Prerequisites for model customization - Amazon Bedrock

Prerequisites for model customization

Before you can start a model customization job, you need to fulfill the following prerequisites:

  1. Determine whether you plan to carry out a Fine-tuning or Continued Pre-training job and which model you plan to use. The choice you make determines the format of the datasets that you feed into the customization job.

  2. Prepare the training dataset file. If the customization method and model that you choose supports a validation dataset, you can also prepare a validation dataset file. Follow the steps below in Prepare the datasets and then upload the files to an Amazon S3 bucket.

  3. (Optional) Create a custom AWS Identity and Access Management (IAM) service role with the proper permissions by following the instructions at Create a service role for model customization to set up the role. You can skip this prerequisite if you plan to use the AWS Management Console to automatically create a service role for you.

  4. (Optional) Set up extra security configurations.