update cmu-11667

docs/深度生成模型/大语言模型/CMU11-667.en.md

@@ -1,32 +1,31 @@
-# Carnegie Mellon University CS 11-667: Large Language Models Methods and Applications
+# CMU11-667: Large Language Models: Methods and Applications
 
-## Course Introduction
+## Course Overview
 
-- **University**: Carnegie Mellon University
-- **Prerequisites**: 
-  - Basic understanding of machine learning (equivalent to 10-301/10-601)
-  - Familiarity with natural language processing concepts (equivalent to 11-411/11-611)
-  - Fluency in Python and knowledge of PyTorch or similar deep learning frameworks.
-- **Course Difficulty**: 🌟🌟🌟🌟🌟🌟
-- **Course Website**: [Large Language Models Methods and Applications](https://cmu-llms.org/)
+- University: Carnegie Mellon University  
+- Prerequisites: Solid background in machine learning (equivalent to CMU 10-301/10-601) and natural language processing (equivalent to 11-411/11-611); proficiency in Python and familiarity with PyTorch or similar deep learning frameworks.  
+- Programming Language: Python  
+- Course Difficulty: 🌟🌟🌟🌟  
+- Estimated Study Hours: 100+ hours  
 
-"Large Language Models Methods and Applications (11-667)" is a graduate-level course that provides a comprehensive overview of the state of large language models (LLMs). 
+This graduate-level course provides a comprehensive overview of methods and applications of Large Language Models (LLMs), covering a wide range of topics from core architectures to cutting-edge techniques. Course content includes:
 
-This course explores the fundamentals and cutting-edge developments of LLMs, beginning with the basics of language model architectures, training, inference, and evaluation. It then delves into interpretability, alignment, emergent capabilities, scaling laws, and efficient training and deployment techniques. Students also learn about the risks and challenges in deploying LLMs and explore novel applications.
+1. **Foundations**: Neural network architectures for language modeling, training procedures, inference, and evaluation metrics.  
+2. **Advanced Topics**: Model interpretability, alignment methods, emergent capabilities, and applications in both textual and non-textual domains.  
+3. **System & Optimization Techniques**: Large-scale pretraining strategies, deployment optimization, and efficient training/inference methods.  
+4. **Ethics & Safety**: Addressing model bias, adversarial attacks, and legal/regulatory concerns.
 
-### Topics Covered:
-- Foundations of language models
-- Network architectures, training, and evaluation
-- Emergent capabilities and scaling laws
-- Applications in natural language processing and beyond
-- Privacy, alignment, and robustness in LLMs
-- Challenges in deployment and ethical considerations
+The course blends lectures, readings, quizzes, interactive exercises, assignments, and a final project to offer students a deep and practical understanding of LLMs, preparing them for both research and real-world system development.
 
-### Learning Goals:
-By the end of the course, students will be able to:
-- Compare and analyze different LLMs and their use cases.
-- Train and implement neural language models in PyTorch.
-- Use open-source tools to fine-tune and perform inference with pre-trained LLMs.
-- Understand and apply LLMs to downstream tasks and identify the impact of pre-training decisions.
-- Read and comprehend research papers on LLMs, understanding terms like scaling laws, RLHF, and prompt engineering.
-- Develop innovative approaches for leveraging LLMs in new applications.
+**Self-Study Tips**:
+
+- Thoroughly read all assigned papers and materials before each class.  
+- Become proficient with PyTorch and implement core models and algorithms by hand.  
+- Complete the assignments diligently to build practical skills and reinforce theoretical understanding.
+
+## Course Resources
+
+- Course Website: <https://cmu-llms.org/>  
+- Course Videos: Selected lecture slides and materials are available on the website; full lecture recordings may require CMU internal access.  
+- Course Materials: Curated research papers and supplementary materials, with the full reading list available on the course site.  
+- Assignments: Six programming assignments covering data preparation, Transformer implementation, retrieval-augmented generation, model evaluation and debiasing, and training efficiency. Details at <https://cmu-llms.org/assignments/>

docs/深度生成模型/大语言模型/CMU11-667.md

@@ -1,32 +1,31 @@
-# Carnegie Mellon University CS 11-667: Large Language Models Methods and Applications
+# CMU11-667: Large Language Models: Methods and Applications
 
