AIF-C01 notes
Developing generative AI solutions

Selecting an FM

Pre-trained models give a head start and converge faster when fine-tuned, but they can carry bias or miss domain nuances. Choose based on the use case.

Selection criteria

CriterionWhat to check
CostLicensing, inference compute, and customization costs against the benefit
ModalityText, image, audio, or multimodal output
LatencyReal-time apps (such as live translation) need fast inference
Multilingual supportThe languages you need, or adaptability through transfer learning
Model sizeBigger models do better on complex tasks but need more compute
Model complexityComplex models handle advanced tasks but are harder to deploy and optimize
CustomizationWhether you can fine-tune it, and the data and compute that takes
Input/output lengthMaximum sequence length for long documents or long outputs
ResponsibilityBias, misinformation risk, misuse, and training data sources
Deployment and integrationFit with your infrastructure, tools, and libraries

Amazon Titan

Amazon's own FMs come in three types: embeddings, text generation, and image generation. Use them as is or fine-tune them with your data.

Keep revisiting your criteria, because the model landscape changes fast.

On this page