LLMForEverybody

LearnLLM.AI

Learning LLM is all you need.

👉 点击 LearnLLM.AI | 学习大模型，从这里开始

LearnLLM.AI 核心亮点

精选大模型面试题库：覆盖从基础到前沿的实战题目，助您高效备战求职，抓住职业机遇；

系统化论文研读：从2017年Transformer奠基性论文出发，按清晰的知识体系梳理技术演进，适合不同基础的开发者循序渐进地深度提升。

专属优惠码

我们为Github用户准备了限时专属优惠码：GITHUB50 ，期待在 LearnLLM.AI 与您继续同行，共同成长！

配套视频教程(持续更新中)：

👉 点击这里 bilibili

👉 点击这里 YouTube

如有疑问，欢迎随时联系我们。

Happy Learning！

LearnLLM.AI 团队

LLM 精选论文

| 时间 | 论文 | 介绍 | 视频 | 开始学习 | | — | — | — | — | — | | 2017-06-12 | Transformer | 提出自注意力与 Transformer 架构 | | LearnLLM.AI | | 2018-06-11 | GPT-1 | 预训练 + 微调的生成式 Transformer | | LearnLLM.AI | | 2018-10-11 | BERT | 双向编码器：MLM + NSP | | LearnLLM.AI | | 2019-02-14 | GPT-2 | 大规模无监督文本生成 | | LearnLLM.AI | | 2019-10-23 | T5 | 文本到文本统一框架 | | LearnLLM.AI | | 2020-05-28 | GPT-3 | 大模型与少样本学习能力 | | LearnLLM.AI | | 2021-07-07 | CodeX | 面向代码生成的 GPT 系列模型 | | LearnLLM.AI | | 2022-02-08 | AlphaCode | 竞赛级代码生成系统 | | LearnLLM.AI | | 2022-03-04 | InstructGPT | 人类反馈对齐与指令微调 | | LearnLLM.AI | | 2023-02-27 | LLaMA-1 | 高效开源预训练基座模型 | | LearnLLM.AI | | 2023-07-18 | LLaMA-2 | LLaMA 升级版，开放商用 | | LearnLLM.AI | | 2023-09-28 | Qwen 1 | 通义千问第一代基座模型 | | LearnLLM.AI | | 2023-10-10 | Mistral 7B | 高效 7B 级开源模型 | | LearnLLM.AI | 持续更新中…

