掌握 AI 的力量：最高效的大模型学习和解决方案

DeepSeeK 开源周

• 1【Day1】 FlashMLA - let's geek out
• 2【Day2】 DeepEP - 第一个用于 MoE 模型训练和推理的开源 EP 通信库
• 3【Day3】 DeepGEMM - 大道至简的通用矩阵运算
• 4【Day4】并行策略优化 - 将并行进行到底
• 5【Day5】 Fire-Flyer 文件系统 - 让数据处理坐上高铁
• 6【Day6】 DeepSeek 如何做到利润率 545%

DeepSeek 深度教程

• 1DeepSeek从入门到精通
• 2DeepSeek指导手册
• 3DeepSeek-R1：通过强化学习激励LLMs的推理能力
• 4DeepSeekV3技术报告
• 5DeepSeek_VL2技术报告

DeepSeek 深度教程

• 1DeepSeek从入门到精通
• 2DeepSeek本地部署
• 3DeepSeek实战技巧
• 4刘知远团队大模型公开课
• 5李宏毅机器学习系列课程
• 6李沐大神《动手学深度学习》

• 1Prompt-Engineering-Guide
• 2openai-cookbook
• 3anthropic-cookbook
• 4generative-ai-for-beginners
• 5promptflow
• 6Awesome-Prompt-Engineering
• 7LangGPT
• 8SuperPrompt
• 9promptfoo
• 10Learning-Prompt
• 11code2prompt
• 12tree-of-thoughts
• 13Learn_Prompting

经典书籍

• 1大规模语言模型：从理论到实践
• 2大语言模型
• 3动手做AI Agent
• 4Generative AI Handbook: A Roadmap for Learning Resources
• 5Understanding Deep Learning
• 6Taming LLMs: A Practical Guide to LLM Pitfalls with Open Source Software
• 7自然语言处理：大模型理论与实践
• 8Hugging Face Course
• 9Google Machine Learning Crash Course
• 10Illustrated book to learn about Transformers & LLMs
• 11Building LLMs for Production: Enhancing LLM Abilities and Reliability with Prompting, Fine-Tuning, and RAG
• 12面向开发者的LLM入门教程
• 13Foundations of Large Language Models
• 14动手学深度学习
• 15动手学大模型Dive into LLMs
• 16Build a Large Language Model (From Scratch)
• 17多模态大模型
• 18大型语言模型实战指南：应用实践与场景落地
• 19Hands-On Large Language Models
• 20动手学强化学习
• 21大模型基础

• 1CS324: Large Language Models
• 2CS229: Machine Learning
• 3CS230: Deep Learning
• 4CS231n: CNN for Visual Recognition
• 5CS224n: NLP with Deep Learning
• 6CS224w: Machine Learning with Graphs
• 7CS224u: Natural Language Understanding
• 8CS234: Reinforcement Learning
• 9CS330: Deep Multi-task Learning
• 10CS25: Transformers United
• 11Stanford ML Explainability
• 12Stanford NLP
• 13CMU CS 11-711: Advanced NLP
• 14CMU CS 11-747: Neural Networks for NLP
• 15CMU CS 11-737: Multilingual NLP
• 16CMU CS 11-785: Deep Learning
• 17CMU CS 11-777: Multimodal ML
• 18CMU CS 10-708: Probabilistic Graphical Models
• 19CMU LTI Low Resource NLP
• 20MIT OpenCourseWare
• 21MIT 6.034: Artificial Intelligence
• 22MIT 6.S094: Deep Learning
• 23MIT 6.S191: Introduction to Deep Learning
• 24MIT 6.S192: Deep Learning for Art
• 25CS221: Artificial Intelligence
• 26MIT 6.5940: TinyML

• 1DeepSeek-R1
• 2DeepSeek-V3
• 3DeepSeek-VL2
• 4Attention Is All You Need
• 5BERT
• 6GPT-3
• 7PaLM
• 8InstructGPT
• 9Constitutional AI
• 10LLaMA
• 11GPT-4
• 12PaLM 2
• 13RWKV
• 14Llama 2
• 15Code Llama
• 16Mistral 7B
• 17Phi-2
• 18Mixtral 8x7B
• 19Stable LM 3B
• 20arXiv LLM Papers
• 21The First Law of Complexodynamics
• 22Recurrent Neural Network Regularization
• 23Keeping Neural Networks Simple
• 24Pointer Networks
• 25Order Matters: Sequence to Sequence for Sets
• 26GPipe: Easy Scaling with Micro-Batch Pipeline Parallelism
• 27Deep Residual Learning for Image Recognition
• 28Multi-Scale Context Aggregation by Dilated Convolutions
• 29Neural Message Passing for Quantum Chemistry
• 30Neural Machine Translation by Jointly Learning to Align and Translate
• 31Identity Mappings in Deep Residual Networks
• 32A Simple Neural Network Module for Relational Reasoning
• 33Variational Lossy Autoencoder
• 34Relational Recurrent Neural Networks
• 35Neural Turing Machines
• 36Deep Speech 2
• 37Scaling Laws for Neural Language Models
• 38A Tutorial on the MDL Principle
• 39Machine Super Intelligence
• 40Kolmogorov Complexity and Algorithmic Randomness
• 41Stanford's CS231n CNN for Visual Recognition
• 42Quantifying Complexity in Closed Systems
• 43Gemini
• 44Claude 3
• 45Papers with Code LLM
• 46The Unreasonable Effectiveness of RNNs
• 47Understanding LSTM Networks

