[{"title":"( 103 个子文件 55.69MB ) LLM八股文知识点集合","children":[{"title":".gitignore <span style='color:#111;'> 247B </span>","children":null,"spread":false},{"title":"LLms.iml <span style='color:#111;'> 383B </span>","children":null,"spread":false},{"title":"xd.lck <span style='color:#111;'> 20.63KB </span>","children":null,"spread":false},{"title":"9-大模型(LLMs)微调面.pdf <span style='color:#111;'> 2.89MB </span>","children":null,"spread":false},{"title":"22-检索增强生成(RAG) 优化策略篇.pdf <span style='color:#111;'> 2.64MB </span>","children":null,"spread":false},{"title":"37-大模型(LLMs)强化学习——RLHF及其变种面.pdf <span style='color:#111;'> 2.42MB </span>","children":null,"spread":false},{"title":"34-基于lora的llama2二次预训练.pdf <span style='color:#111;'> 2.26MB </span>","children":null,"spread":false},{"title":"14-基于LLM+向量库的文档对话 经验面.pdf <span style='color:#111;'> 2.16MB </span>","children":null,"spread":false},{"title":"16-LLM文档对话 —— pdf解析关键问题.pdf <span style='color:#111;'> 2.14MB </span>","children":null,"spread":false},{"title":"77-思维链 Chain-of-Thought(COT)变体篇.pdf <span style='color:#111;'> 1.99MB </span>","children":null,"spread":false},{"title":"44-大模型(LLMs)分布式训练面.pdf <span style='color:#111;'> 1.56MB </span>","children":null,"spread":false},{"title":"26-大模型(LLMs)参数高效微调(PEFT) 面.pdf <span style='color:#111;'> 1.52MB </span>","children":null,"spread":false},{"title":"45-图解分布式训练(一) —— 流水线并行(Pipeline Parallelism).pdf <span style='color:#111;'> 1.44MB </span>","children":null,"spread":false},{"title":"15-大模型 RAG 经验面.pdf <span style='color:#111;'> 1.41MB </span>","children":null,"spread":false},{"title":"23-大模型(LLMs)RAG —— 关键痛点及对应解决方案.pdf <span style='color:#111;'> 1.32MB </span>","children":null,"spread":false},{"title":"55-大模型(LLMs)agent 面.pdf <span style='color:#111;'> 1.30MB </span>","children":null,"spread":false},{"title":"50-图解分布式训练(六)—— Pytorch的 DeepSpeed 详细解析.pdf <span style='color:#111;'> 1.22MB </span>","children":null,"spread":false},{"title":"73-百川智能baichuan7B、13B、53B、baichuan2 总结篇.pdf <span style='color:#111;'> 1.06MB </span>","children":null,"spread":false},{"title":"24-大模型(LLMs)RAG 优化策略 —— RAG-Fusion篇.pdf <span style='color:#111;'> 1.06MB </span>","children":null,"spread":false},{"title":"8-大模型(LLMs)进阶面.pdf <span style='color:#111;'> 1018.61KB </span>","children":null,"spread":false},{"title":"47-图解分布式训练(三) —— nn.parallel.DistributedDataParallel.pdf <span style='color:#111;'> 991.97KB </span>","children":null,"spread":false},{"title":"25-Graph RAG 面 — 一种 基于知识图谱的大模型检索增强实现策略.pdf <span style='color:#111;'> 951.70KB </span>","children":null,"spread":false},{"title":"59-怎么让英文大语言模型支持中文?(二) —— 继续预训练篇.pdf <span style='color:#111;'> 917.66KB </span>","children":null,"spread":false},{"title":"32-大模型(LLMs)增量预训练篇.pdf <span style='color:#111;'> 904.59KB </span>","children":null,"spread":false},{"title":"52-图解分布式训练(八)—— ZeRO 学习.pdf <span style='color:#111;'> 853.90KB </span>","children":null,"spread":false},{"title":"63-LLM(大语言模型)部署加速方法——PagedAttention篇.pdf <span style='color:#111;'> 849.84KB </span>","children":null,"spread":false},{"title":"69-大模型幻觉(LLM Hallucination)面.pdf <span style='color:#111;'> 838.22KB </span>","children":null,"spread":false},{"title":"49-图解分布式训练(五) —— AMP混合精度训练 详细解析.pdf <span style='color:#111;'> 822.80KB </span>","children":null,"spread":false},{"title":"46-图解分布式训练(二) —— nn.DataParallel篇.pdf <span style='color:#111;'> 813.75KB </span>","children":null,"spread":false},{"title":"29-LoRA 系列篇.pdf <span style='color:#111;'> 767.28KB </span>","children":null,"spread":false},{"title":"19-大模型外挂知识库优化——如何利用大模型辅助召回?.pdf <span style='color:#111;'> 733.87KB </span>","children":null,"spread":false},{"title":"41-大模型(LLMs)LLM生成SFT数据方法面.pdf <span style='color:#111;'> 731.09KB </span>","children":null,"spread":false},{"title":"66-纯Python超轻量高性能LLM推理框架 —— LightLLM.pdf <span style='color:#111;'> 