🚀 [从零构建 LLM] 极简大模型训练原理与实践指南。包含 Transformer, Pretraining, SFT 核心代码与对照实验。 | A minimal, principle-first guide to understanding and building LLMs from scratch.
-
Updated
Jun 4, 2026 - Python
GeezerVisonThe World Wide Web, restored to 800 pixels of glory. |
| Home|About|Gaming cabinet|Archives|How it works|Starter sites |
GeezerVison is showing github.com — Build software better, together
#
minimindHere are 29 public repositories matching this topic...Language: All
Filter by language
Sort: Most stars
Sort options
🚀 [从零构建 LLM] 极简大模型训练原理与实践指南。包含 Transformer, Pretraining, SFT 核心代码与对照实验。 | A minimal, principle-first guide to understanding and building LLMs from scratch.
从 MiniMind 源码读起,再延伸到现代大模型技术体系的中文学习笔记。主线逐行精读预训练 / SFT / DPO / PPO / GRPO 与训练机制;附录 17 篇进阶卷覆盖量化、投机解码、RLHF 全景、模型代际史等 MiniMind 没涉及、但进阶绕不开的主题。
nlp deep-learning pytorch transformer moe study-notes from-scratch rope fine-tuning ppo dpo pretraining large-language-models llm rlhf llm-training grpo minimind
对 Tongyun1/from-minimind-to-more 的逐篇结构化精读笔记(基石/架构/算法/求职,含思维导图与批判性批注)
The Cowork Agent for Everything — trainable advertising AI + 14 platform MCP servers + agent skills. Based on minimind (42k stars). Train from zero in 2 hours.
training cross-platform mcp advertising ppc ai-agents google-ads llm meta-ads vllm ollama model-context-protocol agent-skills claude-code minimind
免费 AI / 深度学习学习资料合集 + 学习笔记与代码 | A curated list of free AI & deep learning resources (ML, DL, RL, GNN, LLM, Transformer, Diffusion), plus study notes and code (nanoGPT, minimind, VAE).
machine-learning awesome reinforcement-learning deep-learning tutorials pytorch artificial-intelligence transformer vae chinese awesome-list study-notes learning-resources free-courses graph-neural-networks diffusion-models large-language-models llm nanogpt minimind
100% offline AI desktop pet: HachimoDock x MiniMind x ESP-4P (ESP32-P4). Self-trained + LoRA + quantized model, no PC required.
esp32 lora quantization esp-idf usb-host desktop-pet embedded-ai edge-ai llm esp32-p4 local-llm tiny-llm offline-ai esp32p4 qwen3 minimind hachimodock esp-4p
14 天读透一个 LLM 的全部实现：基于 MiniMind 的本地交互式学习站，逐行看 tensor 维度、可运行实验、小测
练习时长两年半的 AI 大模型 (实际 26M params，2.5B = 两年半) | ikun meme-culture chatbot 🐔🏀
A beginner-friendly VLA project starter: CPU smoke, ACT + PushT-style imitation learning, rollout eval, and resume-ready docs.
internship robotics imitation-learning from-scratch vla act embodied-ai vision-language-action lerobot minimind pusht
u盘随身AI组装套件：断网自动接管的离线小模型 + 保姆级小白组装说明书
GLES2/EGL inference for MiniMind3 64M on Raspberry Pi Zero (VC4), with Q4/Q8 weights, packed KV, tools and an OpenAI-compatible server.
从零复现 26M 中文小语言模型 MiniMind｜预训练→SFT→LoRA→DPO→蒸馏→RLHF 全流程学习复现（基于 jingyaogong/minimind）
MiniMind training systems lab: causal language modeling, supervision contracts, decoder architecture auditing, optimization semantics, and artifact verification with executable diagnostics.
pytorch transformer reproducible-experiments model-analysis gqa pretraining llm-training llm-learning supervised-fine-tuning minimind
Add this topic to your repoTo associate your repository with the minimind topic, visit your repo's landing page and select "manage topics." |
| You are visitor 01402520 — GeezerVison does not store the pages you look up. Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required. |