aws-ai-ml
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseAWS AI/ML Model Customization
AWS AI/ML模型定制
Domain expertise for fine-tuning and deploying models on Amazon SageMaker. Covers the full model customization lifecycle from planning through production deployment.
专注于在Amazon SageMaker上微调与部署模型的领域专业知识。覆盖从规划到生产部署的完整模型定制生命周期。
Routing
路由匹配
Match the user's intent to the appropriate reference folder and load only that content.
| User intent | Reference | When to use |
|---|---|---|
| Plan a model customization project, discover scope of work, resume or modify a plan | references/planning/ | User's request relates to model customization or deployment (fine-tuning, training, building, customizing, reviewing data, deploying or standing up a model — including selecting or deploying an off-the-shelf or base model with no training — or getting advice on approach). Always co-activate with other intents to discover full scope. Load this reference FIRST when the request matches multiple rows in this table — read its plan templates before routing to a single-action reference. |
| Define the business problem, success criteria, or use case spec | references/use-case-specification/ | User says "define my use case", "capture requirements", "what should I decide up front", or as default first step in any plan. Skip only if user explicitly declines. |
| Select or change a base model | references/model-selection/ | User asks which model to use, mentions a model name or family, or wants to evaluate what's available. Always activate model-selection even for known model names because the exact Hub model ID must be resolved. Recommended: route to use-case-specification first to capture requirements — this produces better filtering results. Routing to use-case-specification first is not required if user provides a specific model name/ID or declines. If intent is ambiguous (fine-tune vs deploy as-is), model-selection MUST confirm which path before proceeding. Base model filtering for deployment MUST go through select-for-deployment.md and its scripts for any final recommendation. |
| Choose a fine-tuning technique (SFT, DPO, RLVR, RLAIF) | references/finetuning-technique/ | User has decided to fine-tune and needs to choose a technique, or technique needs validation against the selected model's recipes. Requires a base model to be selected first. |
| Validate dataset quality and format | references/dataset-evaluation/ | User says "is my dataset okay", "check my training data", "I have my own data", or before starting any fine-tuning job. |
| Transform or convert a dataset between formats | references/dataset-transformation/ | User says "transform", "convert", "reformat", or dataset schema needs to change. Always use this rather than writing inline transformation code. |
| Generate fine-tuning code and start training | references/finetuning/ | User says "start training", "fine-tune my model", "I'm ready to train", or plan reaches the finetuning step. Supports SFT, DPO, RLVR, RLAIF trainers. |
| Evaluate or benchmark a trained model | references/model-evaluation/ | User says "evaluate my model", "run a benchmark", "test model performance", "compare models". Supports LLM-as-Judge and Custom Scorer. |
| Deploy a model to endpoint or Bedrock | references/model-deployment/ | User says "deploy my model", "create an endpoint", "make it available". Handles Nova vs OSS deployment pathways. |
