Model packaging (.mar files) in PyTorch - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

What is the main purpose of a .mar file in PyTorch model deployment?

A .mar file is used in PyTorch model deployment. What does it mainly contain?

A It packages the model's weights, code, and configuration for serving.

B It stores only the raw training data used for the model.

C It is a log file recording model training progress.

D It contains only the model's architecture without weights.

💡 Hint

Think about what you need to run a model in production.

A .mar file bundles the model's weights, code, and config so it can be served easily.

❓ Predict Output

intermediate

What is the output of this TorchServe packaging command?

Consider the command below to create a .mar file:

torch-model-archiver --model-name mymodel --version 1.0 --serialized-file model.pt --handler image_classifier --export-path model_store

What will be the name of the generated .mar file in model_store?

A mymodel.mar

B mymodel-1.0.mar

C model.pt.mar

D image_classifier.mar

💡 Hint

The version is appended to the model name in the .mar file.

The .mar file name format is {model-name}-{version}.mar.

❓ Model Choice

advanced

Which file must be included in the .mar archive for custom preprocessing?

You want to add custom preprocessing code to your PyTorch model serving. Which file should you include in the .mar package?

A A custom handler Python script.

B The raw training dataset file.

C A JSON file with training hyperparameters.

D The model's .pt weights file only.

💡 Hint

Custom preprocessing is done in the handler code.

The handler script defines how input data is processed before inference.

❓ Hyperparameter

advanced

Which option correctly sets the batch size for TorchServe during model serving?

You want to configure TorchServe to process 16 inputs at once. Which configuration parameter should you set?

A Set <code>batch_size=16</code> in the training script before packaging.

B Set <code>batch_size=16</code> in the <code>torch-model-archiver</code> command.

C Set <code>batch_size=16</code> in the model's <code>config.properties</code> file.

D Set <code>batch_size=16</code> in the model's .pt file.

💡 Hint

Batch size for serving is a runtime config, not training.

Batch size during serving is set in the config.properties file used by TorchServe.

🔧 Debug

expert

Why does this .mar file fail to load in TorchServe?

You created a .mar file with this command:

torch-model-archiver --model-name faultymodel --version 1.0 --serialized-file model.pt --handler custom_handler.py --export-path model_store

When starting TorchServe, it fails to load the model with an error about missing handler. What is the most likely cause?

A The model.pt file is corrupted and cannot be loaded.

B The export-path directory does not exist.

C The version number must be omitted for custom handlers.

D The handler argument should be the handler name, not the file path.

💡 Hint

Check how the handler argument is specified in torch-model-archiver.

The --handler option expects a handler name or a path inside the archive, not a direct file path.