Skip to content

own O1 preview model

active 2025-01-102026-05-19 (UTC)

Complete coverage26,712 / 26,712 hourly files (100%) · 2 absent upstream2023-08-152026-08-31 (UTC)
Events
4.4K
Pushes
152
Pull requests
112
Issues
92
Stars
3.1K
Forks
331

Activity over time

Daily event counts in the loaded window

Line chart, 495 days from 2025-01-10 to 2026-05-19. Pushes: 152 total, peak 19 in a day. Pull requests: 112 total, peak 9 in a day. Issues: 92 total, peak 6 in a day. Comments: 295 total, peak 22 in a day. Stars: 3,134 total, peak 581 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
SumanthRH3379954102
caoshiyi85151226
DachengLi184111037
lynnliu03074201218
erictang000480619
kouroshHakha360123
tyler-griggs356614
armsp6002
MizuleGPT6005
fanqiwan5013
guspan-tanadi5050
Louym4002
Henchen994002
ZijunSong4001
hxdtest4003
RyanMarten3002
samyon73001
xu3kev3001
LetheSec3002
niccolox3002

Recent activity

Latest issues, pull requests and releases

  • Issue comment#100maharajamihir2025-12-14 15:41
    which prompt should i use?
  • Issue#1201112321sfdsaf2025-11-03 02:35
    How can I obtain the no-think results (e.g., accuracy) for reasoning benchmarks such as gpqa_diamond?
  • Issue comment#119SumanthRH2025-08-05 21:04
    Is this project dead?
  • Issue#119MotherSoraka2025-08-05 20:53
    Is this project dead?
  • Issue comment#118SumanthRH2025-07-12 03:05
    [evals] Update pyproject.toml, forcing datasets<4.0.0 to avoid errors in benchmarks that requires "dataset scripts" features.
  • Pull request#118SumanthRH2025-07-12 03:05
  • Issue comment#117ko1202025-07-12 02:49
    [Evals] Fix MinervaMath dataset YAML for correct evaluation
  • Pull request#118zhouxiangxin19982025-07-10 12:00
  • Issue comment#76BradKML2025-06-01 07:16
    Consider using the RL algorithm -GRPO training?
  • Issue comment#76caoshiyi2025-05-30 17:13
    Consider using the RL algorithm -GRPO training?
  • Issue comment#13BradKML2025-05-30 05:33
    [Roadmap] SkyThought Roadmap
  • Pull request#116DachengLi12025-05-18 03:53
  • Pull request#116DachengLi12025-05-18 03:53
  • Pull request#115DachengLi12025-05-12 18:55
  • Issue comment#113SumanthRH2025-05-08 17:57
    How to pass the `trust_remote_code=True` parameter for some new models?
  • Issue comment#113armsp2025-05-08 09:20
    How to pass the `trust_remote_code=True` parameter for some new models?
  • Issue#113armsp2025-05-08 09:20
    How to pass the `trust_remote_code=True` parameter for some new models?
  • Issue#114Aisp12025-05-08 01:21
    TypeError for test time scaling
  • Issue#113armsp2025-05-07 16:55
    How to pass the `trust_remote_code=True` parameter for some new models?
  • Issue comment#112armsp2025-05-07 16:54
    How long do the evaluations take?
  • Issue#112armsp2025-05-07 16:53
    How long do the evaluations take?
  • Issue#112armsp2025-05-06 08:10
    How does do the evaluations take?
  • Issue#111ZijunSong2025-05-01 01:50
    [HELP] The ray package version.
  • Pull request#110SumanthRH2025-04-22 01:04
  • Pull request#110SumanthRH2025-04-22 00:23

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 3,134 stars here means stars gained during the window, not the repo's star count.