predictions:\n",
-        "        print(prediction)\n",
-        "\n",
-        "\n",
         "# Use FP8 base model for 405B since original model does not fit.\n",
         "deploy_pretrained_model_id = pretrained_model_id\n",
         "if \"Meta-Llama-3.1-405B\" in deploy_pretrained_model_id:\n",
@@ -880,24 +851,32 @@
         "# @markdown Additionally, you can moderate the generated text with Vertex AI. See [Moderate text documentation](https://cloud.google.com/natural-language/docs/moderating-text) for more details.\n",
         "\n",
         "prompt = \"What is a car?\"  # @param {type: \"string\"}\n",
-        "# @markdown If you encounter the issue like `ServiceUnavailable: 503 Took too long to respond when processing`, you can reduce the maximum number of output tokens, such as set `max_tokens` as 20.\n",
+        "# @markdown If you encounter an issue like `ServiceUnavailable: 503 Took too long to respond when processing`, you can reduce the maximum number of output tokens, such as set `max_tokens` as 20.\n",
         "max_tokens = 50  # @param {type:\"integer\"}\n",
         "temperature = 1.0  # @param {type:\"number\"}\n",
         "top_p = 1.0  # @param {type:\"number\"}\n",
         "top_k = 1  # @param {type:\"integer\"}\n",
         "raw_response = False  # @param {type:\"boolean\"}\n",
         "\n",
-        "\n",
-        "predict_vllm(\n",
-        "    prompt=prompt,\n",
-        "    max_tokens=max_tokens,\n",
-        "    temperature=temperature,\n",
-        "    top_p=top_p,\n",
-        "    top_k=top_k,\n",
-        "    raw_response=raw_response,\n",
-        "    lora_weight=final_checkpoint,\n",
+        "# Overrides parameters for inferences.\n",
+        "instance = {\n",
+        "    \"prompt\": prompt,\n",
+        "    \"max_tokens\": max_tokens,\n",
+        "    \"temperature\": temperature,\n",
+        "    \"top_p\": top_p,\n",
+        "    \"top_k\": top_k,\n",
+        "    \"raw_response\": raw_response,\n",
+        "}\n",
+        "if lora_weight:\n",
+        "    instance[\"dynamic-lora\"] = lora_weight\n",
+        "instances = [instance]\n",
+        "response = endpoints[\"vllm_gpu\"].predict(\n",
+        "    instances=instances, use_dedicated_endpoint=use_dedicated_endpoint\n",
         ")\n",
         "\n",
+        "for prediction in response.predictions:\n",
+        "    print(prediction)\n",
+        "\n",
         "# @markdown Click \"Show Code\" to see more details."
       ]
     },