Explore · Ranking › jingyaogong/minimind
🧠 两小时从 0 训出你的 64M 大模型。Train your own 64M LLM from scratch in 2 hours.
#25best daily rank (Nov 19)
+602stars on Nov 20
+2,679stars in 7 days
68.0ktotal stars
Where it stands
Steady · second wave · day 6 of its run
- Best day in the last 13 weeks: +908 stars on Sep 1.
- Nov 20: 66% of that.
- It fell below half of its best day 2 days later.
- Day 6 of its run (the days in a row with at least a tenth of its best day).
- Back above half its best day after dropping below a quarter of it: its second wave.
Stars per day
Aug 24peak 908 a dayNov 21 so far
Fake-star check
No red flags
Checks forks, watchers, issues and how the stars arrived. A flag is a reason to look closer, not proof. How the check works
Why it may be trending
YouTube · 3,685 views · Full Stack · Nov 20X · 87 posts in 7 daysBluesky · 6 posts in 7 daysOwner has 2,482 followers
Where people talk
X: 87 posts linked it in the last 7 days, reposts not counted. See them on X ↗
Bluesky: 6 posts linked it in the last 7 days. See them on Bluesky ↗
On YouTube
- Jingyaogong/minimind — 🧠 Train a 64M-parameter LLM from scratch in just 2h!Signal Coders · 6,414 views · Sep 1
- MiniMind – Train Your Own LLM From Scratch in 2 Hours (Under $1)Full Stack · 3,685 views · Nov 20
- MiniMind: Train a 64M LLM from Scratch in 2 Hours for $0.40 on One RTX 3090CLI Stack · 1,003 views · Sep 3
Videos on YouTube whose description links this repo. YouTube Terms of Service
Days in the ranking
- Nov 20#29
- Nov 19#25
- Nov 15#100
Badge for your README
It shows the best daily rank and updates itself. Paste this into your README:
[](https://truestars.dev/r/jingyaogong/minimind/)