Model optimization for serving (quantization, pruning) in MLOps - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is quantization in model optimization?

Quantization means making the model use smaller numbers to represent data. This makes the model faster and smaller without losing much accuracy.

beginner

Explain pruning in the context of machine learning models.

Pruning removes parts of the model that are not very important. This makes the model simpler and faster to run.

intermediate

How does quantization help in serving machine learning models?

Quantization reduces the size of the model and speeds up predictions by using fewer bits for numbers, which helps when serving models on devices with limited resources.

intermediate

What is a common effect of pruning on model accuracy?

Pruning can slightly reduce accuracy if too much is removed, but careful pruning keeps accuracy high while improving speed and size.

beginner

Name two benefits of model optimization techniques like quantization and pruning.

They make models smaller and faster, which helps run them on devices with less memory and compute power.

What does quantization primarily reduce in a machine learning model?

A The number of training samples

B The number size used to store weights

C The number of layers

D The number of output classes

Quantization reduces the size of numbers used to store model weights, making the model smaller and faster.

What is the main goal of pruning a model?

A To increase training time

B To add more neurons

C To remove less important parts

D To change the model architecture completely

Pruning removes less important parts of the model to make it simpler and faster.

Which of these is a benefit of model quantization?

A Reduces memory usage

B Increases model size

C Slows down inference

D Requires more training data

Quantization reduces memory usage by using smaller number formats.

What can happen if pruning is too aggressive?

A Model accuracy may drop

B Model becomes larger

C Training time increases

D Model outputs random results

Removing too many parts can reduce the model's accuracy.

Which technique helps deploy models on devices with limited resources?

A Data augmentation

B Adding more layers

C Increasing batch size

D Pruning and quantization

Pruning and quantization reduce model size and speed up inference, helping deployment on limited devices.

Describe what quantization and pruning do to a machine learning model and why they are useful for serving.

Think about how to make a model easier to run on small devices.

Explain the trade-offs involved when applying pruning and quantization to a model.

Optimization can affect accuracy; consider the balance.