visual centric task
active 2025-02-26 → 2026-02-20 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 360 days from 2025-02-26 to 2026-02-20. Pushes: 41 total, peak 32 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 8 total, peak 2 in a day. Comments: 16 total, peak 3 in a day. Stars: 257 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
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| xirui-li | 39 | 36 | 0 | 3 |
| HengguangZhou | 6 | 5 | 0 | 0 |
| ruolinsss | 3 | 0 | 0 | 2 |
| Alsac | 2 | 0 | 0 | 2 |
| lerogo | 2 | 0 | 0 | 2 |
| lst627 | 2 | 0 | 0 | 2 |
| li-tianqi | 2 | 0 | 0 | 1 |
| Sisi0518 | 1 | 0 | 0 | 0 |
| xray1111 | 1 | 0 | 0 | 0 |
| dingtine | 1 | 0 | 0 | 0 |
| kasjfksj | 1 | 0 | 0 | 1 |
| yangluo23 | 1 | 0 | 0 | 1 |
| PangziZhang523 | 1 | 0 | 0 | 1 |
| yogurt1127 | 1 | 0 | 0 | 1 |
| zhuqiming678 | 1 | 0 | 0 | 0 |
| Guardian-in-the-WF | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#7yogurt11272025-04-27 06:23request help for code bug
- Issue comment#12lerogo2025-03-27 06:54Aha moment analysis
- Issue comment#12lerogo2025-03-27 06:39Aha moment analysis
- Issue comment#6kasjfksj2025-03-25 22:03Chat template of 'Qwen/Qwen2-VL-2B' (Base model)
- Issue comment#7PangziZhang5232025-03-25 05:16request help for code bug
- Issue#16HengguangZhou2025-03-23 04:00what the dataset is when doing SFT and RL and instruction fine-tune
- Issue comment#12yangluo232025-03-22 01:36Aha moment analysis
- Issue#16zhuqiming6782025-03-19 04:04what the dataset is when doing SFT and RL and instruction fine-tune
- Issue comment#13ruolinsss2025-03-14 03:25Questions about reproducing training results with default configuration
- Issue comment#14ruolinsss2025-03-14 03:23Training speed of base model vs intruct model
- Issue#14ruolinsss2025-03-14 03:23Training speed of base model vs intruct model
- Issue comment#11li-tianqi2025-03-11 02:12What is the expected training speed?
- Issue#11li-tianqi2025-03-11 02:12What is the expected training speed?
- Issue#8Sisi05182025-03-08 07:20multi-image training
- Issue comment#7xirui-li2025-03-08 00:54request help for code bug
- Issue#7dingtine2025-03-08 00:48request help for code bug
- Issue comment#6lst6272025-03-08 00:26Chat template of 'Qwen/Qwen2-VL-2B' (Base model)
- Issue comment#6lst6272025-03-07 02:33Chat template of 'Qwen/Qwen2-VL-2B' (Base model)
- Issue comment#3Alsac2025-03-06 03:32Training method
- Issue#5xray11112025-03-06 03:25seems like the model's reflection thinking is nonsense?
- Issue comment#3xirui-li2025-03-06 03:22Training method
- Issue comment#3Alsac2025-03-06 03:16Training method
- Issue comment#2xirui-li2025-03-05 06:44model checkpoint
- Issue#2Guardian-in-the-WF2025-03-05 05:32model checkpoint
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 257 stars here means stars gained during the window, not the repo's star count.