AWS sagemaker documentation change
Summary
Updated dataset format description from 'Converse format' to 'format shown below'
Security assessment
Minor documentation clarification with no security implications or security feature additions.
Diff
diff --git a/sagemaker/latest/dg/nova-cpt-2.md b/sagemaker/latest/dg/nova-cpt-2.md index 3cb30a182..6214d89fb 100644 --- a//sagemaker/latest/dg/nova-cpt-2.md +++ b//sagemaker/latest/dg/nova-cpt-2.md @@ -17 +17 @@ CPT on Nova 2.0 allows you to extend these advanced capabilities with your domai -Training and validation datasets must be JSONL files following the Converse format, where each line contains a JSON object representing a conversation with the required fields and structure. Here is an example: +Training and validation datasets must be JSONL files following the format shown below, where each line contains a JSON object representing a conversation with the required fields and structure. Here is an example: