Fine-tuning Amazon Nova models
You can customize the Amazon Nova models using the fine-tuning method with labeled proprietary data on Amazon Bedrock to gain more performance for your use case than the models provide out-of-the-box. That is, fine-tuning provides enhancements beyond what is gained with zero- or few-shot invocation and other prompt engineering techniques. You can fine-tune Amazon Nova models when a sufficient amount of high-quality, labeled training data that is available for the following use cases:
-
When you have a niche or specialized tasks in a specific domain.
-
When you want model outputs aligned with brand tone, company policies, or proprietary workflows.
-
When you need better results across a wide number of tasks and thus need to introduce examples in training. This situation is in contrast to providing instructions and examples in prompts, which also impacts token cost and request latency.
-
When you have tight latency requirements and can benefit from smaller models that are tailored to a specific use case.
Available models
Fine-tuning is available for the Nova 2 Lite Amazon Nova 2.0 model and their supported text, image and video modalities.
