You have deployed a model on Vertex AI for real-time inference. During an online prediction request, you get an "Out of Memory" error. What should you do?

• A. Apply for a quota increase for the number of prediction requests.
• B. Send the request again with a smaller batch of instances.
• C. Use batch prediction mode instead of online mode.
• D. Use base64 to encode your data before using it for prediction.

You work for a delivery company. You need to design a system that stores and manages features such as parcels delivered and truck locations over time. The system must retrieve the features with low latency and feed those features into a model for online prediction. The data science team will retrieve historical data at a specific point in time for model training. You want to store the features with minimal effort. What should you do?

• A. Store features as a Vertex AI dataset, and use those features to train the models hosted in Vertex AI endpoints.
• B. Store features in BigQuery timestamp partitioned tables, and use the BigQuery Storage Read API to serve the features.
• C. Store features in Bigtable as key/value data.
• D. Store features in Vertex AI Feature Store.

You are building a TensorFlow text-to-image generative model by using a dataset that contains billions of images with their respective captions. You want to create a low maintenance, automated workflow that reads the data from a Cloud Storage bucket collects statistics, splits the dataset into training/validation/test datasets performs data transformations trains the model using the training/validation datasets, and validates the model by using the test dataset. What should you do?

• A. Use the MLFlow SDK and deploy it on a Google Kubernetes Engine cluster. Create multiple components that use Dataflow and Vertex AI services.
• B. Use the Apache Airflow SDK to create multiple operators that use Dataflow and Vertex AI services. Deploy the workflow on Cloud Composer.
• C. Use the TensorFlow Extended (TFX) SDK to create multiple components that use Dataflow and Vertex AI services. Deploy the workflow on Vertex AI Pipelines.
• D. Use the Kubeflow Pipelines (KFP) SDK to create multiple components that use Dataflow and Vertex AI services. Deploy the workflow on Vertex AI Pipelines.

You are pre-training a large language model on Google Cloud. This model includes custom TensorFlow operations in the training loop. Model training will use a large batch size, and you expect training to take several weeks. You need to configure a training architecture that minimizes both training time and compute costs. What should you do?

• A. Implement 8 workers of a2-megagpu-16g machines by using
  tf.distribute.MultiWorkerMirroredStrategy.
• B. Implement 16 workers of c2d-highcpu-32 machines by using tf.distribute.MirroredStrategy.
• C. Implement 16 workers of a2-highgpu-8g machines by using
  tf.distribute.MultiWorkerMirroredStrategy.
• D. Implement a TPU Pod slice with -accelerator-type=v4-l28 by using tf.distribute.TPUStrategy.

You work for a bank. You have created a custom model to predict whether a loan application should be flagged for human review. The input features are stored in a BigQuery table. The model is performing well, and you plan to deploy it to production. Due to compliance requirements the model must provide explanations for each prediction. You want to add this functionality to your model code with minimal effort and provide explanations that are as accurate as possible.
What should you do?

• A. Update the custom serving container to include sampled Shapley-based explanations in the prediction outputs.
• B. Create an AutoML tabular model by using the BigQuery data with integrated Vertex Explainable AI.
• C. Create a BigQuery ML deep neural network model and use the ML.EXPLAIN_PREDICT method with the num_integral_steps parameter.
• D. Upload the custom model to Vertex AI Model Registry and configure feature-based attribution by using sampled Shapley with input baselines.