本文為英文版的機器翻譯版本，如內容有任何歧義或不一致之處，概以英文版為準。

# 使用 `ModelPackage` 類別部署專屬基礎模型
<a name="jumpstart-foundation-models-use-python-sdk-proprietary"></a>

訂閱 AWS Marketplace中的模型後，必須使用模型套件資訊部署專屬模型。如需 SageMaker AI 和 的詳細資訊 AWS Marketplace，請參閱[在其中購買和銷售 Amazon SageMaker AI 演算法和模型 AWS Marketplace](https://docs.aws.amazon.com/sagemaker/latest/dg/sagemaker-marketplace.html)。若要尋找最新專屬模型 AWS Marketplace 的連結，請參閱 [Amazon SageMaker JumpStart 入門](https://aws.amazon.com/sagemaker/jumpstart/getting-started/?sagemaker-jumpstart-cards.sort-by=item.additionalFields.priority&sagemaker-jumpstart-cards.sort-order=asc&awsf.sagemaker-jumpstart-filter-product-type=product-type%23foundation-model&awsf.sagemaker-jumpstart-filter-text=*all&awsf.sagemaker-jumpstart-filter-vision=*all&awsf.sagemaker-jumpstart-filter-tabular=*all&awsf.sagemaker-jumpstart-filter-audio-tasks=*all&awsf.sagemaker-jumpstart-filter-multimodal=*all&awsf.sagemaker-jumpstart-filter-RL=*all&sagemaker-jumpstart-cards.q=proprietary&sagemaker-jumpstart-cards.q_operator=AND)。

訂閱您選擇的模型之後 AWS Marketplace，您可以使用 SageMaker Python SDK 和與模型提供者相關聯的 SDK 部署基礎模型。例如，AI21 Labs、Cohere 和 LightOn 分別使用`"ai21[SM]"`、`cohere-sagemaker`、和 `lightonsage` 套件。

例如，若要使用 AI21 Labs 的 Jurassic-2 Jumbo Instruct 定義 JumpStart 模型，請使用下列程式碼：

```
import sagemaker
import ai21

role = get_execution_role()
sagemaker_session = sagemaker.Session()
model_package_arn = {{"arn:aws:sagemaker:us-east-1:865070037744:model-package/j2-jumbo-instruct-v1-1-43-4e47c49e61743066b9d95efed6882f35"}}

my_model = ModelPackage(
    role=role, model_package_arn=model_package_arn, sagemaker_session=sagemaker_session
)
```

如需逐步範例，請在 SageMaker Studio Classic 中尋找並執行與您選擇的專屬基礎模型相關聯的筆記本。如需詳細資訊，請參閱[在 Amazon SageMaker Studio Classic 中使用基礎模型](jumpstart-foundation-models-use-studio.md)。如需 SageMaker Python SDK 的詳細資訊，請參閱 [https://sagemaker.readthedocs.io/en/stable/api/inference/model.html#sagemaker.model.ModelPackage](https://sagemaker.readthedocs.io/en/stable/api/inference/model.html#sagemaker.model.ModelPackage)。