点击展开/收起 roadmap

AGI 之路

点击展开/收起 ### 目录 - 🐳[序-AGI之路](#序-AGI之路) - 🐱[第一章-大模型之Pre-Training](#第一章-大模型之Pre-Training) - 🐼[架构](#架构) - 🐹[Optimizer](#Optimizer) - 🐰[激活函数](#激活函数) - 🐭[Attention](#Attention机制) - 🐯[位置编码](#位置编码) - 🐨[Tokenizer](#Tokenizer) - 🐻[并行策略](#并行策略) - 🐷[大模型训练框架](#大模型训练框架) - 🐶[第二章-大模型之部署与推理](#第二章-大模型之部署与推理) - 🐯[第三章-大模型微调](#第三章-大模型微调) - 🐻[第四章-大模型量化](#第四章-大模型量化) - 🐼[第五章-显卡与大模型并行](#第五章-显卡与大模型并行) - 🐨[第六章-Prompt-Engineering](#第六章-Prompt-Engineering) - 🦁[第七章-Agent](#第七章-Agent) - 🐷[RAG](#RAG) - 🐘[第八章-大模型企业落地](#第八章-大模型企业落地) - 🐰[第九章-大模型评估指标](#第九章-大模型评估指标) - 🐷[第十章-热点](#第十章-热点) - 🦁[第十一章-数学](#第十一章-数学) ### 序-AGI之路 **[⬆ 一键返回目录](#目录)** [大家都在谈的Scaling_Law是什么](/LLMForEverybody/00-%E5%BA%8F-AGI%E4%B9%8B%E8%B7%AF/%E5%A4%A7%E5%AE%B6%E9%83%BD%E5%9C%A8%E8%B0%88%E7%9A%84ScalingLaw%E6%98%AF%E4%BB%80%E4%B9%88.html) [智能涌现和AGI的起源](/LLMForEverybody/00-%E5%BA%8F-AGI%E4%B9%8B%E8%B7%AF/%E6%99%BA%E8%83%BD%E6%B6%8C%E7%8E%B0%E5%92%8CAGI%E7%9A%84%E8%B5%B7%E6%BA%90.html) [什么是perplexity](https://mp.weixin.qq.com/s?__biz=MzkyOTY4Mjc4MQ==&mid=2247483766&idx=1&sn=56563281557b6f58feacb935eb6a872a&chksm=c2048544f5730c52cf2bf4c9ed60ac0a21793bacdddc4d63b481d4aa887bc6a838fecf0b6cc7&token=607452854&lang=zh_CN#rd) [Pre-Training预训练Llama-3.1 405B超大杯，需要多少算力资源？](https://mp.weixin.qq.com/s?__biz=MzkyOTY4Mjc4MQ==&mid=2247483839&idx=1&sn=3f35dfe8ed2c87bf4c0b4ac7bfa3e6a9&chksm=c204858df5730c9b8a152a0330dee0183467a063c25aadd0da7cc47d9d5b2f97347fab22708d&token=607452854&lang=zh_CN#rd) ### 第一章-大模型之Pre-Training **[⬆ 一键返回目录](#目录)** #### 架构 [10分钟搞清楚为什么Transformer中使用LayerNorm而不是BatchNorm](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/10%E5%88%86%E9%92%9F%E6%90%9E%E6%B8%85%E6%A5%9A%E4%B8%BA%E4%BB%80%E4%B9%88Transformer%E4%B8%AD%E4%BD%BF%E7%94%A8LayerNorm%E8%80%8C%E4%B8%8D%E6%98%AFBatchNorm.html) [混合专家模型MoE详解节选](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E6%B7%B7%E5%90%88%E4%B8%93%E5%AE%B6%E6%A8%A1%E5%9E%8BMoE%E8%AF%A6%E8%A7%A3%E8%8A%82%E9%80%89.html) [最简单的方式理解Mamba（中文翻译）](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E6%9C%80%E7%AE%80%E5%8D%95%E7%9A%84%E6%96%B9%E5%BC%8F%E7%90%86%E8%A7%A3Mamba%EF%BC%88%E4%B8%AD%E6%96%87%E7%BF%BB%E8%AF%91%EF%BC%89.html) [10分钟了解什么是多模态大模型](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/10%E5%88%86%E9%92%9F%E4%BA%86%E8%A7%A3%E4%BB%80%E4%B9%88%E6%98%AF%E5%A4%9A%E6%A8%A1%E6%80%81%E5%A4%A7%E6%A8%A1%E5%9E%8B.html) #### Optimizer [全网最全的神经网络优化器optimizer总结](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E5%85%A8%E7%BD%91%E6%9C%80%E5%85%A8%E7%9A%84%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C%E4%BC%98%E5%8C%96%E5%99%A8optimizer%E6%80%BB%E7%BB%93.html) [神经网络的优化器（一）综述](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C%E7%9A%84%E4%BC%98%E5%8C%96%E5%99%A8%EF%BC%88%E4%B8%80%EF%BC%89%E6%A6%82%E8%BF%B0.html) [神经网络的优化器（二）SGD](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C%E7%9A%84%E4%BC%98%E5%8C%96%E5%99%A8%EF%BC%88%E4%BA%8C%EF%BC%89SGD.html) [神经网络的优化器（三）Momentum](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C%E7%9A%84%E4%BC%98%E5%8C%96%E5%99%A8%EF%BC%88%E4%B8%89%EF%BC%89Momentum.html) [神经网络的优化器（四）ASGD](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C%E7%9A%84%E4%BC%98%E5%8C%96%E5%99%A8%EF%BC%88%E5%9B%9B%EF%BC%89ASGD.html) [神经网络的优化器（五）Rprop](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C%E7%9A%84%E4%BC%98%E5%8C%96%E5%99%A8%EF%BC%88%E4%BA%94%EF%BC%89Rprop.html) [神经网络的优化器（六）AdaGrad](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C%E7%9A%84%E4%BC%98%E5%8C%96%E5%99%A8%EF%BC%88%E5%85%AD%EF%BC%89AdaGrad.html) [神经网络的优化器（七）AdaDeleta](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C%E7%9A%84%E4%BC%98%E5%8C%96