AWS sagemaker documentation change
Summary
Updated documentation to specify 'Full-rank supervised fine-tuning (SFT)' instead of generic 'Supervised Fine-Tuning (SFT)'
Security assessment
The change adds specificity to the type of fine-tuning methodology but contains no security-related content, vulnerability disclosures, or security enhancements. This appears to be a documentation clarification rather than a security-related update.
Diff
diff --git a/sagemaker/latest/dg/nova-distillation.md b/sagemaker/latest/dg/nova-distillation.md index 5b1bd0363..1d509179c 100644 --- a//sagemaker/latest/dg/nova-distillation.md +++ b//sagemaker/latest/dg/nova-distillation.md @@ -431 +431 @@ Before proceeding to fine-tuning, it's crucial to validate the quality of the au -After data augmentation completes, the second phase involves fine-tuning the student model using Amazon SageMaker HyperPod. For more information, see [Supervised Fine-Tuning (SFT)](./nova-fine-tune.html#nova-fine-tune-sft). +After data augmentation completes, the second phase involves fine-tuning the student model using Amazon SageMaker HyperPod. For more information, see [Full-rank supervised fine-tuning (SFT)](./nova-fine-tune.html#nova-fine-tune-sft).