Alternatives and similar repositories for LLM-from-scratch

Users that are interested in LLM-from-scratch are comparing it to the libraries listed below

• golfxiao / ScratchLLMStepByStep
  一个手把手教你从零开始编写GPT并训练大语言模型的教程
  ☆87Updated 7 months ago
• hellangleZ / hospital_multiagent_system
  医疗问诊系统multi-agent框架
  ☆85Updated 5 months ago
• WangRongsheng / o1-imitator
  ☆54Updated 6 months ago
• datawhalechina / unlock-hf
  解锁HuggingFace生态的百般用法
  ☆93Updated 9 months ago
• wangwei1237 / LLM_in_Action
  Large Language Model in Action
  ☆335Updated 7 months ago
• KaihuaTang / Building-a-Small-LLM-from-Scratch
  该系列的目的是让读者可以在基础的pytorch上，不依赖任何其他现成的外部库，从零开始理解并实现一个大语言模型的所有组成部分，以及训练微调代码，因此读者仅需python，pytorch和最基础深度学习背景知识即可。
  ☆365Updated 3 weeks ago
• RUCAIBox / awesome-llm-pretraining
  Awesome LLM pre-training resources, including data, frameworks, and methods.
  ☆244Updated 4 months ago
• datawhalechina / fun-transformer
  通过带领大家解读Transformer模型来加深对模型的理解
  ☆214Updated 3 months ago
• SmartFlowAI / Hand-on-RAG
  顾名思义：手搓的RAG
  ☆127Updated last year
• datawhalechina / wow-rag
  A simple and trans-platform rag framework and tutorial
  ☆214Updated this week
• anakin87 / qwen-scheduler-grpo
  Train a Language Model with GRPO to create a schedule from a list of events and priorities
  ☆231Updated 4 months ago
• FareedKhan-dev / train-deepseek-r1
  Building DeepSeek R1 from Scratch
  ☆698Updated 5 months ago
• intro-llm / intro-llm.github.io
  website
  ☆447Updated 6 months ago
• yassa9 / qwen600
  Static suckless single batch CUDA-only qwen3-0.6B mini inference engine
  ☆433Updated last week
• huangjia2019 / llm-gpt
  异步图书：《 GPT图解 大模型是怎样构建的》- 这套代码是AI Coder出现之前，自己用纯手工搭建的一套简单有效的NLP经典算法集合。在大语言模型推动的AI Coder兴起之后，很少有机会再创作这么有“手工风”的代码了，不知道这是值得开心还是值得遗憾的事情。
  ☆175Updated last year
• hellangleZ / BY_RAG_V2
  support BM25+vecetor
  ☆29Updated 3 months ago
• chaoswork / llm_illustrated
  看图学大模型
  ☆317Updated last year
• datawhalechina / llm-deploy
  大模型/LLM推理和部署理论与实践
  ☆330Updated 2 months ago
• ninehills / countdown
  Countdown Game Distill&RL
  ☆47Updated 2 weeks ago
• KMnO4-zx / TinyAgent
  基于ReAct手搓一个Agent Demo
  ☆152Updated 2 months ago
• wey-gu / grpo-graph-extraction
  Qwen GRPO Graph Extraction RL Finetune
  ☆55Updated 5 months ago
• bbruceyuan / bit-brain
  最少使用 3090 即可训练自己的比特大脑（miniLLM）🧠（进行中）. Train your own BitBrain(A mini LLM) with just an RTX 3090 minimum.
  ☆36Updated 2 months ago
• intro-llm / intro-llm-code
  ☆287Updated 4 months ago
• Tongjilibo / build_MiniLLM_from_scratch
  从0到1构建一个MiniLLM (pretrain+sft+dpo实践中)
  ☆475Updated 5 months ago
• bbruceyuan / LLMs-101
  从零到一实现一个 miniLLM～（动手学习LLM）
  ☆75Updated last year
• AXYZdong / AMchat
  AM (Advanced Mathematics) Chat is a large language model that integrates advanced mathematical knowledge, exercises in higher mathematics…
  ☆208Updated last year
• ScienceOne-AI / DeepSeek-671B-SFT-Guide
  An open-source solution for full parameter fine-tuning of DeepSeek-V3/R1 671B, including complete code and scripts from training to infer…
  ☆757Updated 6 months ago
• hellangleZ / Agent-MemoryForge
  A complete 7-layer intelligent memory system for AI Agents with multi-modal memory fusion also support context_engineering
  ☆123Updated 2 months ago
• datawhalechina / unlock-deepseek
  DeepSeek 系列工作解读、扩展和复现。
  ☆677Updated 5 months ago
• GenTang / regression2chatgpt
  《解构大语言模型：从线性回归到通用人工智能》配套代码
  ☆239Updated 2 months ago