711.13KB </span>","children":null,"spread":false},{"title":"80-MOE(Mixture-of-Experts)篇.pdf <span style='color:#111;'> 707.43KB </span>","children":null,"spread":false},{"title":"20-大模型外挂知识库优化——负样本样本挖掘篇.pdf <span style='color:#111;'> 704.02KB </span>","children":null,"spread":false},{"title":"68-SwiftInfer —— 大模型无限流式输入推理飙升46%,打破多轮对话长度限制.pdf <span style='color:#111;'> 702.15KB </span>","children":null,"spread":false},{"title":"30-如何使用 PEFT库 中 LoRA?.pdf <span style='color:#111;'> 695.69KB </span>","children":null,"spread":false},{"title":"31-大模型(LLMs)推理面.pdf <span style='color:#111;'> 675.29KB </span>","children":null,"spread":false},{"title":"56-LLMs 位置编码篇.pdf <span style='color:#111;'> 668.64KB </span>","children":null,"spread":false},{"title":"88-文本分类常见面试篇.pdf <span style='color:#111;'> 668.52KB </span>","children":null,"spread":false},{"title":"64-大模型推理加速工具 —— vLLM.pdf <span style='color:#111;'> 667.78KB </span>","children":null,"spread":false},{"title":"54-pytorch 分布式计算 坑-bug 梳理篇.pdf <span style='color:#111;'> 666.11KB </span>","children":null,"spread":false},{"title":"58-怎么让英文大语言模型支持中文?(一) —— 构建中文tokenization.pdf <span style='color:#111;'> 662.40KB </span>","children":null,"spread":false},{"title":"17-大模型(LLMs)RAG 版面分析——表格识别方法篇.pdf <span style='color:#111;'> 661.74KB </span>","children":null,"spread":false},{"title":"51-图解分布式训练(七)—— accelerate 分布式训练 详细解析.pdf <span style='color:#111;'> 641.54KB </span>","children":null,"spread":false},{"title":"11-大模型(LLMs)langchain 面.pdf <span style='color:#111;'> 630.97KB </span>","children":null,"spread":false},{"title":"21-RAG(Retrieval-Augmented Generation)评测面.pdf <span style='color:#111;'> 616.73KB </span>","children":null,"spread":false},{"title":"65-LLM(大语言模型)部署加速方法——Faster Transformer篇.pdf <span style='color:#111;'> 610.56KB </span>","children":null,"spread":false},{"title":"39-强化学习在自然语言处理下的应用篇.pdf <span style='color:#111;'> 571.58KB </span>","children":null,"spread":false},{"title":"76-思维链 Chain-of-Thought(COT).pdf <span style='color:#111;'> 560.39KB </span>","children":null,"spread":false},{"title":"42-大模型(LLMs)显存问题面.pdf <span style='color:#111;'> 525.45KB </span>","children":null,"spread":false},{"title":"90-命名实体识别常见面试篇.pdf <span style='color:#111;'> 505.51KB </span>","children":null,"spread":false},{"title":"2-Layer normalization ƪ.pdf <span style='color:#111;'> 488.55KB </span>","children":null,"spread":false},{"title":"18-大模型(LLMs)RAG 版面分析——文本分块面.pdf <span style='color:#111;'> 482.88KB </span>","children":null,"spread":false},{"title":"1-大模型(LLMs)基础面.pdf <span style='color:#111;'> 481.56KB </span>","children":null,"spread":false},{"title":"28-提示学习(Prompting)篇.pdf <span style='color:#111;'> 446.51KB </span>","children":null,"spread":false},{"title":"70-大模型的幻觉问题篇.pdf <span style='color:#111;'> 418.09KB </span>","children":null,"spread":false},{"title":"4-Attention 升级面.pdf <span style='color:#111;'> 410.36KB </span>","children":null,"spread":false},{"title":"89-文本摘要常见面试篇.pdf <span style='color:#111;'> 406.69KB </span>","children":null,"spread":false},{"title":"60-怎么让英文大语言模型支持中文?(三) —— 对预训练模型进行指令微调.pdf <span style='color:#111;'> 403.15KB </span>","children":null,"spread":false},{"title":"86-多模态常见面试篇.pdf <span style='color:#111;'> 402.62KB </span>","children":null,"spread":false},{"title":"33-增量预训练(Pretrain)样本拼接篇.pdf <span style='color:#111;'> 379.90KB </span>","children":null,"spread":false},{"title":"57-LLMs Tokenizer ƪ.pdf <span style='color:#111;'> 378.62KB </span>","children":null,"spread":false},{"title":"13-基于langchain RAG问答应用实战.pdf <span style='color:#111;'> 375.71KB </span>","children":null,"spread":false},{"title":"3-LLMs 激活函数篇.pdf <span style='color:#111;'> 374.98KB </span>","children":null,"spread":false},{"title":"12-多轮对话中让AI保持长期记忆的8种优化方式篇.pdf <span style='color:#111;'> 362.00KB </span>","children":null,"spread":false},{"title":"91-向量检索常见面试篇.pdf <span style='color:#111;'> 361.62KB </span>","children":null,"spread":false},{"title":"6-LLMs 损失函数篇.pdf <span style='color:#111;'> 355.57KB </span>","children":null,"spread":false},{"title":"79-LLMs 测试集 中 数据泄露 问题篇.pdf <span style='color:#111;'> 340.31KB </span>","children":null,"spread":false},{"title":"61-大模型(LLMs)加速篇.pdf <span style='color:#111;'> 318.67KB </span>","children":null,"spread":false},{"title":"40-大模型(LLMs)训练集面.pdf <span style='color:#111;'> 304.68KB </span>","children":null,"spread":false},{"title":"71-如何缓解大模型幻觉?.pdf <span style='color:#111;'> 282.51KB </span>","children":null,"spread":false},{"title":"36-大模型(LLMs)强化学习面.pdf <span style='color:#111;'> 277.61KB </span>","children":null,"spread":false},{"title":"78-小样本提示学习篇.pdf <span style='color:#111;'> 276.78KB </span>","children":null,"spread":false},{"title":"48-图解分布式训练(四) —— torch.multiprocessing 详细解析.pdf <span style='color:#111;'> 272.59KB </span>","children":null,"spread":false},{"title":"38-大模型(LLMs)强化学习—— PPO 面.pdf <span style='color:#111;'> 270.99KB </span>","children":null,"spread":false},{"title":"43-显存优化策略篇.pdf <span style='color:#111;'> 264.76KB </span>","children":null,"spread":false},{"title":"92-LLMs 其他 Trick.pdf <span style='color:#111;'> 256.64KB </span>","children":null,"spread":false},{"title":"10-LLMs 训练经验帖.pdf <span style='color:#111;'> 253.51KB </span>","children":null,"spread":false},{"title":"35-大模型(LLMs)评测面.pdf <span style='color:#111;'> 252.63KB </span>","children":null,"spread":false},{"title":"53-大模型分布式训练故障恢复篇.pdf <span style='color:#111;'> 250.03KB </span>","children":null,"spread":false},{"title":"62-LLMs 推理性能面.pdf <span style='color:#111;'> 240.92KB </span>","children":null,"spread":false},{"title":"75-GPT 经验篇.pdf <span style='color:#111;'> 239.28KB </span>","children":null,"spread":false},{"title":"81-大模型蒸馏篇.pdf <span style='color:#111;'> 233.14KB </span>","children":null,"spread":false},{"title":"5-transformers 操作篇.pdf <span style='color:#111;'> 227.10KB </span>","children":null,"spread":false},{"title":"74-LLaMA 常见面试题篇.pdf <span style='color:#111;'> 206.97KB </span>","children":null,"spread":false},{"title":"27-适配器微调(Adapter-tuning)篇.pdf <span style='color:#111;'> 184.62KB </span>","children":null,"spread":false},{"title":"7-相似度函数篇.pdf <span style='color:#111;'> 174.95KB </span>","children":null,"spread":false},{"title":"83-自定义 CUDA 函数的轻量级包装器 —— bitsandbytes篇.pdf <span style='color:#111;'> 172.47KB </span>","children":null,"spread":false},{"title":"87-NLP Trick ƪ.pdf <span style='color:#111;'> 146.94KB </span>","children":null,"spread":false},{"title":"82-LLMs 浮点数篇.pdf <span style='color:#111;'> 133.66KB </span>","children":null,"spread":false},{"title":"85-Token及模型参数准备篇.pdf <span style='color:#111;'> 129.14KB </span>","children":null,"spread":false},{"title":"72-LLMs 对比篇.pdf <span style='color:#111;'> 121.13KB </span>","children":null,"spread":false},{"title":"84-大模型(LLMs)软硬件配置面.pdf <span style='color:#111;'> 93.77KB </span>","children":null,"spread":false},{"title":"67-LLM推理技术之StreamingLLM:如何拥有无限长生成能力.pdf <span style='color:#111;'> 41.91KB </span>","children":null,"spread":false},{"title":"main.py <span style='color:#111;'> 2.64KB </span>","children":null,"spread":false},{"title":"requirements.txt <span style='color:#111;'> 16B </span>","children":null,"spread":false},{"title":"version <span style='color:#111;'> 4B </span>","children":null,"spread":false},{"title":"00000000000.xd <span style='color:#111;'> 5.52KB </span>","children":null,"spread":false},{"title":"workspace.xml <span style='color:#111;'> 4.01KB </span>","children":null,"spread":false},{"title":"......","children":null,"spread":false},{"title":"<span style='color:steelblue;'>文件过多,未全部展示</span>","children":null,"spread":false}],"spread":true}]