Skip to content

harvardnlp/annotated-transformer

View on GitHub ↗Related repositories →

本仓库旨在解读 transformer 的源码。参考的源码来自 https://github.com/harvardnlp/annotated-transformer。

Jupyter Notebook · active 2025-03-292026-06-19 (UTC)

Partial coverage11,268 / 12,011 hourly files (94%) · 2 absent upstream · 741 failed, retryable2025-03-282026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
603
Pushes
0
Pull requests
0
Issues
1
Stars
504
Forks
96

Activity over time

Daily event counts in the loaded window

Line chart, 448 days from 2025-03-29 to 2026-06-19. Pushes: 0 total, peak 0 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 1 total, peak 1 in a day. Comments: 2 total, peak 1 in a day. Stars: 504 total, peak 11 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

ContributorContributionsPushesPRsComments
harumo111001
StrongerXi1001
luo-jia13141000

Recent activity

Latest issues, pull requests and releases

  • Issue#137luo-jia13142025-08-02 07:07
    It seems there is a problem with the "make_std_mask" code.
  • Issue comment#92StrongerXi2025-06-22 07:25
    Should the model LayerNorm before encoding?
  • Issue comment#13harumo112025-06-04 04:49
    where should layer norm be applied?

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 504 stars here means stars gained during the window, not the repo's star count.