%E5%99%A8%EF%BC%88%E4%B8%83%EF%BC%89AdaDeleta.html) [神经网络的优化器（八）RMSprop](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C%E7%9A%84%E4%BC%98%E5%8C%96%E5%99%A8%EF%BC%88%E5%85%AB%EF%BC%89RMSprop.html) [神经网络的优化器（九）Adam](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C%E7%9A%84%E4%BC%98%E5%8C%96%E5%99%A8%EF%BC%88%E4%B9%9D%EF%BC%89Adam.html) [神经网络的优化器（十）Nadam](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C%E7%9A%84%E4%BC%98%E5%8C%96%E5%99%A8%EF%BC%88%E5%8D%81%EF%BC%89Nadam.html) [神经网络的优化器（十一）AdamW](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C%E7%9A%84%E4%BC%98%E5%8C%96%E5%99%A8%EF%BC%88%E5%8D%81%E4%B8%80%EF%BC%89AdamW.html) [神经网络的优化器（十二）RAdam](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C%E7%9A%84%E4%BC%98%E5%8C%96%E5%99%A8%EF%BC%88%E5%8D%81%E4%BA%8C%EF%BC%89RAdam.html) #### 激活函数 [为什么大型语言模型都在使用SwiGLU作为激活函数？](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E4%B8%BA%E4%BB%80%E4%B9%88%E5%A4%A7%E5%9E%8B%E8%AF%AD%E8%A8%80%E6%A8%A1%E5%9E%8B%E9%83%BD%E5%9C%A8%E4%BD%BF%E7%94%A8SwiGLU%E4%BD%9C%E4%B8%BA%E6%BF%80%E6%B4%BB%E5%87%BD%E6%95%B0%EF%BC%9F.html) [神经网络的激活函数（一）概述](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C%E7%9A%84%E6%BF%80%E6%B4%BB%E5%87%BD%E6%95%B0%EF%BC%88%E4%B8%80%EF%BC%89%E6%A6%82%E8%BF%B0.html) [神经网络的激活函数（二）Sigmiod、Softmax和Tanh](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C%E7%9A%84%E6%BF%80%E6%B4%BB%E5%87%BD%E6%95%B0%EF%BC%88%E4%BA%8C%EF%BC%89Sigmiod%E3%80%81Softmax%E5%92%8CTanh.html) [神经网络的激活函数（三）ReLU和它的变种](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C%E7%9A%84%E6%BF%80%E6%B4%BB%E5%87%BD%E6%95%B0%EF%BC%88%E4%B8%89%EF%BC%89ReLU%E5%92%8C%E5%AE%83%E7%9A%84%E5%8F%98%E7%A7%8D.html) [神经网络的激活函数（四）ELU和它的变种SELU](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C%E7%9A%84%E6%BF%80%E6%B4%BB%E5%87%BD%E6%95%B0%EF%BC%88%E5%9B%9B%EF%BC%89ELU%E5%92%8C%E5%AE%83%E7%9A%84%E5%8F%98%E7%A7%8DSELU.html) [神经网络的激活函数（五）门控系列-GLU、Swish和SwiGLU](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C%E7%9A%84%E6%BF%80%E6%B4%BB%E5%87%BD%E6%95%B0%EF%BC%88%E4%BA%94%EF%BC%89%E9%97%A8%E6%8E%A7%E7%B3%BB%E5%88%97-GLU%E3%80%81Swish%E5%92%8CSwiGLU.html) [神经网络的激活函数（六）GELU和Mish](<01-第一章-预训练/神经网络的激活函数（六）GELU和Mish.md>) #### Attention机制 [看懂FlashAttention需要的数学储备是？高考数学最后一道大题](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E7%9C%8B%E6%87%82FlashAttention%E9%9C%80%E8%A6%81%E7%9A%84%E6%95%B0%E5%AD%A6%E5%82%A8%E5%A4%87%E6%98%AF%EF%BC%9F%E9%AB%98%E8%80%83%E6%95%B0%E5%AD%A6%E6%9C%80%E5%90%8E%E4%B8%80%E9%81%93%E5%A4%A7%E9%A2%98%EF%BC%81.html) [FlashAttentionv2相比于v1有哪些更新？](<01-第一章-预训练/FlashAttentionv2相比于v1有哪些更新？.md>) [为什么会发展出Multi-Query-Attention和Group-Query-Attention](<01-第一章-预训练/为什么会发展出Multi-Query-Attention和Group-Query-Attention.md>) [一文了解Deepseek系列中的MLA技术](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E4%B8%80%E6%96%87%E4%BA%86%E8%A7%A3Deepseek%E7%B3%BB%E5%88%97%E4%B8%AD%E7%9A%84MLA%E6%8A%80%E6%9C%AF.html) #### 位置编码 [什么是大模型的位置编码Position-Encoding](<01-第一章-预训练/什么是大模型的位置编码Position-Encoding.md>) [复变函数在大模型位置编码中的应用](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E5%A4%8D%E5%8F%98%E5%87%BD%E6%95%B0%E5%9C%A8%E5%A4%A7%E6%A8%A1%E5%9E%8B%E4%BD%8D%E7%BD%AE%E7%BC%96%E7%A0%81%E4%B8%AD%E7%9A%84%E5%BA%94%E7%94%A8.html) [最美的数学公式-欧拉公式](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E6%9C%80%E7%BE%8E%E7%9A%84%E6%95%B0%E5%AD%A6%E5%85%AC%E5%BC%8F-%E6%AC%A7%E6%8B%89%E5%85%AC%E5%BC%8F.html) [从欧拉公式的美到旋转位置编码RoPE](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E4%BB%8E%E6%AC%A7%E6%8B%89%E5%85%AC%E5%BC%8F%E7%9A%84%E7%BE%8E%E5%88%B0%E6%97%8B%E8%BD%AC%E4%BD%8D%E7%BD%AE%E7%BC%96%E7%A0%81RoPE.html) #### Tokenizer [全网最全的大模型分词器（Tokenizer）总结](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E5%85%A8%E7%BD%91%E6%9C%80%E5%85%A8%E7%9A%84%E5%A4%A7%E6%A8%A1%E5%9E%8B%E5%88%86%E8%AF%8D%E5%99%A8%EF%BC%88Tokenizer%EF%BC%89%E6%80%BB%E7%BB%93.html) [搞懂大模型的分词器（一）](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E6%90%9E%E6%87%82%E5%A4%A7%E6%A8%A1%E5%9E%8B%E7%9A%84%E5%88%86%E8%AF%8D%E5%99%A8%EF%BC%88%E4%B8%80%EF%BC%89.html) [搞懂大模型的分词器（二）](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E6%90%9E%E6%87%82%E5%A4%A7%E6%A8%A1%E5%9E%8B%E7%9A%84%E5%88%86%E8%AF%8D%E5%99%A8%EF%BC%88%E4%BA%8C%EF%BC%89.html) [搞懂大模型的分词器（三）](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E6%90%9E%E6%87%82%E5%A4%A7%E6%A8%A1%E5%9E%8B%E7%9A%84%E5%88%86%E8%AF%8D%E5%99%A8%EF%BC%88%E4%B8%89%EF%BC%89.html) [搞懂大模型的分词器（四）](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E6%90%9E%E6%87%82%E5%A4%A7%E6%A8%A1%E5%9E%8B%E7%9A%84%E5%88%86%E8%AF%8D%E5%99%A8%EF%BC%88%E5%9B%9B%EF%BC%89.html) [搞懂大模型的分词器（五）](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E6%90%9E%E6%87%82%E5%A4%A7%E6%A8%A1%E5%9E%8B%E7%9A%84%E5%88%86%E8%AF%8D%E5%99%A8%EF%BC%88%E4%BA%94%EF%BC%89.html) [搞懂大模型的分词器（六）](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E6%90%9E%E6%87%82%E5%A4%A7%E6%A8%A1%E5%9E%8B%E7%9A%84%E5%88%86%E8%AF%8D%E5%99%A8%EF%BC%88%E5%85%AD%EF%BC%89.html) #### 并行策略 [大模型并行策略[中文翻译]](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E5%B9%B6%E8%A1%8C%E7%AD%96%E7%95%A5%5B%E4%B8%AD%E6%96%87%E7%BF%BB%E8%AF%91%5D.html) [大模型分布式训练并行技术（一）概述](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E5%88%86%E5%B8%83%E5%BC%8F%E8%AE%AD%E7%BB%83%E5%B9%B6%E8%A1%8C%E6%8A%80%E6%9C%AF%EF%BC%88%E4%B8%80%EF%BC%89%E6%A6%82%E8%BF%B0.html) [大模型分布式训练并行技术（二）数据并行](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E5%88%86%E5%B8%83%E5%BC%8F%E8%AE%AD%E7%BB%83%E5%B9%B6%E8%A1%8C%E6%8A%80%E6%9C%AF%EF%BC%88%E4%BA%8C%EF%BC%89%E6%95%B0%E6%8D%AE%E5%B9%B6%E8%A1%8C.html) [大模型分布式训练并行技术（三）流水线并行](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E5%88%86%E5%B8%83%E5%BC%8F%E8%AE%AD%E7%BB%83%E5%B9%B6%E8%A1%8C%E6%8A%80%E6%9C%AF%EF%BC%88%E4%B8%89%EF%BC%89%E6%B5%81%E6%B0%B4%E7%BA%BF%E5%B9%B6%E8%A1%8C.html) [大模型分布式训练并行技术（四）张量并行](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E5%88%86%E5%B8%83%E5%BC%8F%E8%AE%AD%E7%BB%83%E5%B9%B6%E8%A1%8C%E6%8A%80%E6%9C%AF%EF%BC%88%E5%9B%9B%EF%BC%89%E5%BC%A0%E9%87%8F%E5%B9%B6%E8%A1%8C.html) [大模型分布式训练并行技术（五）混合并行](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E5%88%86%E5%B8%83%E5%BC%8F%E8%AE%AD%E7%BB%83%E5%B9%B6%E8%A1%8C%E6%8A%80%E6%9C%AF%EF%BC%88%E4%BA%94%EF%BC%89%E6%B7%B7%E5%90%88%E5%B9%B6%E8%A1%8C.html) #### 大模型训练框架 [大模型训练框架（一）综述](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E8%AE%AD%E7%BB%83%E6%A1%86%E6%9E%B6%EF%BC%88%E4%B8%80%EF%BC%89%E7%BB%BC%E8%BF%B0.html) [大模型训练框架（二）FSDP](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E8%AE%AD%E7%BB%83%E6%A1%86%E6%9E%B6%EF%BC%88%E4%BA%8C%EF%BC%89FSDP.html) [大模型训练框架（三）DeepSpeed](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E8%AE%AD%E7%BB%83%E6%A1%86%E6%9E%B6%EF%BC%88%E4%B8%89%EF%BC%89DeepSpeed.html) [大模型训练框架（四）Megatron-LM](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E8%AE%AD%E7%BB%83%E6%A1%86%E6%9E%B6%EF%BC%88%E5%9B%9B%EF%BC%89Megatron-LM.html) [大模型训练框架（五）Accelerate](/LLMForEverybody/01-%E7%AC%AC%E4%B8%80%E7%AB%A0-%E9%A2%84%E8%AE%AD%E7%BB%83/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E8%AE%AD%E7%BB%83%E6%A1%86%E6%9E%B6%EF%BC%88%E4%BA%94%EF%BC%89Accelerate.html) ### 第二章-大模型之部署与推理 **[⬆ 一键返回目录](#目录)** [10分钟私有化部署大模型到本地](/LLMForEverybody/02-%E7%AC%AC%E4%BA%8C%E7%AB%A0-%E9%83%A8%E7%BD%B2%E4%B8%8E%E6%8E%A8%E7%90%86/10%E5%88%86%E9%92%9F%E7%A7%81%E6%9C%89%E5%8C%96%E9%83%A8%E7%BD%B2%E5%A4%A7%E6%A8%A1%E5%9E%8B%E5%88%B0%E6%9C%AC%E5%9C%B0.html) [模型部署不求人！