Customize Amazon Nova in Amazon SageMaker AI
News
Amazon Nova introduces comprehensive model customization capabilities for its model family through SageMaker AI, enabling advanced adaptation techniques for Nova Micro, Nova Lite, and Nova Pro models.
- Customization techniques include:
- Continued Pre-Training
- Supervised Fine-Tuning (SFT)
- Direct Preference Optimization (DPO)
- Proximal Policy Optimization
- Knowledge Distillation
- Supports both parameter-efficient and full-model training
- Available in SageMaker training jobs and SageMaker HyperPod
- Deployable on Amazon Bedrock with on-demand or Provisioned Throughput inference
- Currently available in US East (N. Virginia) region
This release allows organizations to adapt Nova models to their specific knowledge, workflows, and brand while maintaining performance and low latency.
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
Related articles
Jul 16
2025
2025
Announcing Amazon Nova customization in Amazon SageMaker AI
Jul 23
2025
2025
Customize Amazon Nova in Amazon SageMaker AI using Direct Preference Optimization
Dec 3
2025
2025
New serverless model customization capability in Amazon SageMaker AI
Dec 3
2025
2025
New serverless customization in Amazon SageMaker AI accelerates model fine-tuning
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.