Skip to content

active 2025-06-272026-02-28 (UTC)

Partial coverage11,226 / 11,955 hourly files (94%) · 2 absent upstream · 726 failed, retryable2025-03-302026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
136
Pushes
2
Pull requests
0
Issues
16
Stars
94
Forks
5

Activity over time

Daily event counts in the loaded window

Line chart, 247 days from 2025-06-27 to 2026-02-28. Pushes: 2 total, peak 1 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 16 total, peak 3 in a day. Comments: 16 total, peak 2 in a day. Stars: 94 total, peak 20 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
qize-yqz8106
wyclike5002
qq314159264001
AlexiaJM1000
wwxs123W1000
King-king4241000
gengenkai1000
shiyongde1000
221250110NJUSE1000
Yuxuan20031000
xlchen02051001
vegetabledogzy1000
cheliu-computation1001

Recent activity

Latest issues, pull requests and releases

  • Issue#17wwxs123W2025-12-23 06:54
    A question about the frame and FPS settings in your paper.
  • Issue#16vegetabledogzy2025-10-21 08:23
    Increasing the batch_size set in stage2 will result in an error. Is it because a larger batch_size is not supported?
  • Issue#15gengenkai2025-09-10 15:52
    Why not show your model's results on OmniBench?
  • Issue comment#12cheliu-computation2025-08-28 03:24
    How to reproduce Qwen2.5-Omni-7B-Thinker's 64.20% Result on IntentBench
  • Issue#14221250110NJUSE2025-08-17 11:43
    Request for Preprocessed qa_think.json Files for Daily-Omni and WorldSense
  • Issue#13King-king4242025-07-31 09:15
    Any code for running a demo?
  • Issue comment#11qize-yqz2025-07-31 05:13
    data_config/rollout_stage1.json?
  • Issue comment#12qize-yqz2025-07-24 11:44
    How to reproduce Qwen2.5-Omni-7B-Thinker's 64.20% Result on IntentBench
  • Issue comment#12shouzhoupeng2025-07-24 02:42
    How to reproduce Qwen2.5-Omni-7B-Thinker's 64.20% Result on IntentBench
  • Issue comment#12cheliu-computation2025-07-23 16:48
    How to reproduce Qwen2.5-Omni-7B-Thinker's 64.20% Result on IntentBench
  • Issue comment#12qize-yqz2025-07-22 10:52
    How to reproduce Qwen2.5-Omni-7B-Thinker's 64.20% Result on IntentBench
  • Issue#12shouzhoupeng2025-07-22 03:24
    How to reproduce Qwen2.5-Omni-7B-Thinker's 64.20% Result on IntentBench
  • Issue comment#11qize-yqz2025-07-18 09:46
    data_config/rollout_stage1.json?
  • Issue#11shiyongde2025-07-18 04:28
    data_config/rollout_stage1.json?
  • Issue comment#10qize-yqz2025-07-17 06:15
    Why don't we need to set the user part of the labels to -100 in sft.py?
  • Issue#9wyclike2025-07-16 07:10
    How could get the other two evaluation datasets?
  • Issue comment#7wyclike2025-07-16 07:07
    Why set 'use_audio_in_video' false?
  • Issue comment#7qize-yqz2025-07-16 04:02
    Why set 'use_audio_in_video' false?
  • Issue#8wyclike2025-07-15 14:12
    typo error
  • Issue comment#7wyclike2025-07-15 12:06
    Why set 'use_audio_in_video' false?
  • Issue comment#7qize-yqz2025-07-15 08:29
    Why set 'use_audio_in_video' false?
  • Issue#7wyclike2025-07-15 03:15
    Why set 'use_audio_in_video' false?
  • Issue comment#6qq314159262025-07-14 10:03
    Working with VLLM
  • Issue#6qq314159262025-07-12 15:00
    Working with VLLM
  • Issue#5qq314159262025-07-12 08:29
    No chat_template in tokenizer_config.json

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 94 stars here means stars gained during the window, not the repo's star count.