从TTFT到Throughput的性能估算终极公式](/LLMForEverybody/02-%E7%AC%AC%E4%BA%8C%E7%AB%A0-%E9%83%A8%E7%BD%B2%E4%B8%8E%E6%8E%A8%E7%90%86/%E6%A8%A1%E5%9E%8B%E9%83%A8%E7%BD%B2%E4%B8%8D%E6%B1%82%E4%BA%BA%EF%BC%81%E4%BB%8ETTFT%E5%88%B0Throughput%E7%9A%84%E6%80%A7%E8%83%BD%E4%BC%B0%E7%AE%97%E7%BB%88%E6%9E%81%E5%85%AC%E5%BC%8F.html) [大模型output-token为什么比input-token贵](<02-第二章-部署与推理/大模型output-token为什么比input-token贵？.md>) [如何评判大模型的输出速度？首Token延迟和其余Token延迟有什么不同？](/LLMForEverybody/02-%E7%AC%AC%E4%BA%8C%E7%AB%A0-%E9%83%A8%E7%BD%B2%E4%B8%8E%E6%8E%A8%E7%90%86/%E5%A6%82%E4%BD%95%E8%AF%84%E5%88%A4%E5%A4%A7%E6%A8%A1%E5%9E%8B%E7%9A%84%E8%BE%93%E5%87%BA%E9%80%9F%E5%BA%A6%EF%BC%9F%E9%A6%96Token%E5%BB%B6%E8%BF%9F%E5%92%8C%E5%85%B6%E4%BD%99Token%E5%BB%B6%E8%BF%9F%E6%9C%89%E4%BB%80%E4%B9%88%E4%B8%8D%E5%90%8C%EF%BC%9F.html) [大模型的latency（延迟）和throughput（吞吐量）有什么区别](/LLMForEverybody/02-%E7%AC%AC%E4%BA%8C%E7%AB%A0-%E9%83%A8%E7%BD%B2%E4%B8%8E%E6%8E%A8%E7%90%86/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E7%9A%84latency%EF%BC%88%E5%BB%B6%E8%BF%9F%EF%BC%89%E5%92%8Cthroughput%EF%BC%88%E5%90%9E%E5%90%90%E9%87%8F%EF%BC%89%E6%9C%89%E4%BB%80%E4%B9%88%E5%8C%BA%E5%88%AB.html) [vLLM使用PagedAttention轻松、快速且廉价地提供LLM服务（中文版翻译）](<02-第二章-部署与推理/vLLM使用PagedAttention轻松、快速且廉价地提供LLM服务（中文版翻译）.md>) [DevOps，AIOps，MLOps，LLMOps，这些Ops都是什么？](<02-第二章-部署与推理/DevOps，AIOps，MLOps，LLMOps，这些Ops都是什么？.md>) [大模型推理框架（一）综述](/LLMForEverybody/02-%E7%AC%AC%E4%BA%8C%E7%AB%A0-%E9%83%A8%E7%BD%B2%E4%B8%8E%E6%8E%A8%E7%90%86/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E6%8E%A8%E7%90%86%E6%A1%86%E6%9E%B6%EF%BC%88%E4%B8%80%EF%BC%89%E7%BB%BC%E8%BF%B0.html) [大模型推理框架（二）vLLM](/LLMForEverybody/02-%E7%AC%AC%E4%BA%8C%E7%AB%A0-%E9%83%A8%E7%BD%B2%E4%B8%8E%E6%8E%A8%E7%90%86/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E6%8E%A8%E7%90%86%E6%A1%86%E6%9E%B6%EF%BC%88%E4%BA%8C%EF%BC%89vLLM.html) [大模型推理框架（三）Text generation inference (TGI)](<02-第二章-部署与推理/大模型推理框架（三）Text generation inference (TGI).md>) [大模型推理框架（四）TensorRT-LLM](/LLMForEverybody/02-%E7%AC%AC%E4%BA%8C%E7%AB%A0-%E9%83%A8%E7%BD%B2%E4%B8%8E%E6%8E%A8%E7%90%86/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E6%8E%A8%E7%90%86%E6%A1%86%E6%9E%B6%EF%BC%88%E5%9B%9B%EF%BC%89TensorRT-LLM.html) [大模型推理框架（五）Ollama](/LLMForEverybody/02-%E7%AC%AC%E4%BA%8C%E7%AB%A0-%E9%83%A8%E7%BD%B2%E4%B8%8E%E6%8E%A8%E7%90%86/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E6%8E%A8%E7%90%86%E6%A1%86%E6%9E%B6%EF%BC%88%E4%BA%94%EF%BC%89Ollama.html) ### 第三章-大模型微调 **[⬆ 一键返回目录](#目录)** [10分钟教你套壳（不是）Llama-3，小白也能上手](https://mp.weixin.qq.com/s?__biz=MzkyOTY4Mjc4MQ==&mid=2247483895&idx=1&sn=72e9ca9874aeb4fd51a076c14341242f&chksm=c20485c5f5730cd38f43cf32cc851ade15286d5bd14c8107906449f8c52db9d3bfd72cfc40c8&token=607452854&lang=zh_CN#rd) [大模型的参数高效微调（PEFT），LoRA微调以及其它](/LLMForEverybody/03-%E7%AC%AC%E4%B8%89%E7%AB%A0-%E5%BE%AE%E8%B0%83/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E7%9A%84%E5%8F%82%E6%95%B0%E9%AB%98%E6%95%88%E5%BE%AE%E8%B0%83%EF%BC%88PEFT%EF%BC%89%EF%BC%8CLoRA%E5%BE%AE%E8%B0%83%E4%BB%A5%E5%8F%8A%E5%85%B6%E5%AE%83.html) [大模型微调之Soft prompts（一）概述](<03-第三章-微调/大模型微调之Soft prompts（一）概述.md>) [大模型微调之Soft prompts（二）Prompt Tuning](<03-第三章-微调/大模型微调之Soft prompts（二）Prompt Tuning.md>) [大模型微调之Soft prompts（三）Prefix-Tuning](<03-第三章-微调/大模型微调之Soft prompts（三）Prefix-Tuning.md>) [大模型微调之Soft prompts（四）P-Tuning](<03-第三章-微调/大模型微调之Soft prompts（四）P-Tuning.md>) [大模型微调之Soft prompts（五）Multitask prompt tuning](<03-第三章-微调/大模型微调之Soft prompts（五）Multitask prompt