Skip to content

sai-dpo

active 2025-02-112025-12-31 (UTC)

Complete coverage26,421 / 26,421 hourly files (100%) · 2 absent upstream2023-08-152026-08-19 (UTC)
Events
335
Pushes
18
Pull requests
0
Issues
17
Stars
229
Forks
28

Activity over time

Daily event counts in the loaded window

Line chart, 324 days from 2025-02-11 to 2025-12-31. Pushes: 18 total, peak 7 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 17 total, peak 3 in a day. Comments: 37 total, peak 5 in a day. Stars: 229 total, peak 28 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
WeiXiongUST318023
hanningzhang121002
pspdada11004
ToheartZhang6004
raojay74002
junkangwu3001
Freder-chen2000
CurryxIaoHu2001
Jiangchenglin5211000

Recent activity

Latest issues, pull requests and releases

  • Issue#11pspdada2025-04-21 11:56
    eval/grader.py test error
  • Issue#10pspdada2025-04-21 11:55
    Question about training prompt template
  • Issue#14pspdada2025-04-21 11:52
    Can not perform evaluate on competition_math benchmark
  • Issue comment#15WeiXiongUST2025-04-11 14:26
    Code update request
  • Issue#15Jiangchenglin5212025-04-11 05:16
    Code update request
  • Issue#14pspdada2025-04-02 14:24
    Can not perform evaluate on competition_math benchmark
  • Issue comment#12WeiXiongUST2025-04-01 22:32
    Garbled Outputs from vLLM Sampling Causing Instability in Preference Learning
  • Issue comment#11hanningzhang2025-04-01 22:18
    eval/grader.py test error
  • Issue comment#13hanningzhang2025-04-01 22:00
    What is the correct prompt type for deepseek-ai/DeepSeek-R1-Distill-Llama-8B?
  • Issue#13CurryxIaoHu2025-04-01 14:35
    What is the correct prompt type for deepseek-ai/DeepSeek-R1-Distill-Llama-8B?
  • Issue#12pspdada2025-03-31 12:45
    Garbled Outputs from vLLM Sampling Causing Instability in Preference Learning
  • Issue#11pspdada2025-03-30 07:45
    eval/grader.py test error
  • Issue comment#9pspdada2025-03-30 06:52
    Reward labeling is too slow
  • Issue comment#9pspdada2025-03-30 05:38
    Reward labeling is too slow
  • Issue comment#9pspdada2025-03-30 04:58
    Reward labeling is too slow
  • Issue comment#9WeiXiongUST2025-03-30 04:50
    Reward labeling is too slow
  • Issue comment#9pspdada2025-03-30 04:49
    Reward labeling is too slow
  • Issue comment#10WeiXiongUST2025-03-29 18:58
    Question about training prompt template
  • Issue#10pspdada2025-03-29 13:22
    Question about training prompt template
  • Issue comment#9raojay72025-03-28 01:40
    Reward labeling is too slow
  • Issue#9raojay72025-03-28 01:40
    Reward labeling is too slow
  • Issue comment#9WeiXiongUST2025-03-27 20:28
    Reward labeling is too slow
  • Issue comment#9WeiXiongUST2025-03-27 20:27
    Reward labeling is too slow
  • Issue comment#9WeiXiongUST2025-03-25 03:34
    Reward labeling is too slow
  • Issue comment#9raojay72025-03-25 03:27
    Reward labeling is too slow

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 229 stars here means stars gained during the window, not the repo's star count.