Skip to content

microsoft/TransformerCompression

View on GitHub ↗Related repositories →

For releasing code related to compression methods for transformers, accompanying our publications, forked from microsoft/TransformerCompression

active 2024-07-012026-02-26 (UTC)

Partial coverage15,189 / 18,621 hourly files (82%) · 2 absent upstream · 3,432 failed, retryable2024-06-262026-08-11 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
97
Pushes
5
Pull requests
0
Issues
5
Stars
63
Forks
18

Activity over time

Daily event counts in the loaded window

Line chart, 606 days from 2024-07-01 to 2026-02-26. Pushes: 5 total, peak 4 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 5 total, peak 1 in a day. Comments: 6 total, peak 2 in a day. Stars: 63 total, peak 3 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
pashminacameron5500
NamburiSrinath3002
jiajunsun682001
sriyachakravarthy2001
mxjmtxrm1001
thu-mzy1001
RanchiZhao1000
xiaoyu-work1000

Recent activity

Latest issues, pull requests and releases

  • Issue#188NamburiSrinath2025-06-10 02:18
    Loading models is not easy with `from_pretrained`
  • Issue comment#73NamburiSrinath2025-06-10 02:15
    loading models is painful and not HF compatible
  • Issue comment#139NamburiSrinath2025-06-10 02:14
    Make sliced models HuggingFace compatible
  • Issue comment#181thu-mzy2025-05-08 04:14
    Some confusion about the equation.6 in the sliceGPT paper.
  • Issue#183xiaoyu-work2025-01-04 01:41
    transformers dependency version upgrade
  • Issue comment#176mxjmtxrm2024-10-24 02:53
    NaN weights after rotating and slicing
  • Issue comment#167jiajunsun682024-10-20 08:31
    How to finetune with multi-gpus under data parallel setting?
  • Issue#176sriyachakravarthy2024-08-17 09:52
    NaN weights after rotating and slicing
  • Issue comment#114sriyachakravarthy2024-08-15 06:24
    How to export entire model?
  • Issue#175jiajunsun682024-07-31 02:18
    need help
  • Issue#174RanchiZhao2024-07-12 10:13
    Quarot: DeepSeek-V2 Support

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 63 stars here means stars gained during the window, not the repo's star count.