1.jingyaogong / minimind
🧠 Train a 64M-parameter LLM from scratch in just 2h!
+16,366 stars
from 48,368 · score 9.70
Ranked by Attention Score: stars gained over the last 180 complete days
6 repositories by Attention Score · May 7, 2026 – Nov 2, 2026 (UTC)
🧠 Train a 64M-parameter LLM from scratch in just 2h!
Python scraper based on AI
Pocket Flow: 100-line LLM framework. Let Agents build Agents!
Pocket Flow: Codebase to Tutorial
MCP server that connects AI agents to your running Neovim instance via msgpack-RPC — no plugins required.
An NLP library for Uralic languages such as Finnish, Skolt Sami, Moksha and so on. Also supporting some non-Uralic languages such as Spanish, French, Arabic, Swedish, Norwegian, Russian and English. LLMs, FSTs and More!