AWS bedrock documentation change
Summary
Restructured documentation with clearer headings, converted numbered steps to markdown list format, and removed redundant section titles. Added emphasis to key actions and consolidated prerequisite information.
Security assessment
Changes are organizational and formatting improvements without addressing vulnerabilities or security incidents. The note about exclusive model access and data usage policies remains unchanged from previous documentation.
Diff
diff --git a/bedrock/latest/userguide/model-distillation.md b/bedrock/latest/userguide/model-distillation.md index 014611830..3abe6a29b 100644 --- a//bedrock/latest/userguide/model-distillation.md +++ b//bedrock/latest/userguide/model-distillation.md @@ -5 +5 @@ -How Amazon Bedrock Model Distillation works +How to use Amazon Bedrock Model DistillationHow Amazon Bedrock Model Distillation works @@ -11,14 +11 @@ How Amazon Bedrock Model Distillation works -To use Amazon Bedrock Model Distillation, you do the following: - - 1. Choose a teacher model and a student model. For more information, see [Choose teacher and student models for distillation](./prequisites-model-distillation.html). - - 2. Prepare your training data for distillation. Your training data is a collection of prompts stored in `.jsonl` files. Amazon Bedrock uses the input data to generate responses from the teacher model and uses the responses to fine-tune the student model. - - * You can optimize the synthetic data generation process by formatting your input prompts for the use case that you want. For more information, see [Optimize your input prompts for synthetic data generation](./distillation-prepare-datasets.html#distillation-data-prep-prompt-optimization). - - * You can prepare labeled input data as prompt-response pairs. Amazon Bedrock can use these pairs as golden examples while generating responses from the teacher model. For more information, see [Option 1: Provide your own prompts for data preparation](./distillation-data-prep-option-1.html). - - * If you enable CloudWatch Logs invocation logging, you can use existing teacher responses from invocation logs stored in Amazon S3 as training data. An invocation log in Amazon Bedrock is a detailed record of model invocations. For more information, see [Option 2: Use invocation logs for data preparation](./distillation-data-prep-option-2.html). - - 3. Create a Distillation job. This job creates a smaller, faster, and more cost-effective model for your use case. Only you can access the final distilled model. Amazon Bedrock doesn't use your data to train any other teacher or student model for public use. For more information, see [Submit a model distillation job in Amazon Bedrock](./submit-model-distillation-job.html). For more information on setting up on demand inference, see [Set up inference for a custom model](./model-customization-use.html). - +## How to use Amazon Bedrock Model Distillation @@ -25,0 +13 @@ To use Amazon Bedrock Model Distillation, you do the following: +To use Amazon Bedrock Model Distillation, you do the following: @@ -26,0 +15 @@ To use Amazon Bedrock Model Distillation, you do the following: + 1. **Choose a teacher model and a student model** – For more information, see [Prerequisites for model distillation](./prequisites-model-distillation.html). @@ -28,5 +17 @@ To use Amazon Bedrock Model Distillation, you do the following: -###### Topics - - * How Amazon Bedrock Model Distillation works - - * [Access and security for Model Distillation](./model-distillation-access-security.html) + 2. **Prepare your training data for distillation** – Your training data is a collection of prompts stored in `.jsonl` files. Amazon Bedrock uses the input data to generate responses from the teacher model and uses the responses to fine-tune the student model. @@ -34 +19 @@ To use Amazon Bedrock Model Distillation, you do the following: - * [Choose teacher and student models for distillation](./prequisites-model-distillation.html) + * **Optimize prompts** – Format your input prompts for the use case that you want. For more information, see [Optimize your input prompts for synthetic data generation](./distillation-prepare-datasets.html#distillation-data-prep-prompt-optimization). @@ -36 +21 @@ To use Amazon Bedrock Model Distillation, you do the following: - * [Prepare your training datasets for distillation](./distillation-prepare-datasets.html) + * **Use labeled examples** – Prepare labeled input data as prompt-response pairs. Amazon Bedrock can use these pairs as golden examples while generating responses from the teacher model. For more information, see [Option 1: Provide your own prompts for data preparation](./distillation-data-prep-option-1.html). @@ -38 +23 @@ To use Amazon Bedrock Model Distillation, you do the following: - * [Submit a model distillation job in Amazon Bedrock](./submit-model-distillation-job.html) + * **Use invocation logs** – If you enable CloudWatch Logs invocation logging, you can use existing teacher responses from invocation logs stored in Amazon S3 as training data. An invocation log in Amazon Bedrock is a detailed record of model invocations. For more information, see [Option 2: Use invocation logs for data preparation](./distillation-data-prep-option-2.html). @@ -40 +25 @@ To use Amazon Bedrock Model Distillation, you do the following: - * [Clone a distillation job](./clone-model-distillation-job.html) + 3. **Create a distillation job** – This job creates a smaller, faster, and more cost-effective model for your use case. Only you can access the final distilled model. Amazon Bedrock doesn't use your data to train any other teacher or student model for public use. For more information, see [Submit a model distillation job in Amazon Bedrock](./submit-model-distillation-job.html). For more information on setting up on demand inference, see [Set up inference for a custom model](./model-customization-use.html). @@ -55,2 +39,0 @@ If Amazon Bedrock Model Distillation uses its proprietary data synthesis techniq -### Creating a distilled model using prompts that you provide - @@ -59,2 +41,0 @@ Amazon Bedrock uses the input prompts that you provide to generate responses fro -### Creating a distilled model using production data - @@ -67 +48,2 @@ When you generate responses from the model using the `InvokeModel` or `Converse` -**Choosing prompts with invocation logs** +Choosing prompts with invocation logs + @@ -71 +53,2 @@ If you choose to have Amazon Bedrock use only the prompts from the invocation lo -**Choosing prompt-response pairs with invocation logs** +Choosing prompt-response pairs with invocation logs + @@ -83 +66 @@ Evaluate your RFT model -Access and security for Model Distillation +Prerequisites