利用 SLM 结合边缘设备构建 AIoT Agent-卢建晖.pdf

1、利用 SLM 结合边缘设备构建 AIoT Agent卢建晖 微软高级云技术布道师模型发展模型继续发展文本语音视频图片向量闭源模型 云端 开源模型 本地企业最终选择Cloud LLMLocal SLMs混合模型GPUNPUCPU云+本地的算力架构微调微调RAG行业数据SLM什么是 SLM(Small Language Model)LLMSLM厂商的 SLM 角力模型选择 LLM vs SLM性能1.更少的算力需求2.部署在更小的设备甚至边缘计算场景上无障碍1.更多开发者和组织可以使用2.具备一定的业务能力，便于企业开发人员使用定制化1.针对特定领域和任务进行微调2.所有权不同的开源小模型应用场景

2、Qianwen-chatOpenELMGemma-2bPhi3知识/文本/聊天NanoDBjina-embeddings-v2-base-cn向量模型图片，代码LLaVAAudioCraftNanoVLM数据算法评估部署如何组织数据企业内部多个数据源的整理如何有效组织数据数据安全Qlora vs Lora参数调整计算本地或云端模型性能提示工程有效性效能存储边缘设备的部署模型压缩回应迭代影响构建行业模型的四大要素Azure AIAzure AI Content SafetyAzure OpenAI ServiceAzure AI TranslatorAzure AI DocumentIntell

3、igenceAzure AI VisionAzure AI SearchAzure AI LanguageAzure AI SpeechAzure AI ServicesPre-trained,turnkey solutions for intelligent applicationsCutting-Edge ModelsAccess to the latest foundation and open-source modelsAzure AI StudioOne place for building and deploying AI solutionsResponsible AI Model

4、Fine TuningModel TrainingAzure Machine LearningFull-lifecycle tools for designing and managing responsible AI modelsPrompt FlowOrchestrationModel CatalogSolutionEvaluationModelBenchmarkingContinuous MonitoringCode-First ExperienceAzure AI InfrastructureState-of-the-art silicon and systems for AI wor

5、kloadsAzure Maia SiliconMicrofluidic CoolingHigh-Bandwidth NetworkingMicrosoft FabricUnified data platformLake House can build data based on businessCloud+local data integrationPrompt flowResult EvaluationCompare modelsbusiness flow integrationONNX RuntimeCross-platformResponseInt4,float32,float16 m

6、ulti-format compatibleAzure Machine LearningFull-lifecycle tools for designing and managing responsible AI modelsPrompt FlowOrchestrationDeploymentDatastoreModel CatalogComputeNvidiaSLM+Azure MLSLM OpsSLMSLMF Fineine-tuning-tuningModelModeldatasetEvaluationDep