Skip to content

Vance0124/Token-level-Direct-Preference-Optimization

View on GitHub ↗Related repositories →

Reference implementation for Token-level Direct Preference Optimization(TDPO)

active 2024-04-162026-05-23 (UTC)

Complete coverage26,369 / 26,369 hourly files (100%) · 2 absent upstream2023-08-152026-08-17 (UTC)
Events
188
Pushes
13
Pull requests
2
Issues
11
Stars
139
Forks
12

Activity over time

Daily event counts in the loaded window

Line chart, 768 days from 2024-04-16 to 2026-05-23. Pushes: 13 total, peak 2 in a day. Pull requests: 2 total, peak 2 in a day. Issues: 11 total, peak 3 in a day. Comments: 8 total, peak 3 in a day. Stars: 139 total, peak 6 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
Vance0124241316
yuchen8142001
junkangwu2001
LuckerYi1000
Yeeesir1000
robin0871000
tcxia1000
fiberleif1010
wangxu08201000

Recent activity

Latest issues, pull requests and releases

  • Issue#7Vance01242024-11-13 02:33
    Some questions about the paper
  • Issue#8junkangwu2024-09-26 07:03
    Inquiry About KL Divergence in ICML 2024 Paper
  • Issue comment#8junkangwu2024-09-26 07:03
    Inquiry About KL Divergence in ICML 2024 Paper
  • Issue comment#8Vance01242024-09-26 04:25
    Inquiry About KL Divergence in ICML 2024 Paper
  • Issue comment#7Vance01242024-09-26 04:15
    Some questions about the paper
  • Issue#7robin0872024-09-24 07:33
    Some questions about the paper
  • Issue#6tcxia2024-09-11 08:01
    Can you train DPO directly? Using open-source base models.
  • Issue#5wangxu08202024-07-15 03:17
    How do you go about evaluating ALIGNMENT(accuracy) and DIVERSITY(entropy)? Is there a code available?
  • Issue#4Vance01242024-07-06 08:38
    How to eval the models
  • Issue#3Vance01242024-07-06 08:37
    How about the loss curve? especially when converge
  • Issue#2Vance01242024-07-06 08:37
    Some questions about the code
  • Issue comment#4Vance01242024-06-27 14:33
    How to eval the models
  • Issue comment#3Vance01242024-06-27 14:13
    How about the loss curve? especially when converge
  • Issue comment#2Vance01242024-06-27 14:08
    Some questions about the code
  • Issue#4Yeeesir2024-06-26 12:38
    How to eval the models
  • Issue#3LuckerYi2024-06-13 09:18
    How about the loss curve? especially when converge
  • Issue comment#2yuchen8142024-06-05 14:39
    Some questions about the code
  • Issue comment#2Vance01242024-05-28 09:23
    Some questions about the code
  • Issue#2yuchen8142024-05-18 14:38
    Some questions about the code
  • Pull request#1Vance01242024-05-06 13:09
  • Pull request#1fiberleif2024-05-06 13:05

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 139 stars here means stars gained during the window, not the repo's star count.