• 1Axolotl
• 2LLaMA-Factory
• 3360-LLaMA-Factory
• 4unsloth
• 5TRL
• 6Firefly
• 7Xtuner
• 8torchtune
• 9Swift
• 10AutoTrain
• 11OpenRLHF
• 12Ludwig
• 13mistral-finetune
• 14aikit
• 15H2O-LLMStudio
• 16LitGPT
• 17LLMBox
• 18PaddleNLP
• 19workbench-llamafactory
• 20TinyLLaVA Factory
• 21LLM-Foundry
• 22lmms-finetune
• 23Simplifine
• 24Transformer Lab
• 25Liger-Kernel
• 26ChatLearn
• 27nanotron
• 28Proxy Tuning
• 29Effective LLM Alignment
• 30Autotrain-advanced
• 31Meta Lingua
• 32Vision-LLM Alignemnt
• 33finetune-Qwen2-VL
• 34Online-RLHF
• 35InternEvo
• 36veRL
• 37Oumi
• 38Kiln

• 1LM Studio
• 2LLM Pricing
• 3NVIDIA ChatRTX
• 4ollama
• 5Open WebUI
• 6Text Generation WebUI
• 7Xinference
• 8LangChain
• 9LlamaIndex
• 10lobe-chat
• 11TensorRT-LLM
• 12vllm
• 13LlamaChat
• 14chat-with-mlx
• 15Open Interpreter
• 16Chat-ollama
• 17chat-ui
• 18MemGPT
• 19koboldcpp
• 20LLMFarm
• 21enchanted
• 22Flowise
• 23Jan
• 24LMDeploy
• 25RouteLLM
• 26MInference
• 27Mem0
• 28SGLang
• 29AirLLM
• 30LLMHub
• 31YuanChat
• 32LiteLLM
• 33GuideLLM
• 34LLM-Engines
• 35OARC
• 36g1
• 37MemoryScope
• 38OpenLLM
• 39Infinity
• 40optillm
• 41LLaMA Box
• 42ZhiLight
• 43DashInfer
• 44LocalAI
• 45ktransformers

• 1LangChain
• 2GPT4All
• 3Unstructured.io
• 4LlamaIndex
• 5dify
• 6langfuse
• 7Auto-GPT
• 8PrivateGPT

• 1LangChain Text Splitters
• 2Unstructured.io
• 3LlamaIndex
• 4TextCortex
• 5Label Studio
• 6Texthero
• 7Snorkel
• 8Prodigy
• 9DataTorch
• 10Tabula
• 11Adobe PDF Services API
• 12Great Expectations
• 13Kedro
• 14Weights & Biases
• 15Cleanlab
• 16DeepSpeed
• 17Doccano
• 18Rubrix
• 19Argilla
• 20DataPrep.ai
• 21Haystack
• 22Datasets CLI
• 23PDFPlumber
• 24Nougat
• 25Grobid
• 26PdfMiner.six
• 27OCRmyPDF
• 28Camelot
• 29DocTR
• 30PaddleOCR

DeepSeek 深度教程

• 1AnythingLLM
• 2MaxKB
• 3RAGFlow
• 4Dify
• 5FastGPT
• 6Langchain-Chatchat
• 7QAnything
• 8Quivr
• 9RAG-GPT
• 10Verba
• 11FlashRAG
• 12GraphRAG
• 13LightRAG (SylphAI-Inc)
• 14GraphRAG-Ollama-UI
• 15nano-GraphRAG
• 16RAG Techniques
• 17ragas
• 18kotaemon
• 19RAGapp
• 20TurboRAG
• 21LightRAG (HKUDS)
• 22TEN
• 23AutoRAG
• 24KAG (OpenSPG - knowledge-enhanced)
• 25Fast-GraphRAG
• 26Tiny-GraphRAG
• 27DB-GPT GraphRAG
• 28Chonkie
• 29RAGLite
• 30KAG (OpenSPG - logical form)
• 31CAG
• 32MiniRAG
• 33XRAG