Module to create Amazon Bedrock custom model
For requirements regarding module structure: style-guide-terraform.md
| Name | Version |
|---|---|
| aws | ~> 5.73 |
| Name | Version |
|---|---|
| terraform | ~> 1.3 |
| aws | ~> 5.73 |
The following input variables are required:
Description: Name for the custom model.
Type: string
Description: A name for the customization job.
Type: string
Description: The Amazon Resource Name (ARN) of an IAM role that Bedrock can assume to perform tasks on your behalf.
Type: string
Description: The S3 URI where the output data is stored.
Type: string
Description: The S3 URI where the training data is stored.
Type: string
The following input variables are optional (have default values):
Description: Model identifier.
Type: string
Default: "amazon.titan-text-express-v1"
Description: The custom model is encrypted at rest using this key. Specify the key ARN.
Type: string
Default: null
Description: The customization type. Valid values: FINE_TUNING, CONTINUED_PRE_TRAINING.
Type: string
Default: null
Description: Parameters related to tuning the model.
Type: map(string)
Default: {}
Description: The S3 URI where the validation data is stored.
Type: string
Default: null
Description: Configuration parameters for the private Virtual Private Cloud (VPC) that contains the resources you are using for this job.
Type:
object({
security_group_ids = list(string)
subnet_ids = list(string)
})Default: null
Description: A map of tags to assign to the customization job and custom model.
Type: map(string)
Default: {}
| Name | Description |
|---|---|
| custom_model_arn | The ARN of the output model. |
| job_arn | The ARN of the customization job. |
Copyright (c) 2024 Flaconi GmbH