Skip to content

Free-form flows are a generative model training a pair of neural networks via maximum likelihood

active 2023-10-272025-08-17 (UTC)

Partial coverage20,503 / 26,259 hourly files (78%) · 2 absent upstream · 5,753 failed, retryable2023-08-152026-08-13 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
54
Pushes
14
Pull requests
3
Issues
6
Stars
17
Forks
4

Activity over time

Daily event counts in the loaded window

Line chart, 661 days from 2023-10-27 to 2025-08-17. Pushes: 14 total, peak 3 in a day. Pull requests: 3 total, peak 1 in a day. Issues: 6 total, peak 2 in a day. Comments: 9 total, peak 3 in a day. Stars: 17 total, peak 2 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
fdraxler171123
RussellALA3210
ThisIsForReview3001
adam23922001
thelostscout2001
liang-zhicong2001
wj-gxy1001
laodar1001
hummerichsander1100

Recent activity

Latest issues, pull requests and releases

  • Pull request#10RussellALA2025-06-20 11:52
  • Issue comment#9fdraxler2025-04-26 17:27
    Minimal example not fitting
  • Issue comment#8fdraxler2024-10-30 08:38
    Interested in reproducing MNIST - training seems to focus on NLL only
  • Issue comment#8adam23922024-10-30 02:00
    Interested in reproducing MNIST - training seems to focus on NLL only
  • Issue comment#8wj-gxy2024-10-30 01:54
    Interested in reproducing MNIST - training seems to focus on NLL only
  • Issue#8adam23922024-10-15 20:05
    Interested in reproducing MNIST - training seems to focus on NLL only
  • Issue comment#6laodar2024-05-21 02:33
    How to implement a conditional version of FFF loss?
  • Issue comment#5thelostscout2024-05-18 10:46
    Issues with grad calculation in fff loss function
  • Issue#5thelostscout2024-05-18 10:41
    Issues with grad calculation in fff loss function
  • Issue comment#4ThisIsForReview2024-01-14 21:38
    Training Stopped
  • Issue comment#2fdraxler2024-01-09 13:46
    How to sample from latent space after training
  • Issue#2fdraxler2024-01-09 13:46
    How to sample from latent space after training
  • Issue#4ThisIsForReview2024-01-03 03:40
    Training Stopped
  • Issue#3ThisIsForReview2024-01-03 00:06
    Training stopped
  • Issue comment#2liang-zhicong2023-12-28 12:45
    How to sample from latent space after training
  • Issue#2liang-zhicong2023-12-27 12:06
    How to sample from latent space after training
  • Pull request#1fdraxler2023-12-15 11:04
  • Pull request#1fdraxler2023-11-23 16:43

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 17 stars here means stars gained during the window, not the repo's star count.