jingyaogong/minimind

從零訓練64M參數LLM的開源教學專案，2小時可完成SFT。 🧠 Train a 64M-parameter LLM from scratch in just 2h!

Python 63k 8.2k 官網 Website

artificial-intelligencelarge-language-model

AI 推薦理由 Why AI picked it

92 學習資源 Learning 2026-09-06

完整覆蓋預訓練、SFT、LoRA、RLHF、MoE、多模態等流程，且核心程式碼用PyTorch原生實作，適合學習LLM內部機制。README提供詳細模型列表、資料集、訓練腳本與第三方框架相容性，文件完整度高。只需單張消費級GPU即可復現，上手成本低。 Covers pretraining, SFT, LoRA, RLHF, MoE, and multimodal pipelines with PyTorch-native implementations, ideal for learning LLM internals. README provides detailed model lists, datasets, training scripts, and third-party compatibility, with high documentation completeness. Runs on a single consumer GPU, lowering onboarding cost.

上榜紀錄 Trending history

最佳名次 #5 Best rank #5 上榜 21 天 21 days listed 首次上榜 2026-09-01 First seen 2026-09-01