LLM Architecture From Scratch

Implementing LLM architectures from scratch in PyTorch

What you get

LLM Architecture From Scratch is a free, open-source AI tool published on GitHub by YeonwooSung. Implementing LLM architectures from scratch in PyTorch GitHub stars: 1,112 License: BSD-3-Clause (free to use) Language: Python Topics: deepseek-r1, deepseek-v3, gemma3, kimi-k2, llama4, llm, moe, qwen3 Last updated: 2026-10-22 How to get it: open the repository on GitHub, read the README and follow the setup steps. HEEEXY lists it in the Lab because it is popular, actively maintained and openly licensed.

More for new on github

  • Yetone Magpie: Every agent's model. One place. Codex on DeepSeek, Claude Code on Kimi, from the menu bar.
  • Printfilm: PRINTFILM: AI short-video marketing and AI short-drama creation platform
  • Answer Me With Html: Answer me with HTML — an agent skill that answers hard questions with a one-page HTML you can actually read. 让 AI Agent 用一页 HTML 回答复杂问题。