AWS bedrock documentation change
Summary
Updated model ID from 'amazon.nova-lite-v2:0:256k' to 'amazon.nova-2-lite-v1:0:256k', grammatical fixes in security bullet point, and minor wording adjustments
Security assessment
The changes include a model version update and grammatical corrections. The security bullet point edit adds a possessive apostrophe but does not introduce new security content or address vulnerabilities.
Diff
diff --git a/bedrock/latest/userguide/reinforcement-fine-tuning.md b/bedrock/latest/userguide/reinforcement-fine-tuning.md index 67d78fb44..63edcff28 100644 --- a//bedrock/latest/userguide/reinforcement-fine-tuning.md +++ b//bedrock/latest/userguide/reinforcement-fine-tuning.md @@ -26 +26 @@ Reinforcement fine-tuning can provide the following benefits: - * **Improved model performance** \- Reinforcement fine-tuning improves model accuracy over base models. This enables optimization for price and performance by training smaller, faster, and more efficient model variants. + * **Improved model performance** \- Reinforcement fine-tuning improves model accuracy compared to base models. This enables optimization for price and performance by training smaller, faster, and more efficient model variants. @@ -30 +30 @@ Reinforcement fine-tuning can provide the following benefits: - * **Security and compliance** \- Your proprietary data never leaves AWS secure, governed environment during the customization process. + * **Security and compliance** \- Your proprietary data never leaves AWS's secure, governed environment during the customization process. @@ -56 +56 @@ Supported models for reinforcement fine-tuning Provider | Model | Model ID | Sin -Amazon | Nova 2 Lite | amazon.nova-lite-v2:0:256k | us-east-1 +Amazon | Nova 2 Lite | amazon.nova-2-lite-v1:0:256k | us-east-1