AWS bedrock documentation change
Summary
Added detailed console workflow for model distillation jobs, including encryption options, VPC settings, and IAM role configuration. Expanded API documentation and added 'Next steps' section.
Security assessment
Added documentation about KMS encryption for job artifacts and VPC configurations for job protection, which are security features. However, there's no evidence of addressing a specific security vulnerability.
Diff
diff --git a/bedrock/latest/userguide/submit-model-distillation-job.md b/bedrock/latest/userguide/submit-model-distillation-job.md index 553f27137..34dfefc65 100644 --- a//bedrock/latest/userguide/submit-model-distillation-job.md +++ b//bedrock/latest/userguide/submit-model-distillation-job.md @@ -5 +5 @@ -PrerequisitesSubmit your job +PrerequisitesSubmit your jobNext steps @@ -9 +9 @@ PrerequisitesSubmit your job -You can perform model distillation by sending a [CreateModelCustomizationJob](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_CreateModelCustomizationJob.html) (see link for request and response formats and field details) request with an [Amazon Bedrock control plane endpoint](https://docs.aws.amazon.com/general/latest/gr/bedrock.html#br-cp). +You can perform model distillation through the Amazon Bedrock console or by sending a [CreateModelCustomizationJob](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_CreateModelCustomizationJob.html) request with an [Amazon Bedrock control plane endpoint](https://docs.aws.amazon.com/general/latest/gr/bedrock.html#br-cp). @@ -13 +13 @@ You can perform model distillation by sending a [CreateModelCustomizationJob](ht - * Create an AWS Identity and Access Management (IAM) service role to access the S3 bucket where you want to store your model customization training and validation data. You can create this role automatically by using the AWS Management Console or manually. For more information on the manual option, see [Create an IAM service role for model customization](./custom-model-job-access-security.html#custom-model-job-service-role). + * Create an AWS Identity and Access Management (IAM) service role to access the Amazon S3 bucket where you want to store your model customization training and validation data. You can create this role using the AWS Management Console or manually. For more information on the manual option, see [Create an IAM service role for model customization](./custom-model-job-access-security.html#custom-model-job-service-role). @@ -21,0 +22,2 @@ You can perform model distillation by sending a [CreateModelCustomizationJob](ht +When your Distillation job completes, you can analyze the results of the customization process. For more information see [Analyze the results of a model customization job](./model-customization-analyze.html). + @@ -24 +26,70 @@ You can perform model distillation by sending a [CreateModelCustomizationJob](ht -Minimally, you must provide the following fields to submit your model distillation job when using the Amazon Bedrock API. +Console + + + 1. Sign in to the AWS Management Console using an [IAM role with Amazon Bedrock permissions](./getting-started.html), and open the Amazon Bedrock console at [https://console.aws.amazon.com/bedrock/](https://console.aws.amazon.com/bedrock/). + + 2. From the left navigation pane, choose **Custom models** under **Foundation models**. + + 3. Choose **Create distillation job**. + + 4. For **Distilled model details** , do the following: + + 1. For **Distilled model name** , enter a name for your distilled model. + + 2. (Optional) For **Model encryption** , select the checkbox if you want to provide a KMS key for encrypting your job and its related artifacts. + +For more information, see [Encryption of model customization jobs and artifacts](./encryption-custom-job.html). + + 3. (Optional) Apply **Tags** to your distilled model. + + 5. For **Job configuration** , do the following: + + 1. For **Job name** , enter a name for your distillation job. + + 2. (Optional) For **Model encryption** , select the checkbox if you want to provide a KMS key for encrypting your job and its related artifacts. + +For more information, see [Encryption of model customization jobs and artifacts](./encryption-custom-job.html). + + 3. (Optional) Apply **Tags** to your job. + + 6. For **Teacher model - Student model details** , choose the teacher and student models for creating your distilled model. + +For more information, see [Choose teacher and student models for distillation](./prequisites-model-distillation.html). + + 7. For **Synthetic data generation** , do the following: + + 1. For **Max response length** , specify the maximum length of the synthetic responses generated by the teacher model. + + 2. For **Distillation input dataset** , choose one of the following options: + + * **Directly upload to S3 location** – Specify the S3 location where you're storing the input dataset (prompts) that'll be used for distillation. For more information, see [Option 1: Provide your own prompts for data preparation](./distillation-data-prep-option-1.html). + + * **Provide access to invocation logs** – Specify the S3 location where you're storing the invocation logs with the input dataset (prompts) that'll be used for distillation. For more information, see [Option 2: Use invocation logs for data preparation](./distillation-data-prep-option-2.html). + + * (Optional) For **Request Metadata Filters** , specify filters if you want Amazon Bedrock to only use certain prompts in your logs for distillation. + + * Choose **Read prompts** or **Read prompt-response pairs** depending on what you want Amazon Bedrock to access from your logs. Keep in mind that responses are read only if your teacher model matches the model in your logs. + + 8. For **Distillation output** , specify the S3 location where you want to upload the metrics and reports about your distillation job. + +For more information, see [Analyze the results of a model customization job](./model-customization-analyze.html). + + 9. For **VPC settings** , choose a VPC configuration for accessing the S3 bucket with your training data. + +For more information, see [(Optional) Protect your model customization jobs using a VPC](./custom-model-job-access-security.html#vpc-model-customization). + + 10. For **Service access** , specify the IAM role for accessing the S3 bucket with your training data. Unless you use a Cross Region inference profile or VPC configurations, you can create the role in the Amazon Bedrock console with the correct permissions automatically configured. Or you can use an existing service role. + +For a job that has Amazon VPC configurations or uses a Cross Region inference profile, you must create a new service role in IAM that has the required permissions. + +For more information, see [Create an IAM service role for model customization](./custom-model-job-access-security.html#custom-model-job-service-role). + + 11. Choose **Create distillation job** to start the distillation job. After you customize a model, you can share it or copy it to a different region. To run inference using a custom model (including copied models), you must purchase Provisioned Throughput for it. See [Increase model invocation capacity with Provisioned Throughput in Amazon Bedrock](./prov-throughput.html). + + + + +API + + +At minimum, you must provide the following fields to submit your model distillation job when using the Amazon Bedrock API. @@ -32 +103 @@ roleArn | Role that gives Amazon Bedrock permissions to read training and valida -trainingDataConfig | The Amazon S3 path that has training data +trainingDataConfig | The Amazon S3 path that has your training data @@ -79,0 +151,7 @@ The response returns a `jobArn` of the model distillation job. +## Next steps + + * [Monitor your distillation job](./model-customization-monitor.html). When your Distillation job completes, you can analyze the results of the customization process. For more information see [Analyze the results of a model customization job](./model-customization-analyze.html). + + + + @@ -88 +166 @@ Option 2: Use invocation logs for data preparation -Customize a model with fine-tuning or continued pre-training +Clone a distillation job