模型自定义代码示例

首先，创建一个名为的文本文件FineTuningData.json。将下方的 JSON 代码复制到文本文件中，${output-bucket}用您的 S3 存储桶名称替换${training-bucket}和。

{
    "trainingDataConfig": {
        "s3Uri": "s3://${training-bucket}/train.jsonl"
    },
    "outputDataConfig": {
        "s3Uri": "s3://${output-bucket}"
    }
}

要提交模型自定义作业，请导航到终端FineTuningData.json中包含的文件夹，然后在命令行中运行以下命令，${your-customization-role-arn}替换为您设置的模型自定义角色。

aws bedrock create-model-customization-job \
    --customization-type FINE_TUNING \
    --base-model-identifier arn:aws:bedrock:us-east-1::foundation-model/amazon.titan-text-express-v1 \
    --role-arn ${your-customization-role-arn} \
    --job-name MyFineTuningJob \
    --custom-model-name MyCustomModel \
    --hyper-parameters epochCount=1,batchSize=1,learningRate=.0001,learningRateWarmupSteps=0 \
    --cli-input-json file://FineTuningData.json
                

响应会返回一个 jobArn。给作业留些时间来完成。您可以使用以下命令检查其状态：

aws bedrock get-model-customization-job \
    --job-identifier "jobArn"

当 status 为 COMPLETE 时，您会在响应中看到 trainingMetrics。您可以通过运行以下命令将项目下载到当前文件夹，aet.et-bucket替换为输出存储桶jobId名称和自定义任务的 ID（最后一个斜杠之后的序列jobArn）。

aws s3 cp s3://${output-bucket}/model-customization-job-jobId . --recursive

运行以下命令为您的自定义模型购买无需承诺的预调配吞吐量。

aws bedrock create-provisioned-model-throughput \
    --model-id MyCustomModel \
    --provisioned-model-name MyProvisionedCustomModel \
    --model-units 1

响应会返回一个 provisionedModelArn。留出一段时间来创建预调配吞吐量。要检查其状态，请在以下命令中提供预调配模型的名称或 ARN 作为 provisioned-model-id。

aws bedrock get-provisioned-model-throughput \
    --provisioned-model-id ${provisioned-model-arn}

如果 status 为 InService，则您可以使用以下命令，使用自定义模型运行推理。您必须提供预调配模型的 ARN 作为 model-id。输出将写入当前文件夹output.txt中名为的文件中。

aws bedrock-runtime invoke-model \
    --model-id ${provisioned-model-arn} \
    --body '{"inputText": "What is AWS?", "textGenerationConfig": {"temperature": 0.5}}' \
    --cli-binary-format raw-in-base64-out \
    output.txt

运行以下代码片段提交微调作业。${your-customization-role-arn}替换为您设置和替${training-bucket}换MyCustomizationRole的 ARN 以及您的 S3 存储桶名称。${output-bucket}

import boto3

bedrock = boto3.client(service_name='bedrock')
    
# Set parameters
customizationType = "FINE_TUNING"
baseModelIdentifier = "arn:aws:bedrock:us-east-1::foundation-model/amazon.titan-text-express-v1"
roleArn = "${your-customization-role-arn}"
jobName = "MyFineTuningJob"
customModelName = "MyCustomModel"
hyperParameters = {
        "epochCount": "1",
        "batchSize": "1",
        "learningRate": ".0001",
        "learningRateWarmupSteps": "0"
    }
trainingDataConfig = {"s3Uri": "s3://${training-bucket}/myInputData/train.jsonl"}
outputDataConfig = {"s3Uri": "s3://${output-bucket}/myOutputData"}

# Create job
response_ft = bedrock.create_model_customization_job(
    jobName=jobName, 
    customModelName=customModelName,
    roleArn=roleArn,
    baseModelIdentifier=baseModelIdentifier,
    hyperParameters=hyperParameters,
    trainingDataConfig=trainingDataConfig,
    outputDataConfig=outputDataConfig
)

jobArn = response_ft.get('jobArn')

响应会返回一个 jobArn。给作业留些时间来完成。您可以使用以下命令检查其状态：

bedrock.get_model_customization_job(jobIdentifier=jobArn).get('status')

当status为时COMPLETE，你可以在GetModelCustomizationJob响应trainingMetrics中看到。您也可以按照下载对象中的步骤下载指标。

运行以下命令为您的自定义模型购买无需承诺的预调配吞吐量。

response_pt = bedrock.create_provisioned_model_throughput(
    modelId="MyCustomModel",
    provisionedModelName="MyProvisionedCustomModel",
    modelUnits="1"
)

provisionedModelArn = response_pt.get('provisionedModelArn')

响应会返回一个 provisionedModelArn。留出一段时间来创建预调配吞吐量。要检查其状态，请在以下命令中提供预调配模型的名称或 ARN 作为 provisionedModelId。

bedrock.get_provisioned_model_throughput(provisionedModelId=provisionedModelArn)

如果 status 为 InService，则您可以使用以下命令，使用自定义模型运行推理。您必须提供预调配模型的 ARN 作为 modelId。

import json
import logging
import boto3

from botocore.exceptions import ClientError


class ImageError(Exception):
    "Custom exception for errors returned by the model"

    def __init__(self, message):
        self.message = message


logger = logging.getLogger(__name__)
logging.basicConfig(level=logging.INFO)


def generate_text(model_id, body):
    """
    Generate text using your provisioned custom model.
    Args:
        model_id (str): The model ID to use.
        body (str) : The request body to use.
    Returns:
        response (json): The response from the model.
    """

    logger.info(
        "Generating text with your provisioned custom model %s", model_id)

    brt = boto3.client(service_name='bedrock-runtime')

    accept = "application/json"
    content_type = "application/json"

    response = brt.invoke_model(
        body=body, modelId=model_id, accept=accept, contentType=content_type
    )
    response_body = json.loads(response.get("body").read())

    finish_reason = response_body.get("error")

    if finish_reason is not None:
        raise ImageError(f"Text generation error. Error is {finish_reason}")

    logger.info(
        "Successfully generated text with provisioned custom model %s", model_id)

    return response_body


def main():
    """
    Entrypoint for example.
    """
    try:
        logging.basicConfig(level=logging.INFO,
                            format="%(levelname)s: %(message)s")

        model_id = provisionedModelArn

        body = json.dumps({
            "inputText": "what is AWS?"
        })

        response_body = generate_text(model_id, body)
        print(f"Input token count: {response_body['inputTextTokenCount']}")

        for result in response_body['results']:
            print(f"Token count: {result['tokenCount']}")
            print(f"Output text: {result['outputText']}")
            print(f"Completion reason: {result['completionReason']}")

    except ClientError as err:
        message = err.response["Error"]["Message"]
        logger.error("A client error occurred: %s", message)
        print("A client error occured: " +
              format(message))
    except ImageError as err:
        logger.error(err.message)
        print(err.message)

    else:
        print(
            f"Finished generating text with your provisioned custom model {model_id}.")


if __name__ == "__main__":
    main()