tuning.md>) [大模型微调之Adapters（一）概述](/LLMForEverybody/03-%E7%AC%AC%E4%B8%89%E7%AB%A0-%E5%BE%AE%E8%B0%83/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E5%BE%AE%E8%B0%83%E4%B9%8BAdapters%EF%BC%88%E4%B8%80%EF%BC%89%E6%A6%82%E8%BF%B0.html) [大模型微调之Adapters（二）LoRA](/LLMForEverybody/03-%E7%AC%AC%E4%B8%89%E7%AB%A0-%E5%BE%AE%E8%B0%83/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E5%BE%AE%E8%B0%83%E4%B9%8BAdapters%EF%BC%88%E4%BA%8C%EF%BC%89LoRA.html) [大模型微调之Adapters（三）QLoRA](/LLMForEverybody/03-%E7%AC%AC%E4%B8%89%E7%AB%A0-%E5%BE%AE%E8%B0%83/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E5%BE%AE%E8%B0%83%E4%B9%8BAdapters%EF%BC%88%E4%B8%89%EF%BC%89QLoRA.html) [大模型微调之Adapters（四）AdaLoRA](/LLMForEverybody/03-%E7%AC%AC%E4%B8%89%E7%AB%A0-%E5%BE%AE%E8%B0%83/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E5%BE%AE%E8%B0%83%E4%B9%8BAdapters%EF%BC%88%E5%9B%9B%EF%BC%89AdaLoRA.html) [大模型微调框架（一）综述](03-第三章-微调/assest/大模型微调框架（一）综述) [大模型微调框架（二）Huggingface-PEFT](03-第三章-微调/assest/大模型微调框架（二）Huggingface-PEFT) [大模型微调框架（三）Llama-Factory](03-第三章-微调/assest/大模型微调框架（三）Llama-Factory) ### 第四章-大模型量化 **[⬆ 一键返回目录](#目录)** [10分钟理解大模型的量化](/LLMForEverybody/04-%E7%AC%AC%E5%9B%9B%E7%AB%A0-%E9%87%8F%E5%8C%96/10%E5%88%86%E9%92%9F%E7%90%86%E8%A7%A3%E5%A4%A7%E6%A8%A1%E5%9E%8B%E7%9A%84%E9%87%8F%E5%8C%96.html) [大模型量化认知的三重境界](/LLMForEverybody/04-%E7%AC%AC%E5%9B%9B%E7%AB%A0-%E9%87%8F%E5%8C%96/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E9%87%8F%E5%8C%96%E8%AE%A4%E7%9F%A5%E7%9A%84%E4%B8%89%E9%87%8D%E5%A2%83%E7%95%8C.html) ### 第五章-显卡与大模型并行 **[⬆ 一键返回目录](#目录)** [AGI时代人人都可以看懂的显卡知识](https://mp.weixin.qq.com/s?__biz=MzkyOTY4Mjc4MQ==&mid=2247484001&idx=1&sn=5a178a9006cc308f2e84b5a0db6994ff&chksm=c2048653f5730f45b3b08af03023aee24969d89ad5586e4e25c68b09393bf5a8abfd9670a6f3&token=607452854&lang=zh_CN#rd) [Transformer架构的GPU并行和之前的NLP算法有什么不同？](/LLMForEverybody/05-%E7%AC%AC%E4%BA%94%E7%AB%A0-%E6%98%BE%E5%8D%A1%E4%B8%8E%E5%B9%B6%E8%A1%8C/Transformer%E6%9E%B6%E6%9E%84%E7%9A%84GPU%E5%B9%B6%E8%A1%8C%E5%92%8C%E4%B9%8B%E5%89%8D%E7%9A%84NLP%E7%AE%97%E6%B3%95%E6%9C%89%E4%BB%80%E4%B9%88%E4%B8%8D%E5%90%8C%EF%BC%9F.html) [大模型部署三要素：显存、计算与通信深度解析](/LLMForEverybody/05-%E7%AC%AC%E4%BA%94%E7%AB%A0-%E6%98%BE%E5%8D%A1%E4%B8%8E%E5%B9%B6%E8%A1%8C/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E9%83%A8%E7%BD%B2%E4%B8%89%E8%A6%81%E7%B4%A0%EF%BC%9A%E6%98%BE%E5%AD%98%E3%80%81%E8%AE%A1%E7%AE%97%E4%B8%8E%E9%80%9A%E4%BF%A1%E6%B7%B1%E5%BA%A6%E8%A7%A3%E6%9E%90.html) ### 第六章-Prompt-Engineering **[⬆ 一键返回目录](#目录)** [过去式就能越狱大模型？一文了解大模型安全攻防战](<06-第六章-Prompt Engineering/过去式就能越狱大模型？一文了解大模型安全攻防战.md>) [万字长文Prompt-Engineering-解锁大模型的力量](<06-第六章-Prompt Engineering/万字长文Prompt-Engineering-解锁大模型的力量.md>) [COT思维链，TOT思维树，GOT思维图，这些都是什么](<06-第六章-Prompt Engineering/COT思维链，TOT思维树，GOT思维图，这些都是什么.md>) ### 第七章-Agent **[⬆ 一键返回目录](#目录)** [如何设计智能体架构：参考OpenAI还是Anthropic?](07-第七章-Agent/如何设计智能体架构：参考OpenAI还是Anthropic?.md) [MCP：基础概念、快速应用和背后原理](/LLMForEverybody/07-%E7%AC%AC%E4%B8%83%E7%AB%A0-Agent/MCP%EF%BC%9A%E5%9F%BA%E7%A1%80%E6%A6%82%E5%BF%B5%E3%80%81%E5%BF%AB%E9%80%9F%E5%BA%94%E7%94%A8%E5%92%8C%E8%83%8C%E5%90%8E%E5%8E%9F%E7%90%86.html) [LLM应用落地指南之应用的分类(一)](07-第七章-Agent/LLM应用落地指南之应用的分类(一).md) [LLM应用落地之架构设计（二）](/LLMForEverybody/07-%E7%AC%AC%E4%B8%83%E7%AB%A0-Agent/LLM%E5%BA%94%E7%94%A8%E8%90%BD%E5%9C%B0%E4%B9%8B%E6%9E%B6%E6%9E%84%E8%AE%BE%E8%AE%A1%EF%BC%88%E4%BA%8C%EF%BC%89.html) [LLM应用落地之Text-2-SQL（三）](/LLMForEverybody/07-%E7%AC%AC%E4%B8%83%E7%AB%A0-Agent/LLM%E5%BA%94%E7%94%A8%E8%90%BD%E5%9C%B0%E4%B9%8BText-2-SQL%EF%BC%88%E4%B8%89%EF%BC%89.html) [开发大模型or使用大模型](/LLMForEverybody/07-%E7%AC%AC%E4%B8%83%E7%AB%A0-Agent/%E5%BC%80%E5%8F%91%E5%A4%A7%E6%A8%A1%E5%9E%8Bor%E4%BD%BF%E7%94%A8%E5%A4%A7%E6%A8%A1%E5%9E%8B.html) [Agent设计范式与常见框架](/LLMForEverybody/07-%E7%AC%AC%E4%B8%83%E7%AB%A0-Agent/Agent%E8%AE%BE%E8%AE%A1%E8%8C%83%E5%BC%8F%E4%B8%8E%E5%B8%B8%E8%A7%81%E6%A1%86%E6%9E%B6.html) [langchain向左coze向右](/LLMForEverybody/07-%E7%AC%AC%E4%B8%83%E7%AB%A0-Agent/langchain%E5%90%91%E5%B7%A6coze%E5%90%91%E5%8F%B3.html) #### RAG [向量数据库拥抱大模型](/LLMForEverybody/07-%E7%AC%AC%E4%B8%83%E7%AB%A0-Agent/%E5%90%91%E9%87%8F%E6%95%B0%E6%8D%AE%E5%BA%93%E6%8B%A5%E6%8A%B1%E5%A4%A7%E6%A8%A1%E5%9E%8B.html) [搭配Knowledge-Graph的RAG架构](<07-第七章-Agent/搭配Knowledge-Graph的RAG架构.md>) [GraphRAG：解锁大模型对叙述性私人数据的检索能力（中文翻译）](<07-第七章-Agent/GraphRAG解锁大模型对叙述性私人数据的检索能力（中文翻译）.md>) [干货：落地企业级RAG的实践指南](<07-第七章-Agent/干货-落地企业级RAG的实践指南.md>) [10分钟了解如何进行多模态RAG](/LLMForEverybody/07-%E7%AC%AC%E4%B8%83%E7%AB%A0-Agent/10%E5%88%86%E9%92%9F%E4%BA%86%E8%A7%A3%E5%A6%82%E4%BD%95%E8%BF%9B%E8%A1%8C%E5%A4%9A%E6%A8%A1%E6%80%81RAG.html) ### 第八章-大模型企业落地 **[⬆ 一键返回目录](#目录)** [CRUD-ETL工程师的末日从NL2SQL到ChatBI](/LLMForEverybody/08-%E7%AC%AC%E5%85%AB%E7%AB%A0-%E5%A4%A7%E6%A8%A1%E5%9E%8B%E4%BC%81%E4%B8%9A%E8%90%BD%E5%9C%B0/CRUDETL%E5%B7%A5%E7%A8%8B%E5%B8%88%E7%9A%84%E6%9C%AB%E6%97%A5%E4%BB%8ENL2SQL%E5%88%B0ChatBI.html) [大模型落地难点之幻觉](/LLMForEverybody/08-%E7%AC%AC%E5%85%AB%E7%AB%A0-%E5%A4%A7%E6%A8%A1%E5%9E%8B%E4%BC%81%E4%B8%9A%E8%90%BD%E5%9C%B0/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E8%90%BD%E5%9C%B0%E9%9A%BE%E7%82%B9%E4%B9%8B%E5%B9%BB%E8%A7%89.html) [大模型落地难点之输出的不确定性](/LLMForEverybody/08-%E7%AC%AC%E5%85%AB%E7%AB%A0-%E5%A4%A7%E6%A8%A1%E5%9E%8B%E4%BC%81%E4%B8%9A%E8%90%BD%E5%9C%B0/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E8%90%BD%E5%9C%B0%E9%9A%BE%E7%82%B9%E4%B9%8B%E8%BE%93%E5%87%BA%E7%9A%84%E4%B8%8D%E7%A1%AE%E5%AE%9A%E6%80%A7.html) [大模型落地难点之结构化输出](/LLMForEverybody/08-%E7%AC%AC%E5%85%AB%E7%AB%A0-%E5%A4%A7%E6%A8%A1%E5%9E%8B%E4%BC%81%E4%B8%9A%E8%90%BD%E5%9C%B0/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E8%90%BD%E5%9C%B0%E9%9A%BE%E7%82%B9%E4%B9%8B%E7%BB%93%E6%9E%84%E5%8C%96%E8%BE%93%E5%87%BA.html) [大模型应用涌现出的新工作机会-红队测试Red-teaming](/LLMForEverybody/08-%E7%AC%AC%E5%85%AB%E7%AB%A0-%E5%A4%A7%E6%A8%A1%E5%9E%8B%E4%BC%81%E4%B8%9A%E8%90%BD%E5%9C%B0/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E5%BA%94%E7%94%A8%E6%B6%8C%E7%8E%B0%E5%87%BA%E7%9A%84%E6%96%B0%E5%B7%A5%E4%BD%9C%E6%9C%BA%E4%BC%9A-%E7%BA%A2%E9%98%9F%E6%B5%8B%E8%AF%95Red-teaming.html) [大模型复读机问题](/LLMForEverybody/08-%E7%AC%AC%E5%85%AB%E7%AB%A0-%E5%A4%A7%E6%A8%A1%E5%9E%8B%E4%BC%81%E4%B8%9A%E8%90%BD%E5%9C%B0/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E5%A4%8D%E8%AF%BB%E6%9C%BA%E9%97%AE%E9%A2%98.html) ### 第九章-大模型评估指标 [大模型有哪些评估指标？](/LLMForEverybody/09-%E7%AC%AC%E4%B9%9D%E7%AB%A0-%E8%AF%84%E4%BC%B0%E6%8C%87%E6%A0%87/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E6%9C%89%E5%93%AA%E4%BA%9B%E8%AF%84%E4%BC%B0%E6%8C%87%E6%A0%87%EF%BC%9F.html) [大模型性能评测之大海捞针(Needle In A Haystack)](/LLMForEverybody/09-%E7%AC%AC%E4%B9%9D%E7%AB%A0-%E8%AF%84%E4%BC%B0%E6%8C%87%E6%A0%87/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E6%80%A7%E8%83%BD%E8%AF%84%E6%B5%8B%E4%B9%8B%E5%A4%A7%E6%B5%B7%E6%8D%9E%E9%92%88.html) [评估指标/大模型性能评测之数星星](/LLMForEverybody/09-%E7%AC%AC%E4%B9%9D%E7%AB%A0-%E8%AF%84%E4%BC%B0%E6%8C%87%E6%A0%87/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E6%80%A7%E8%83%BD%E8%AF%84%E6%B5%8B%E4%B9%8B%E6%95%B0%E6%98%9F%E6%98%9F.html) ### 第十章-热点 **[⬆ 一键返回目录](#目录)** [Llama 3.1 405B 为什么这么大？](https://mp.weixin.qq.com/s?__biz=MzkyOTY4Mjc4MQ==&mid=2247483782&idx=1&sn=3a14a0cde14eb6643beaeb5b472ffa26&chksm=c20485b4f5730ca2d7b002a29e617a75c08d004a1b3da891ab352cbe31ca37541a546e29abc7&token=607452854&lang=zh_CN#rd) [9.11大于9.9？大模型怎么又翻车了？](https://mp.weixin.qq.com/s?