Skip to content

Results File w/ Hugging face links

active 2025-03-072025-04-20 (UTC)

Complete coverage26,642 / 26,642 hourly files (100%) · 2 absent upstream2023-08-152026-08-29 (UTC)
Events
454
Pushes
211
Pull requests
35
Issues
71
Stars
3
Forks
2

Activity over time

Daily event counts in the loaded window

Line chart, 45 days from 2025-03-07 to 2025-04-20. Pushes: 211 total, peak 23 in a day. Pull requests: 35 total, peak 8 in a day. Issues: 71 total, peak 12 in a day. Comments: 56 total, peak 12 in a day. Stars: 3 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
BrownianNotion2881442245
heisenger372424
fredericowieser291126
alexncoleman231911
charliestamp200212660
victorfiz11620
NikhilBaid1100

Recent activity

Latest issues, pull requests and releases

  • Issue#51BrownianNotion2025-04-09 17:30
    Replace default upload means with `trainer.push_to_hub()`
  • Issue#49BrownianNotion2025-04-09 17:30
    Fix package issues
  • Issue#50BrownianNotion2025-04-09 17:30
    Add datasets to main
  • Issue#27BrownianNotion2025-04-09 17:30
    Support Fused Adam and torch.compile to speed up training
  • Issue#40BrownianNotion2025-04-09 17:29
    Add PPL on eval step logging
  • Issue#60BrownianNotion2025-04-09 17:29
    Eval random baseline/unclipped
  • Issue#56BrownianNotion2025-04-09 17:29
    Implement 1.58 bit BitDistiller
  • Issue#48BrownianNotion2025-04-09 17:29
    Review 1 bit implementation
  • Issue#43BrownianNotion2025-04-09 17:29
    Analyse model weight distributions + check for dead activations
  • Issue#64BrownianNotion2025-04-08 16:29
    Larger teacher ablation - only use larger teacher data with self-distillation
  • Issue#55BrownianNotion2025-04-03 15:41
    Test GH200 instance on lambda labs
  • Issue#34BrownianNotion2025-04-03 15:40
    Use larger teacher models for distillation
  • Pull request#63BrownianNotion2025-04-03 15:34
  • Issue#20BrownianNotion2025-04-02 01:42
    Type up MVP results of 1/2bit models in overleaf table
  • Issue comment#56BrownianNotion2025-04-02 01:40
    Implement 1.58 bit BitDistiller
  • Issue comment#56BrownianNotion2025-04-01 21:38
    Implement 1.58 bit BitDistiller
  • Issue#62BrownianNotion2025-04-01 19:39
    Run 7B 3 bit int quantisation
  • Issue#59BrownianNotion2025-04-01 18:49
    Run missing evals on old models
  • Pull request#61charliestamp20022025-03-31 19:33
  • Pull request#58charliestamp20022025-03-31 19:21
  • Issue#60BrownianNotion2025-03-30 00:26
    Eval random baseline/unclipped
  • Issue#41BrownianNotion2025-03-28 16:48
    Different Loss Functions and How They Effect Knowledge Distillation
  • Issue#59BrownianNotion2025-03-28 16:41
    Run missing evals on old models
  • Issue comment#56BrownianNotion2025-03-28 01:01
    Implement 1.58 bit BitDistiller
  • Pull request#58charliestamp20022025-03-27 21:28

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 3 stars here means stars gained during the window, not the repo's star count.