人人都能懂的大语言模型：从基础到实践应用（2026版）
本课程是面向初学者的实用型入门课程，介绍大型语言模型（LLMs）如ChatGPT和Gemini。无论您来自何种背景，本课程都将从高层次讲解LLM的工作原理，说明它们能做什么、不能做什么，并指导您如何在学习、工作和日常生活中有效使用它们。通过动手演示和引导式练习，您将学习提示技巧，如何批判性地评估输出结果，如何应对幻觉和偏见问题，并安全、负责任地使用常见工具（例如文档处理、摘要生成、翻译、数据任务）。课程结束时，您将能够构建属于自己的“LLM工作流程”，用于实际任务——写作、研究、规划和提升效率——而无需具备高级编程技能。
课程概述
📚 内容概要
本课程是面向初学者的、实用性强的大语言模型（LLM）入门课程，涵盖 ChatGPT、Gemini 等典型模型。无论您来自何种背景，本课程都将从宏观层面解释大语言模型的工作原理，阐明其能力边界与局限性，并指导您在学习、工作和日常生活中高效使用这些模型。通过动手演示与引导式练习，您将掌握提示工程技巧，学会批判性评估输出结果，应对幻觉与偏见问题，并安全、负责任地使用常见工具（如文档处理、摘要生成、翻译、数据任务）。完成本课程后，您将能够构建个人专属的“LLM 工作流”，用于写作、研究、规划与效率提升，无需具备高级编程技能。
从基础数学逻辑到分布式代理编排：塑造大型模型时代的顶尖系统架构师。
🎯 学习目标
- 认知类：理解机器学习的数学基石（线性代数、微积分、概率论），以及从感知机到 LSTM 的神经网络架构历史脉络。
- 技能类：熟练使用 Unix Shell 命令远程操作服务器，并利用自动微分引擎实现基本计算图。
- 情感态度类：在调试复杂系统（如梯度爆炸）时，重视“理论根基”而非“过早抽象”。
- 已生成
- 认知类：解释后训练流程的机制，包括监督微调（SFT）与强化学习（RL）框架（如 GRPO）的区别。
- 技能类：设计多阶段训练流程——从冷启动到最终对齐，采用参数高效微调（PEFT）技术，如 LoRA。
- 情感态度类：认识到应将人工智能从“神秘黑箱”转变为由机械层与明确内部推理构成的工程化系统。
- 认知类：对比线性集成框架与循环图式编排，区分垂直集成（MCP）与水平集成（A2A）协议。
- 技能类：运用图论原则定义专用节点与条件边，并使用 FastMCP 实现 MCP 服务以连接代理与外部数据。
- 情感态度类：珍视“循环执行”与状态管理在模拟复杂人类认知流程中的重要性。
课程 共 7 课时 · 预计 21.0h
课程
Lesson
This lesson challenges the "API fallacy" by emphasizing that true LLM mastery requires moving beyond high-level wrappers to understand the underlying mathematical foundations of linear algebra, calculus, and tensor mechanics. Students learn that grounding their practice in these core principles is essential for effective debugging, hardware optimization, and transitioning from cloud-based models to localized architectures.
This lesson explores the engineering mechanics behind Transformers, focusing on how Scaled Dot-Product Attention and the QKV framework enable models to process and predict text. Students will learn how to implement these concepts using matrix operations and stability techniques like positional encoding and layer normalization to ensure efficient, stable model training.
This lesson explores how raw base models are transformed into reliable assistants through a post-training pipeline involving supervised fine-tuning, reinforcement learning, and efficient adaptation techniques like LoRA. Students will learn how to build reasoning capabilities and optimize model performance on limited hardware by focusing on targeted parameter updates rather than full-model retraining.
This lesson explores the transition of prompt engineering into a formal discipline, emphasizing the use of Retrieval-Augmented Generation (RAG) and multi-provider orchestration to ensure system resilience and accuracy. Students learn to move beyond basic heuristics by implementing semantic chunking and architectural safeguards to mitigate hallucinations and prevent single-point-of-failure vulnerabilities in production environments.
This lesson explores the strategic shift toward local LLM deployment to address enterprise needs for data privacy, cost management, and operational resiliency. It also clarifies the critical distinction between OSI-compliant Open Source models and Open Weights models, emphasizing the importance of verifying licensing and usage restrictions for compliance.
This lesson explores the shift from linear AI chains to autonomous agentic workflows, which utilize graph-based architectures to enable cyclic execution, self-correction, and complex decision-making. Students will learn how to leverage state management, the Model Context Protocol (MCP), and multi-agent communication to build intelligent systems capable of reasoning and tool use.
This lesson guides students in transitioning from passive API users to expert architects by mastering autonomous system design, including the Model Context Protocol (MCP) and Agent-to-Agent (A2A) communication. It emphasizes building empirical engineering intuition through local pipelines, rigorous performance evaluation, and an understanding of advanced post-training alignment techniques like GRPO.