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。

# 範例筆記本
<a name="jumpstart-foundation-models-example-notebooks"></a>

如需有關如何將公開的 JumpStart 基礎模型與 SageMaker Python SDK 搭配使用的步驟範例，請參閱下列有關產生文字、產生影像和模型自訂的筆記本。

**注意**  
專屬和公開的 JumpStart 基礎模型具有不同的 SageMaker AI Python SDK 部署工作流程。透過 Amazon SageMaker Studio Classic 或 SageMaker AI 主控台探索專屬基礎模型範例筆記本。如需詳細資訊，請參閱[JumpStart 基礎模型用量](jumpstart-foundation-models-use.md)。

您可以複製 [Amazon SageMaker AI 範例儲存庫](https://github.com/aws/amazon-sagemaker-examples/tree/main/introduction_to_amazon_algorithms/jumpstart-foundation-models)，以在 Studio 內您選擇的 Jupyter 環境中執行可用的 JumpStart 基礎模型範例。如需可用於在 SageMaker AI 中建立和存取 Jupyter 之應用程式的詳細資訊，請參閱[Amazon SageMaker Studio 中支援的應用程式](studio-updated-apps.md)。

## 時間序列預測
<a name="jumpstart-foundation-models-example-notebooks-time-series"></a>

您可以使用 Chronos 模型來預測時間序列資料。它們是以語言模型架構為基礎。使用 [SageMaker JumpStart 簡介 - 使用 Chronos 預測時間序列](https://github.com/aws/amazon-sagemaker-examples/blob/default/%20%20%20%20generative_ai/sm-jumpstart_time_series_forecasting.ipynb)筆記本來開始進行。

如需可用 Chronos 模型的詳細資訊，請參閱[可用的基礎模型](jumpstart-foundation-models-latest.md)。

## 產生文字
<a name="jumpstart-foundation-models-example-notebooks-text-generation"></a>

探索文字產生範例筆記本，包括有關一般文字產生工作流程、多語言文字分類、即時批次推論、小樣本學習、聊天機器人互動等的指引。
+ [SageMaker JumpStart 基礎模型 - HuggingFace Text2Text 以 FLAN-T5 XL 為例的文字產生](https://sagemaker-examples.readthedocs.io/en/latest/introduction_to_amazon_algorithms/jumpstart-foundation-models/text2text-generation-flan-t5.html)
+ [SageMaker JumpStart 基礎模型 - BloomZ：多語言文字分類、問題與回答、程式碼產生、段落重新詞組等](https://sagemaker-examples.readthedocs.io/en/latest/introduction_to_amazon_algorithms/jumpstart-foundation-models/text2text-generation-bloomz.html)
+ [SageMaker JumpStart 基礎模型 - HuggingFace Text2Text 批次轉換和即時批次推論](https://sagemaker-examples.readthedocs.io/en/latest/introduction_to_amazon_algorithms/jumpstart-foundation-models/text2text-generation-Batch-Transform.html)
+ [SageMaker JumpStart 基礎模型 - GPT-J、GPT-Neo 小樣本學習](https://sagemaker-examples.readthedocs.io/en/latest/introduction_to_amazon_algorithms/jumpstart-foundation-models/text-generation-few-shot-learning.html)
+ [SageMaker JumpStart 基礎模型 - 聊天機器人](https://sagemaker-examples.readthedocs.io/en/latest/introduction_to_amazon_algorithms/jumpstart-foundation-models/text-generation-chatbot.html)
+ [SageMaker JumpStart 簡介 - 使用 Mistral 模型產生文字](https://sagemaker-examples.readthedocs.io/en/latest/introduction_to_amazon_algorithms/jumpstart-foundation-models/mistral-7b-instruction-domain-adaptation-finetuning.html)
+ [SageMaker JumpStart 簡介 - 使用 Falcon 模型產生文字](https://sagemaker-examples.readthedocs.io/en/latest/introduction_to_amazon_algorithms/jumpstart-foundation-models/falcon-7b-instruction-domain-adaptation-finetuning.html)

