# anuj0456/OpenArch

<https://repo.masters-masters.com/en/repos/anuj0456/OpenArch>

[Home](https://repo.masters-masters.com/en) › [anuj0456](https://repo.masters-masters.com/en/owners/anuj0456) › [OpenArch](https://repo.masters-masters.com/en/repos/anuj0456/OpenArch)

anuj0456/OpenArch has 427 stars on GitHub. Its RepoMasters card: Alpha tier. PyTorch implementations of modern open-source LLM architectures (Llama, Qwen…

| Field | Value |
| --- | --- |
| Owner | [anuj0456](https://repo.masters-masters.com/en/owners/anuj0456) |
| Stars | 427 |
| Forks | 34 |
| Language | [Python](https://repo.masters-masters.com/en/languages/python) |
| License | MIT |
| Created | 2026 |
| Topics | architecture, attention-mechanism, deep-learning, deepseek, gemma, language-models, llama3, llms, mixture-of-experts, python |
| Tier | [Alpha (250 to 699 ★)](https://repo.masters-masters.com/en/ranks/b_movie) |
| View on GitHub | [anuj0456/OpenArch](https://github.com/anuj0456/OpenArch) |

## Repository

PyTorch implementations of modern open-source LLM architectures (Llama, Qwen, DeepSeek, Gemma, GPT-OSS, Kimi, and more) — written from scratch for readability and learning, based on Sebastian Raschka's LLM Architecture Gallery.

The tier for repos with 250 to 699 ★. Published odds per card pulled: 20%. Rarity: Uncommon.

## Nearby in Python

- [H-EmbodVis/VEGA-3D · ★ 427 · Python · Alpha](https://repo.masters-masters.com/en/repos/H-EmbodVis/VEGA-3D)
- [QuantML-Research/wq-alpha-research · ★ 427 · Python · Alpha](https://repo.masters-masters.com/en/repos/QuantML-Research/wq-alpha-research)
- [smarkyie/NSP-Box · ★ 427 · Python · Alpha](https://repo.masters-masters.com/en/repos/smarkyie/NSP-Box)
- [openyou/libfitbit · ★ 427 · Python · Alpha](https://repo.masters-masters.com/en/repos/openyou/libfitbit)
- [titoBouzout/Tag · ★ 427 · Python · Alpha](https://repo.masters-masters.com/en/repos/titoBouzout/Tag)
- [mozilla/agithub · ★ 427 · Python · Alpha](https://repo.masters-masters.com/en/repos/mozilla/agithub)

---
Data: GitHub · Illustration drawn by RepoMasters from the repo’s ID and its language color.