[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-90731":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":13,"openIssues":14,"contributorsCount":14,"subscribersCount":14,"size":14,"stars1d":14,"stars7d":14,"stars30d":14,"stars90d":14,"forks30d":14,"starsTrendScore":14,"compositeScore":15,"rankGlobal":10,"rankLanguage":10,"license":16,"archived":17,"fork":17,"defaultBranch":18,"hasWiki":19,"hasPages":17,"topics":20,"createdAt":10,"pushedAt":10,"updatedAt":39,"readmeContent":10,"aiSummary":10,"trendingCount":14,"starSnapshotCount":14,"syncStatus":40,"lastSyncTime":41,"discoverSource":42},90731,"minimind-deep-dive","Enping-Hu\u002Fminimind-deep-dive","Enping-Hu","逐行对照 MiniMind 源码精读、并延伸到大模型技术体系的中文学习笔记 —— 预训练 \u002F SFT \u002F DPO \u002F PPO \u002F GRPO、训练机制、MiniMind2→3 版本对照、真实实验证据。","",null,"Python",58,1,0,36.9,"Creative Commons Attribution 4.0 International",false,"main",true,[21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"deep-learning","dpo","fine-tuning","from-scratch","grpo","large-language-models","llm","llm-training","minimind","moe","nlp","ppo","pretraining","pytorch","rlhf","rope","study-notes","transformer","2026-07-02 04:01:58",2,"2026-07-02 02:32:00","CREATED_QUERY"]