# labmlai/annotated_deep_learning_paper_implementations

> A collection of simple PyTorch implementations of 60+ deep learning papers — transformers, GANs, optimizers, RL and more — with line-by-line annotated explanations. Helps understand algorithms directly from the source papers.

- Magnitude: 1.7 out of 10 — Steady
- Stars: 67,677 total · Not enough measurements today
- Star trust: star growth looks organic
- Category: Learning & lists · Language: Python · License: MIT · Created: 2020-08-25 · Last push: 2026-11-02
- GitHub: https://github.com/labmlai/annotated_deep_learning_paper_implementations · Homepage: https://nn.labml.ai · Page: https://gitnova.dev/en/r/labmlai/annotated_deep_learning_paper_implementations

## Useful for

- Study multi-head attention internals through line-by-line code annotations
- Copy an Adam or Sophia-G implementation into your own training setup
- Explore a DDPM or Stable Diffusion implementation for image generation

## Why it’s here

- There are not enough fresh counter measurements for today's UTC day. The gain is unknown.
- GitHub Trending Python today: #16, +16 stars.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 6,781
- Issues and pull requests: 299
- Watchers: 495
- Average over the last week: 12 per day
- Usual pace: 6 per day

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-10-06 … 2026-11-04: 8, 8, 11, 7, 4, 4, 6, 7, 8, 9, 2, 7, 8, 8, 6, 9, 4, 8, 8, 4, 5, 7, 4, 9, 7, 12, 19, 20, 16, None

## Spotted in now

- GitHub Trending Python today: #16, +16 stars

## Similar by description

1. **eriklindernoren/ML-From-Scratch** — 1.1 · Cooling · Learning & lists · Python · +1 star measured 2026-11-04, 00:26–12:26 UTC, ≈ 2 by evening
   A collection of machine learning models and algorithms implemented from scratch in NumPy, from linear regression to deep learning, focused on showing how they work internally rather than on performance.
   Full card: https://gitnova.dev/en/r/eriklindernoren/ML-From-Scratch.md
2. **aa1143/NamiGPT** — 1.1 · Cooling · Learning & lists · Python · +4 stars measured 2026-11-04, 00:26–12:27 UTC, ≈ 7 by evening
   A step-by-step GPT-2 tutorial in PyTorch: from tokenization to text generation, with a hand-written implementation without ready-made Transformer modules and loading of OpenAI's official weights.
   Full card: https://gitnova.dev/en/r/aa1143/NamiGPT.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-11-04 12:30 UTC, updated every 30 minutes.