## 產生影像
<a name="jumpstart-foundation-models-example-notebooks-image-generation"></a>

開始使用文字到影像的穩定擴散模型，了解如何部署修復模型，並試著用簡單的工作流程來生成您狗狗的影像。
+ [JumpStart 簡介 - 文字轉影像](https://sagemaker-examples.readthedocs.io/en/latest/introduction_to_amazon_algorithms/jumpstart_text_to_image/Amazon_JumpStart_Text_To_Image.html)
+ [JumpStart 影像編輯簡介 - 穩定擴散修復](https://sagemaker-examples.readthedocs.io/en/latest/introduction_to_amazon_algorithms/jumpstart_inpainting/Amazon_JumpStart_Inpainting.html)
+ [為您的狗生成有趣的影像](https://sagemaker-examples.readthedocs.io/en/latest/introduction_to_amazon_algorithms/jumpstart_text_to_image/custom_dog_image_generator.html)

## 自訂模型
<a name="jumpstart-foundation-models-example-notebooks-model-customization"></a>

有時您的使用案例需要針對特定任務進行更大的基礎模型自訂。如需模型自訂方法的詳細資訊，請參閱[基礎模型自訂](jumpstart-foundation-models-customize.md)或探索下列其中一個範例筆記本。
+ [SageMaker JumpStart 基礎模型 - 微調網域特定資料集上的文字產生 GPT-J 6B 模型](https://sagemaker-examples.readthedocs.io/en/latest/introduction_to_amazon_algorithms/jumpstart-foundation-models/domain-adaption-finetuning-gpt-j-6b.html)
+ [SageMaker JumpStart 基礎模型 - HuggingFace Text2Text 指令微調](https://sagemaker-examples.readthedocs.io/en/latest/introduction_to_amazon_algorithms/jumpstart-foundation-models/instruction-fine-tuning-flan-t5.html)
+ [檢索增強生成：使用 LangChain 和 Cohere 生成和 SageMaker JumpStart 嵌入模型回答問題](https://sagemaker-examples.readthedocs.io/en/latest/introduction_to_amazon_algorithms/jumpstart-foundation-models/question_answering_retrieval_augmented_generation/question_answering_Cohere+langchain_jumpstart.html)
+ [檢索增強生成：使用 LLama-2、Pinecone 和自訂資料集回答問題](https://sagemaker-examples.readthedocs.io/en/latest/introduction_to_amazon_algorithms/jumpstart-foundation-models/question_answering_retrieval_augmented_generation/question_answering_pinecone_llama-2_jumpstart.html)
+ [檢索增強生成：以開放原始碼的 LangChain 程式庫的自訂資料集為基礎回答問題](https://sagemaker-examples.readthedocs.io/en/latest/introduction_to_amazon_algorithms/jumpstart-foundation-models/question_answering_retrieval_augmented_generation/question_answering_langchain_jumpstart.html)
+ [檢索增強生成：以自訂資料集為基礎回答問題](https://sagemaker-examples.readthedocs.io/en/latest/introduction_to_amazon_algorithms/jumpstart-foundation-models/question_answering_retrieval_augmented_generation/question_answering_jumpstart_knn.html)
+ [檢索增強生成：使用 Llama-2 和文字嵌入模型回答問題](https://sagemaker-examples.readthedocs.io/en/latest/introduction_to_amazon_algorithms/jumpstart-foundation-models/question_answering_retrieval_augmented_generation/question_answering_text_embedding_llama-2_jumpstart.html)
+ [Amazon SageMaker JumpStart - 文字嵌入與句子類似性](https://sagemaker-examples.readthedocs.io/en/latest/introduction_to_amazon_algorithms/jumpstart-foundation-models/question_answering_retrieval_augmented_generation/text-embedding-sentence-similarity.html)