準備資料以進行多模態微調

以下是準備資料以微調理解模型的指導方針和要求：

設計有效的訓練範例

您的訓練資料應該示範您希望模型展現的行為。SFT 會教導模型如何回應，而不是知道什麼。如果您發現自己建立訓練範例主要是為了注入事實知識 （例如，「錯誤碼 E-45 是什麼意思？」 答案為「E-45 表示感應器逾時」)，請考慮 RAG 或提示工程是否可以達成相同的結果，而無需微調。

將來源資料轉換為對話格式時，請遵循下列原則：

常見的資料轉換模式

下列模式說明如何將常見的企業資料格式轉換為有效的 SFT 訓練範例。

模式 1：要分類或查詢的結構化記錄

當您的來源資料是具有 issue、 cause和 等欄位的記錄資料表或資料庫resolution時，請將每個記錄作為使用者問題框架，其中包含相關的輸入欄位和助理回應作為目標輸出欄位。

// train.jsonl
{
  "schemaVersion": "bedrock-conversation-2024",
  "system": [
    {
      "text": "You are a technical support assistant. Given an issue description, identify the most likely root cause and recommended resolution."
    }
  ],
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "text": "A user reports: 'Application crashes on startup after the latest update.' What is the likely cause and resolution?"
        }
      ]
    },
    {
      "role": "assistant",
      "content": [
        {
          "text": "Cause: Incompatible configuration file from the previous version.\nResolution: Delete the local configuration cache and restart the application to regenerate default settings."
        }
      ]
    }
  ]
}

模式 2：結構化問答的階層或分類資料

當您的來源資料是程式碼階層或分類，例如產品類別樹狀目錄或分類系統時， 會產生問題，要求模型導覽階層。在系統提示或使用者轉彎中包含分類內容。

// train.jsonl
{
  "schemaVersion": "bedrock-conversation-2024",
  "system": [
    {
      "text": "You are a product catalog assistant. Answer questions about product categories and classifications accurately."
    }
  ],
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "text": "What top-level category does product code 'EL-4520' belong to, and what subcategories does it include?"
        }
      ]
    },
    {
      "role": "assistant",
      "content": [
        {
          "text": "Product code EL-4520 belongs to the Electronics category. It includes the subcategories: Audio Equipment, Portable Speakers, and Wireless Accessories."
        }
      ]
    }
  ]
}

模式 3：教學對話方塊的程序文件

當您的來源資料包含標準操作程序、執行手冊或step-by-step指南時，請將程序轉換為任務導向問題。使用者詢問如何執行任務，而助理會以一致的格式提供步驟。

// train.jsonl
{
  "schemaVersion": "bedrock-conversation-2024",
  "system": [
    {
      "text": "You are an IT operations assistant. Provide step-by-step instructions based on approved runbooks and standard operating procedures."
    }
  ],
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "text": "How do I reset a user's multi-factor authentication when they have lost access to their device?"
        }
      ]
    },
    {
      "role": "assistant",
      "content": [
        {
          "text": "Follow these steps to reset a user's multi-factor authentication:\n1. Verify the user's identity using the approved verification procedure.\n2. Disable the existing MFA configuration in the identity management console.\n3. Generate a new temporary access code and send it to the user's verified email.\n4. Instruct the user to log in with the temporary code and re-enroll their new device.\n5. Confirm the new MFA device is working by requesting a test authentication.\n6. Document the reset in the support ticket."
        }
      ]
    }
  ]
}

資料集格式範例

下列範例資料集格式提供供您遵循的指南。

// train.jsonl
{
  "schemaVersion": "bedrock-conversation-2024",
  "system": [
    {
      "text": "You are a digital assistant with a friendly personality"
    }
  ],
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "text": "What is the capital of Mars?"
        }
      ]
    },
    {
      "role": "assistant",
      "content": [
        {
          "text": "Mars does not have a capital. Perhaps it will one day."
        }
      ]
    }
  ]
}

// train.jsonl{
    "schemaVersion": "bedrock-conversation-2024",
    "system": [{
        "text": "You are a smart assistant that answers questions respectfully"
    }],
    "messages": [{
            "role": "user",
            "content": [{
                    "text": "What does the text in this image say?"
                },
                {
                    "image": {
                        "format": "png",
                        "source": {
                            "s3Location": {
                                "uri": "s3://your-bucket/your-path/your-image.png",
                                "bucketOwner": "your-aws-account-id"
                            }
                        }
                    }
                }
            ]
        },
        {
            "role": "assistant",
            "content": [{
                "text": "The text in the attached image says 'LOL'."
            }]
        }
    ]
}

{
    "schemaVersion": "bedrock-conversation-2024",
    "system": [{
        "text": "You are a helpful assistant designed to answer questions crisply and to the point"
    }],
    "messages": [{
            "role": "user",
            "content": [{
                    "text": "How many white items are visible in this video?"
                },
                {
                    "video": {
                        "format": "mp4",
                        "source": {
                            "s3Location": {
                                "uri": "s3://your-bucket/your-path/your-video.mp4",
                                "bucketOwner": "your-aws-account-id"
                            }
                        }
                    }
                }
            ]
        },
        {
            "role": "assistant",
            "content": [{
                "text": "There are at least eight visible items that are white"
            }]
        }
    ]
}

資料集限制條件

Amazon Nova 對理解模型的模型自訂套用下列限制。