Skip to content

Qwen3Guard is a multilingual guardrail model series developed by the Qwen team at Alibaba Cloud.

active 2025-09-232026-06-30 (UTC)

Partial coverage11,299 / 12,120 hourly files (93%) · 2 absent upstream · 818 failed, retryable2025-03-232026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
240
Pushes
5
Pull requests
0
Issues
9
Stars
210
Forks
8

Activity over time

Daily event counts in the loaded window

Line chart, 281 days from 2025-09-23 to 2026-06-30. Pushes: 5 total, peak 2 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 9 total, peak 1 in a day. Comments: 7 total, peak 3 in a day. Stars: 210 total, peak 58 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
chenhan975302
haidequanbu4003
zjysteven3001
hzhwcmhf2200
ciaoyizhen2000
HLSUD1000
avicbj1000
gaozhiguang1000
mj199610121000
xinjicong1001

Recent activity

Latest issues, pull requests and releases

  • Issue comment#7haidequanbu2026-02-28 09:48
    Clarification on support for multiple harmful categories in a single prompt
  • Issue#13avicbj2025-12-01 02:56
    License?
  • Issue#15haidequanbu2025-11-14 09:32
    Labels in Multilingual Evaluation
  • Issue comment#15haidequanbu2025-11-14 09:32
    Labels in Multilingual Evaluation
  • Issue#15HLSUD2025-11-07 10:46
    Labels in Multilingual Evaluation
  • Issue#14gaozhiguang2025-11-06 10:17
    如何基于GSPO训练qwen3-4b模型,增强其安全能力
  • Issue comment#9xinjicong2025-10-17 06:49
    怎么样可以降低模型输出controversial 更多输出准确的safe、unsafe呢
  • Issue comment#5chenhan972025-10-17 03:37
    请问分类标签支持新增或者自定义吗
  • Issue comment#2chenhan972025-10-17 03:34
    hello,train set is open?
  • Issue comment#6zjysteven2025-10-04 19:49
    关于技术报告中的标签清理的两点细节
  • Issue#6zjysteven2025-10-04 19:49
    关于技术报告中的标签清理的两点细节
  • Issue#8ciaoyizhen2025-09-30 01:20
    训练后,epoch=1表现正常,epoch=2直接输出!!!
  • Issue comment#6haidequanbu2025-09-29 07:05
    关于技术报告中的标签清理的两点细节
  • Issue#6zjysteven2025-09-28 05:43
    关于技术报告中的标签清理的两点细节
  • Issue#5mj199610122025-09-26 07:38
    请问分类标签支持新增或者自定义吗
  • Issue#4ciaoyizhen2025-09-24 09:35
    后续会提供微调代码吗?

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 210 stars here means stars gained during the window, not the repo's star count.