🧑🏫60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
Python · active 2024-12-01 → 2026-08-07 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 615 days from 2024-12-01 to 2026-08-07. Pushes: 11 total, peak 3 in a day. Pull requests: 5 total, peak 1 in a day. Issues: 12 total, peak 6 in a day. Comments: 12 total, peak 5 in a day. Stars: 5,215 total, peak 57 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| vpj | 19 | 9 | 1 | 3 |
| NisargUpadhyayIITJ | 3 | 0 | 0 | 3 |
| ww-rm | 2 | 0 | 0 | 2 |
| leftyvuelaalto-sudo | 2 | 0 | 0 | 0 |
| yuffon | 1 | 0 | 0 | 0 |
| dyedd | 1 | 0 | 0 | 0 |
| wsl1717 | 1 | 0 | 0 | 0 |
| pharrera | 1 | 0 | 0 | 1 |
| nikihowe | 1 | 0 | 1 | 0 |
| Mirko150674 | 1 | 0 | 0 | 0 |
| AnanyaRaval | 1 | 0 | 0 | 1 |
| yiminglin-ai | 1 | 0 | 0 | 1 |
| MayureshMore | 1 | 0 | 1 | 0 |
| thanhtcptit | 1 | 0 | 1 | 0 |
| kommentlezz | 1 | 0 | 1 | 0 |
| sracha4355 | 1 | 0 | 0 | 1 |
| chiamerica | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#301Mirko1506742026-05-08 07:46Mc_Paper
- Pull request#265thanhtcptit2026-01-22 04:26
- Issue#293chiamerica2026-01-03 14:29Minor corrections in documentation for Nucleus Sampling implementation
- Issue#290leftyvuelaalto-sudo2025-10-25 03:57'your_email@example.com
- Issue comment#288vpj2025-07-28 11:17安装不了labml_helpers包
- Issue comment#262vpj2025-07-18 05:26mha.py array shapes
- Issue#262vpj2025-07-18 05:26mha.py array shapes
- Issue#246vpj2025-07-18 05:23question about RotaryPEMultiHeadAttention: rotary_percentage
- Issue#282vpj2025-07-18 05:22Attention takes softmax over wrong dimension
- Issue#263vpj2025-07-18 05:22LORA
- Issue#257vpj2025-07-18 05:22Chinese Translation
- Issue comment#254vpj2025-07-18 05:22connection timed out
- Issue#254vpj2025-07-18 05:22connection timed out
- Pull request#287vpj2025-07-18 05:14
- Issue comment#282pharrera2025-05-30 01:42Attention takes softmax over wrong dimension
- Issue#288wsl17172025-05-20 02:41安装不了labml_helpers包
- Issue comment#275AnanyaRaval2025-03-26 03:03How to Contribute to This Repository
- Issue comment#241ww-rm2025-03-16 07:00Wrong Image Scale in DDPM
- Issue comment#241NisargUpadhyayIITJ2025-03-16 06:15Wrong Image Scale in DDPM
- Issue comment#241ww-rm2025-03-16 06:05Wrong Image Scale in DDPM
- Issue comment#241NisargUpadhyayIITJ2025-03-16 05:44Wrong Image Scale in DDPM
- Issue comment#270NisargUpadhyayIITJ2025-03-16 05:43Unet error in DDPM
- Pull request#286nikihowe2025-03-10 00:26
- Pull request#284MayureshMore2025-02-15 18:14
- Issue#283yuffon2025-02-14 05:17How to run model on multiple GPUs?
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 5,215 stars here means stars gained during the window, not the repo's star count.