__biz=MzkyOTY4Mjc4MQ==&mid=2247483800&idx=1&sn=48b326352c37d686f7f46ee5df9f00b4&chksm=c20485aaf5730cbca8f0dfcb9746830229b8f07eec092e0e124bc558d1073ee32e3f55716221&token=607452854&lang=zh_CN#rd) [韩国“N 号房”事件因Deep Fake再现，探究背后的技术和应对方法](<10-第十章-热点/韩国“N 号房”事件因Deep-Fake再现，探究背后的技术和应对方法.md>) [我是怎么通过2022下半年软考高级：系统架构设计师考试的](/LLMForEverybody/10-%E7%AC%AC%E5%8D%81%E7%AB%A0-%E7%83%AD%E7%82%B9/%E6%88%91%E6%98%AF%E6%80%8E%E4%B9%88%E9%80%9A%E8%BF%872022%E4%B8%8B%E5%8D%8A%E5%B9%B4%E8%BD%AF%E8%80%83%E9%AB%98%E7%BA%A7%EF%BC%9A%E7%B3%BB%E7%BB%9F%E6%9E%B6%E6%9E%84%E8%AE%BE%E8%AE%A1%E5%B8%88%E8%80%83%E8%AF%95%E7%9A%84.html) [用Exploit and Explore解决不知道吃什么的选择困难症](<10-第十章-热点/用Exploit-and-Explore解决不知道吃什么的选择困难症.md>) ### 第十一章-数学 **[⬆ 一键返回目录](#目录)** #### 线性代数 [0基础学习AI大模型必备数学知识之线性代数（一）](/LLMForEverybody/11-%E7%AC%AC%E5%8D%81%E4%B8%80%E7%AB%A0-%E6%95%B0%E5%AD%A6/linear-algebra/0%E5%9F%BA%E7%A1%80%E5%AD%A6%E4%B9%A0AI%E5%A4%A7%E6%A8%A1%E5%9E%8B%E5%BF%85%E5%A4%87%E6%95%B0%E5%AD%A6%E7%9F%A5%E8%AF%86%E4%B9%8B%E7%BA%BF%E6%80%A7%E4%BB%A3%E6%95%B0%EF%BC%88%E4%B8%80%EF%BC%89.html) [0基础学习AI大模型必备数学知识之线性代数（二）](/LLMForEverybody/11-%E7%AC%AC%E5%8D%81%E4%B8%80%E7%AB%A0-%E6%95%B0%E5%AD%A6/linear-algebra/0%E5%9F%BA%E7%A1%80%E5%AD%A6%E4%B9%A0AI%E5%A4%A7%E6%A8%A1%E5%9E%8B%E5%BF%85%E5%A4%87%E6%95%B0%E5%AD%A6%E7%9F%A5%E8%AF%86%E4%B9%8B%E7%BA%BF%E6%80%A7%E4%BB%A3%E6%95%B0%EF%BC%88%E4%BA%8C%EF%BC%89.html) [0基础学习AI大模型必备数学知识之线性代数（三）](/LLMForEverybody/11-%E7%AC%AC%E5%8D%81%E4%B8%80%E7%AB%A0-%E6%95%B0%E5%AD%A6/linear-algebra/0%E5%9F%BA%E7%A1%80%E5%AD%A6%E4%B9%A0AI%E5%A4%A7%E6%A8%A1%E5%9E%8B%E5%BF%85%E5%A4%87%E6%95%B0%E5%AD%A6%E7%9F%A5%E8%AF%86%E4%B9%8B%E7%BA%BF%E6%80%A7%E4%BB%A3%E6%95%B0%EF%BC%88%E4%B8%89%EF%BC%89.html) #### 微积分 [0基础学习AI大模型必备数学知识之微积分（一）](/LLMForEverybody/11-%E7%AC%AC%E5%8D%81%E4%B8%80%E7%AB%A0-%E6%95%B0%E5%AD%A6/calculus/0%E5%9F%BA%E7%A1%80%E5%AD%A6%E4%B9%A0AI%E5%A4%A7%E6%A8%A1%E5%9E%8B%E5%BF%85%E5%A4%87%E6%95%B0%E5%AD%A6%E7%9F%A5%E8%AF%86%E4%B9%8B%E5%BE%AE%E7%A7%AF%E5%88%86%EF%BC%88%E4%B8%80%EF%BC%89.html) [0基础学习AI大模型必备数学知识之微积分（二）](/LLMForEverybody/11-%E7%AC%AC%E5%8D%81%E4%B8%80%E7%AB%A0-%E6%95%B0%E5%AD%A6/calculus/0%E5%9F%BA%E7%A1%80%E5%AD%A6%E4%B9%A0AI%E5%A4%A7%E6%A8%A1%E5%9E%8B%E5%BF%85%E5%A4%87%E6%95%B0%E5%AD%A6%E7%9F%A5%E8%AF%86%E4%B9%8B%E5%BE%AE%E7%A7%AF%E5%88%86%EF%BC%88%E4%BA%8C%EF%BC%89.html) #### 概率统计 [0基础学习AI大模型必备数学知识之概率统计（一）贝叶斯定理和概率分布](/LLMForEverybody/11-%E7%AC%AC%E5%8D%81%E4%B8%80%E7%AB%A0-%E6%95%B0%E5%AD%A6/Probability&Statistics/0%E5%9F%BA%E7%A1%80%E5%AD%A6%E4%B9%A0AI%E5%A4%A7%E6%A8%A1%E5%9E%8B%E5%BF%85%E5%A4%87%E6%95%B0%E5%AD%A6%E7%9F%A5%E8%AF%86%E4%B9%8B%E6%A6%82%E7%8E%87%E7%BB%9F%E8%AE%A1%EF%BC%88%E4%B8%80%EF%BC%89%E8%B4%9D%E5%8F%B6%E6%96%AF%E5%AE%9A%E7%90%86%E5%92%8C%E6%A6%82%E7%8E%87%E5%88%86%E5%B8%83.html) [0基础学习AI大模型必备数学知识之概率统计（二）概率分布的描述方法](/LLMForEverybody/11-%E7%AC%AC%E5%8D%81%E4%B8%80%E7%AB%A0-%E6%95%B0%E5%AD%A6/Probability&Statistics/0%E5%9F%BA%E7%A1%80%E5%AD%A6%E4%B9%A0AI%E5%A4%A7%E6%A8%A1%E5%9E%8B%E5%BF%85%E5%A4%87%E6%95%B0%E5%AD%A6%E7%9F%A5%E8%AF%86%E4%B9%8B%E6%A6%82%E7%8E%87%E7%BB%9F%E8%AE%A1%EF%BC%88%E4%BA%8C%EF%BC%89%E6%A6%82%E7%8E%87%E5%88%86%E5%B8%83%E7%9A%84%E6%8F%8F%E8%BF%B0%E6%96%B9%E6%B3%95.html) [0基础学习AI大模型必备数学知识之概率统计（三）中心极限定理](/LLMForEverybody/11-%E7%AC%AC%E5%8D%81%E4%B8%80%E7%AB%A0-%E6%95%B0%E5%AD%A6/Probability&Statistics/0%E5%9F%BA%E7%A1%80%E5%AD%A6%E4%B9%A0AI%E5%A4%A7%E6%A8%A1%E5%9E%8B%E5%BF%85%E5%A4%87%E6%95%B0%E5%AD%A6%E7%9F%A5%E8%AF%86%E4%B9%8B%E6%A6%82%E7%8E%87%E7%BB%9F%E8%AE%A1%EF%BC%88%E4%B8%89%EF%BC%89%E4%B8%AD%E5%BF%83%E6%9E%81%E9%99%90%E5%AE%9A%E7%90%86.html)

🌐 点击 LearnLLM.AI | 学习大模型，从这里开始

Star History Chart

This site is open source. Improve this page.