fix: missing link

notebooks/official/generative_ai/rlhf_tune_llm.ipynb

@@ -711,7 +711,7 @@
       },
       "source": [
         "### Bulk Inference\n",
-        "You can perform bulk inference using your tuned model, regardless of whether it is an open-source model or PaLM 2 model. To perform bulk inference you will need the tuned model path, which can be found in the Vertex Pipelines UI under **Reinforcer** > **Output Parameters** > `output_model_path`. See the \"Bulk Inference\" tutorial for more details on how to generate offline predictions from a tuned model checkpoint."
+        "You can perform bulk inference using your tuned model, regardless of whether it is an open-source model or PaLM 2 model. To perform bulk inference you will need the tuned model path, which can be found in the Vertex Pipelines UI under **Reinforcer** > **Output Parameters** > `output_model_path`. See the [Bulk Inference](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/generative_ai/batch_eval_llm.ipynb) tutorial for more details on how to generate offline predictions from a tuned model checkpoint."
       ]
     },
     {