Skip to content

TIGER-AI-Lab/CritiqueFineTuning

View on GitHub ↗Related repositories →

Code for "Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate"

active 2025-01-292026-02-08 (UTC)

Complete coverage26,571 / 26,571 hourly files (100%) · 2 absent upstream2023-08-152026-08-26 (UTC)
Events
264
Pushes
64
Pull requests
0
Issues
13
Stars
162
Forks
9

Activity over time

Daily event counts in the loaded window

Line chart, 376 days from 2025-01-29 to 2026-02-08. Pushes: 64 total, peak 36 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 13 total, peak 2 in a day. Comments: 15 total, peak 4 in a day. Stars: 162 total, peak 21 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
Wyyyb635604
wenhuchen15806
DripNowhy4002
mst2723001
yangzhch62000
lijianshe022000
yyyhz1001
zhuyglx1000
yucc-leon1001

Recent activity

Latest issues, pull requests and releases

  • Issue comment#10yyyhz2025-06-10 08:16
    Unable to reproduce results
  • Issue comment#9yucc-leon2025-06-06 03:02
    Really interesting! But why this worked?
  • Issue comment#9wenhuchen2025-06-05 19:50
    Really interesting! But why this worked?
  • Issue#7Wyyyb2025-06-04 21:04
    CFT data of MetaMath & NuminaMath
  • Issue comment#7Wyyyb2025-06-04 21:04
    CFT data of MetaMath & NuminaMath
  • Issue comment#8Wyyyb2025-06-04 20:57
    base model with chat template
  • Issue#8yangzhch62025-05-13 05:53
    base model with chat template
  • Issue#7yangzhch62025-05-08 10:17
    CFT data of MetaMath & NuminaMath
  • Issue#5Wyyyb2025-04-15 20:33
    The model Qwen2.5-Math-7B without fine-tuning cannot reproduce the ratings in the paper
  • Issue comment#5Wyyyb2025-04-09 15:09
    The model Qwen2.5-Math-7B without fine-tuning cannot reproduce the ratings in the paper
  • Issue#6Wyyyb2025-04-09 15:08
    Unfair results due to using MATH as the validation set
  • Issue comment#6wenhuchen2025-03-14 03:30
    Unfair results due to using MATH as the validation set
  • Issue comment#6wenhuchen2025-03-14 03:17
    Unfair results due to using MATH as the validation set
  • Issue comment#6wenhuchen2025-03-14 03:01
    Unfair results due to using MATH as the validation set
  • Issue comment#6wenhuchen2025-03-14 02:52
    Unfair results due to using MATH as the validation set
  • Issue#4wenhuchen2025-03-11 13:27
    about inference
  • Issue#4zhuyglx2025-03-11 05:55
    about inference
  • Issue#3lijianshe022025-02-22 05:03
    critique loss function
  • Issue#3lijianshe022025-02-22 03:58
    critique loss function
  • Issue comment#2DripNowhy2025-02-11 11:52
    Cannot reproduce
  • Issue#2DripNowhy2025-02-11 11:51
    Cannot reproduce
  • Issue comment#2Wyyyb2025-02-11 09:55
    Cannot reproduce
  • Issue comment#2DripNowhy2025-02-11 04:59
    Cannot reproduce
  • Issue comment#2wenhuchen2025-02-11 04:42
    Cannot reproduce
  • Issue#2DripNowhy2025-02-11 04:06
    Cannot reproduce

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 162 stars here means stars gained during the window, not the repo's star count.