Cianplan

Level 5: AI / LLM systems · L5.8 Generative AI on AWS: Bedrock in practice (AIP-C01)

Customizing a model on Bedrock, and serving it

Choose between prompt engineering, fine-tuning, continued pre-training, distillation, reinforcement fine-tuning and Custom Model Import on Bedrock, and decide how the resulting model is served: on-demand deployment, an imported model on demand, or Provisioned Throughput.

13 min · Pro

What you take away

  • Prompt engineering and retrieval come first; train only when the gap is behaviour a prompt cannot hold, never to keep facts current.

And 3 more inside the class, in Pro.

How the class is laid out

  1. The problem
  2. The simple version
  3. Decide what is missing
  4. How a custom model is served
  5. Check your understanding