| Set up IAM roles, S3 buckets, SDK configuration | references/sdk-getting-started/ | User says "set up", "getting started", "check my environment", "configure SDK", or as first step in any plan involving SageMaker training/evaluation/deployment. |
| Manage project directory and artifacts | references/directory-management/ | Starting a new project, resuming existing one, or when PLAN.md needs to be associated with a project directory. |
| Set up, update, or delete a SageMaker Managed MLflow app | references/manage-mlflow/ | User says "set up MLflow", "create MLflow app", "update my MLflow app", "delete my MLflow app", "I need an MLflow server", asks "what is SageMaker MLflow", or a workflow needs an MLflow backend and none is connected. |
| Diagnose a failing or unhealthy SageMaker endpoint | references/endpoint-diagnostics/ | User reports endpoint errors, latency, inference failures, or a deployment that failed. "What's the status of my endpoint?", "Is my endpoint erroring?", "My endpoint failed — why?", "How many instances are running behind my endpoint?", "Is the latency my model or SageMaker?", "Show me the container logs for my endpoint." NOT for training-job issues, endpoint deletion, scaling changes, or new deployments. |
将用户意图匹配到对应的参考文件夹并仅加载该内容。
| 用户意图 | 参考文档 | 使用场景 |
|---|---|---|
| 规划模型定制项目、确定工作范围、恢复或修改计划 | references/planning/ | 用户请求涉及模型定制或部署（微调、训练、构建、定制、审核数据、部署或搭建模型——包括选择或部署现成的或无需训练的基础模型——或寻求方法建议）。始终与其他意图共同激活以明确完整范围。当请求匹配本表多行内容时，优先加载此参考文档——在路由到单一操作参考文档前先阅读其计划模板。 |
| 定义业务问题、成功标准或用例规范 | references/use-case-specification/ | 用户提及“定义我的用例”、“捕获需求”、“我应该提前确定什么”，或作为任何计划的默认第一步。仅当用户明确拒绝时可跳过。 |
| 选择或更换基础模型 | references/model-selection/ | 用户询问应使用哪个模型、提及模型名称或系列，或想要评估可用选项。即使已知模型名称，也始终激活模型选择流程，因为必须解析精确的Hub模型ID。建议： 先路由到用例规范环节以捕获需求——这会产生更好的筛选结果。如果用户提供了特定模型名称/ID或明确拒绝，则无需先路由到用例规范环节。如果意图模糊（微调vs直接部署），模型选择流程必须先确认路径再继续。用于部署的基础模型筛选必须通过select-for-deployment.md及其脚本才能给出最终建议。 |
| 选择微调技术（SFT、DPO、RLVR、RLAIF） | references/finetuning-technique/ | 用户已决定进行微调并需要选择技术，或需要针对所选模型的验证集验证技术。要求先选定基础模型。 |
| 验证数据集质量与格式 | references/dataset-evaluation/ | 用户提及“我的数据集是否可用”、“检查我的训练数据”、“我有自己的数据”，或在启动任何微调作业前。 |
| 在不同格式间转换数据集 | references/dataset-transformation/ | 用户提及“转换”、“转换格式”、“重新格式化”，或需要更改数据集架构。始终使用此流程而非编写内联转换代码。 |
| 生成微调代码并启动训练 | references/finetuning/ | 用户提及“启动训练”、“微调我的模型”、“我准备好训练了”，或计划进入微调步骤。支持SFT、DPO、RLVR、RLAIF训练器。 |
| 评估或基准测试训练后的模型 | references/model-evaluation/ | 用户提及“评估我的模型”、“运行基准测试”、“测试模型性能”、“比较模型”。支持LLM-as-Judge和自定义评分器。 |
| 将模型部署到端点或Bedrock | references/model-deployment/ | 用户提及“部署我的模型”、“创建端点”、“使其可用”。处理Nova与OSS部署路径。 |
| 设置IAM角色、S3存储桶、SDK配置 | references/sdk-getting-started/ | 用户提及“设置”、“入门”、“检查我的环境”、“配置SDK”，或作为任何涉及SageMaker训练/评估/部署计划的第一步。 |
| 管理项目目录与工件 | references/directory-management/ | 启动新项目、恢复现有项目，或需要将PLAN.md与项目目录关联时。 |
| 设置、更新或删除SageMaker托管MLflow应用 | references/manage-mlflow/ | 用户提及“设置MLflow”、“创建MLflow应用”、“更新我的MLflow应用”、“删除我的MLflow应用”、“我需要MLflow服务器”，询问“SageMaker MLflow是什么”，或工作流需要MLflow后端但未连接时。 |
| 诊断故障或异常的SageMaker端点 | references/endpoint-diagnostics/ | 用户报告端点错误、延迟、推理失败，或部署失败。例如“我的端点状态如何？”、“我的端点是否出错？”、“我的端点失败了——原因是什么？”、“我的端点背后运行着多少实例？”、“延迟是模型问题还是SageMaker问题？”、“显示我的端点容器日志。”不适用于训练作业问题、端点删除、缩放更改或新部署场景。 |
Rules
规则
- Progressive disclosure. Load only the reference folder relevant to the current user intent. Do not load all references at once.
- Best-effort help. If the user's request falls outside this skill's references, do not dead-end the conversation. Help them using general AWS knowledge and documentation, and inform the user that the guidance is not covered by this skill's validated workflows.
- 渐进式披露。仅加载与当前用户意图相关的参考文件夹。不要一次性加载所有参考文档。
- 尽力协助。如果用户的请求超出本技能的参考范围，不要终止对话。利用通用AWS知识和文档帮助他们，并告知用户该指导不属于本技能的已验证工作流范畴。