AWS bedrock documentation change
Summary
Restructured prerequisites for model distillation, adding dedicated permissions section and reorganizing model selection criteria into a table format
Security assessment
The changes add explicit documentation about IAM permissions, S3 bucket access requirements, and encryption options for distillation jobs. This enhances security awareness but doesn't address any specific vulnerability. The cross-region inference permissions clarification improves security posture by ensuring proper access controls.
Diff
diff --git a/bedrock/latest/userguide/prequisites-model-distillation.md b/bedrock/latest/userguide/prequisites-model-distillation.md index 6c4a4115d..d2907fad5 100644 --- a//bedrock/latest/userguide/prequisites-model-distillation.md +++ b//bedrock/latest/userguide/prequisites-model-distillation.md @@ -5 +5 @@ -Supported models and Regions for distillation +PermissionsChoose teacher and student models for distillation @@ -7 +7 @@ Supported models and Regions for distillation -# Choose teacher and student models for distillation +# Prerequisites for model distillation @@ -9 +9 @@ Supported models and Regions for distillation -For Model Distillation, you choose a teacher and student model. +Before you can begin, make sure that you understand access and security controls for Model Distillation. You must also choose a teacher and student model for your distillation job. @@ -11 +11 @@ For Model Distillation, you choose a teacher and student model. - * **Choose a teacher model** +## Permissions @@ -13,7 +13 @@ For Model Distillation, you choose a teacher and student model. -Choose a teacher model that's significantly larger and more capable than the student model, and whose accuracy you want to achieve for your use case. To make distillation more effective, choose a model that's already trained on tasks similar to your use case. - -For some teacher models, you can choose a Cross-Region inference profile ([Increase throughput with cross-Region inference](./cross-region-inference.html)). Cross-Region inference automatically selects the optimal AWS Region within your geography to process your inference request. This improves customer experience by maximizing available resources and model availability. To use a Cross-Region inference profile, your service role must have permissions to invoke the inference profile in an AWS Region, in addition to the model in each Region in the inference profile. For a policy example, see [(Optional) Permissions to create a Distillation job with a cross-region inference profile](./custom-model-job-access-security.html#custom-models-cross-region-inference-profile-permissions). - - * **Choose a student model** - -Choose a student model that's significantly smaller in size than the teacher model. The student model must be one of the student models paired with your teacher model in the following table. +Before you can begin, make sure that you understand access and security controls for Model Distillation. You must have an IAM service role that can access the Amazon S3 bucket where you want to store your Model Distillation training and validation data. Amazon Bedrock also has options for encrypting and further securing your distillation jobs and artifacts. For more information, see [Model customization access and security](./custom-model-job-access-security.html). @@ -20,0 +15 @@ Choose a student model that's significantly smaller in size than the teacher mod +To use a cross-region inference profile for a teacher model in a Distillation job, your service role must have permissions to invoke the inference profile in an AWS Region, in addition to the model in each Region in the inference profile. For a policy example, see [(Optional) Permissions to create a Distillation job with a cross-region inference profile](./custom-model-job-access-security.html#custom-models-cross-region-inference-profile-permissions). For more information about cross-region inference, see [Increase throughput with cross-Region inference](./cross-region-inference.html). @@ -21,0 +17 @@ Choose a student model that's significantly smaller in size than the teacher mod +## Choose teacher and student models for distillation @@ -22,0 +19,4 @@ Choose a student model that's significantly smaller in size than the teacher mod +Model Type | Selection Criteria | Key Considerations | Requirements +---|---|---|--- +**Teacher Model** | Choose a teacher model that's significantly larger and more capable than the student model, and whose accuracy you want to achieve for your use case. | To make distillation more effective, choose a model that's already trained on tasks similar to your use case. For some teacher models, you can choose a Cross-Region inference profile. | Must have permissions to invoke inference profiles and models in each Region. See cross-region inference documentation for policy examples. +**Student Model** | Choose a student model that's significantly smaller in size than the teacher model. | The student model must be one of the student models paired with your teacher model in the supported models table. | Must be compatible with selected teacher model as shown in the following table. @@ -26 +26 @@ The following section lists the supported models and regions for Amazon Bedrock -## Supported models and Regions for Amazon Bedrock Model Distillation +### Supported models and Regions for Amazon Bedrock Model Distillation @@ -55 +55 @@ To use the Amazon Web Services Documentation, Javascript must be enabled. Please -Access and security for Model Distillation +Distillation @@ -57 +57 @@ Access and security for Model Distillation -Prepare your training datasets for distillation +Prepare data