Reasoning version of QwenVL2.5 optimized for action recognition in videos (Experimental GRPO with LoRA support)
active 2025-04-13 → 2026-02-23 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 317 days from 2025-04-13 to 2026-02-23. Pushes: 68 total, peak 35 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 3 total, peak 3 in a day. Comments: 3 total, peak 2 in a day. Stars: 17 total, peak 2 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
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| nfsrules | 69 | 68 | 0 | 1 |
| wyn1015 | 3 | 0 | 0 | 1 |
| illusionnnnnnn | 2 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#1illusionnnnnnn2025-06-22 15:17Why is it this in line 73 while this comment is not cancelled in line 261 in qwen2.5VL-R1-main/src/training/modality_patch.py
- Issue comment#1nfsrules2025-06-22 04:56Why is it this in line 73 while this comment is not cancelled in line 261 in qwen2.5VL-R1-main/src/training/modality_patch.py
- Issue comment#2wyn10152025-06-20 16:25Is it that the training data is insufficient, or is the parameter setting not the same as in read.me? The output of this grpo after training the model is also incorrect. The ones after sft are also incorrect.
- Issue#2wyn10152025-06-20 13:52Is it that the training data is insufficient, or is the parameter setting not the same as in read.me? The output of this grpo after training the model is also incorrect. The ones after sft are also incorrect.
- Issue#2wyn10152025-06-20 13:511828/5000 Is it that the training data is insufficient, or is the parameter setting not the same as in read.me? The output of this grpo after training the model is also incorrect. The ones after sft are also incorrect.
- Issue#1illusionnnnnnn2025-06-20 05:56Why is it this in line 73 while this comment is not cancelled in line 261 in qwen2.5VL-R1-main/src/training/modality_patch.py
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 17 stars here means stars gained during the window, not the repo's star count.