 ## 课程简介
 
-- **所属大学**: 卡内基梅隆大学 (Carnegie Mellon University)
-- **先修要求**: 
-  - 机器学习的基本知识（相当于课程 10-301/10-601）
-  - 自然语言处理的相关概念（相当于课程 11-411/11-611）
-  - 熟练掌握 Python 编程，了解 PyTorch 或类似的深度学习框架。
-- **课程难度**: 🌟🌟🌟🌟🌟🌟
-- **课程网站**: [大型语言模型的方法与应用](https://cmu-llms.org/)
+- 所属大学：Carnegie Mellon University
+- 先修要求：具备机器学习基础（相当于 CMU 的 10-301/10-601）和自然语言处理基础（相当于 11-411/11-611）；熟练掌握 Python，熟悉 PyTorch 等深度学习框架。
+- 编程语言：Python
+- 课程难度：🌟🌟🌟🌟
+- 预计学时：100 学时以上
 
-《大型语言模型的方法与应用 (11-667)》是一门研究生课程，提供关于大型语言模型（LLMs）最新进展的全面概述。
+该研究生课程全面介绍了大型语言模型（LLM）的方法与应用，涵盖从基础架构到前沿技术的广泛主题。课程内容包括：
 
-课程涵盖了语言模型的基础知识、网络架构、训练、推理与评估，并深入探讨了解释性、对齐、涌现能力、扩展定律，以及高效训练和部署的最新技术。学生还将学习 LLM 的部署风险及挑战，并探索其在新应用中的潜力。
+1. **基础知识**：语言模型的网络架构、训练、推理和评估方法。
+2. **进阶主题**：模型解释性、对齐方法、涌现能力，以及在语言任务和非文本任务中的应用。
+3. **扩展技术**：大规模预训练技术、模型部署优化，以及高效的训练和推理方法。
+4. **伦理与安全**：模型偏见、攻击方法、法律问题等。
 
-### 课程内容：
-- 语言模型的基础
-- 网络架构、训练与评估
-- 涌现能力与扩展定律
-- 在自然语言处理及其他领域的应用
-- 隐私保护、对齐与鲁棒性
-- 部署中的挑战与伦理考虑
+课程采用讲座、阅读材料、小测验、互动活动、作业和项目相结合的方式进行，旨在为学生提供深入理解 LLM 的机会，并为进一步的研究或应用打下坚实基础。
 
-### 学习目标：
-完成课程后，学生将能够：
-- 比较并分析不同的 LLM 模型及其应用场景。
-- 使用 PyTorch 实现和训练语言模型。
-- 使用开源工具微调并进行预训练模型的推理。
-- 理解 LLM 在下游任务中的应用，并评估训练时的决策对这些任务的影响。
-- 阅读并理解 LLM 领域的学术论文，掌握相关术语（如扩展定律、RLHF、提示工程等）。
-- 设计创新方法，将现有大型语言模型应用于新场景。
+**自学建议**：
+
+- 认真阅读每次课前指定的论文和材料。
+- 熟悉 PyTorch 等深度学习框架，动手实现模型和算法。
+- 扎实完成课程作业。
+
+## 课程资源
+
+- 课程网站：<https://cmu-llms.org/>
+- 课程视频：部分讲座幻灯片和材料可在课程网站获取，完整视频可能需通过 CMU 内部平台访问。
+- 课程教材：精选论文和资料，具体阅读列表详见课程网站。
+- 课程作业：共六次作业，涵盖预训练数据准备、Transformer 实现、检索增强生成、模型比较与偏见缓解、训练效率提升等主题，详情见 <https://cmu-llms.org/assignments/>

docs/深度生成模型/大语言模型/CMU11-711.md

@@ -18,6 +18,7 @@
 
 * 提前阅读课前推荐文献，跟着阅读顺序循序渐进。
 * 准备好 Python 环境并熟悉 PyTorch/Hugging Face，因为大量实战代码示例基于此。
+* 扎实完成课程作业。
 
 ## 课程资源