[Preprint 2025] Thinkless: LLM Learns When to Think
active 2025-05-20 → 2026-03-02 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 287 days from 2025-05-20 to 2026-03-02. Pushes: 15 total, peak 3 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 4 total, peak 2 in a day. Comments: 26 total, peak 5 in a day. Stars: 127 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
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| VainF | 28 | 15 | 0 | 13 |
| 541wsy | 5 | 0 | 0 | 4 |
| s2014628 | 3 | 0 | 0 | 3 |
| CurryxIaoHu | 3 | 0 | 0 | 2 |
| Rinnolo | 1 | 0 | 0 | 1 |
| hxyyyds | 1 | 0 | 0 | 1 |
| andrearama | 1 | 0 | 0 | 1 |
| Goldbags01 | 1 | 0 | 0 | 0 |
| acoding-xuan | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#9VainF2025-08-29 18:22可以在npu上运行吗？
- Issue comment#10VainF2025-08-29 18:21For 7B models
- Issue comment#11VainF2025-08-29 18:19how to train on multi node
- Issue comment#8zhuhr9252025-07-19 16:44eval result issue
- Issue comment#8VainF2025-07-17 19:57eval result issue
- Issue comment#7VainF2025-06-29 13:00SFT issue
- Issue comment#7hxyyyds2025-06-29 08:48SFT issue
- Issue comment#4andrearama2025-06-20 19:32can i run the experiment using 4 v100 32GB gpu
- Issue comment#6VainF2025-06-19 16:53call for warmup code
- Issue#5541wsy2025-06-17 09:00After SFT warm-up, Model only generate <short>?
- Issue comment#5541wsy2025-06-17 08:59After SFT warm-up, Model only generate <short>?
- Issue#6acoding-xuan2025-06-17 02:28call for warmup code
- Issue comment#5VainF2025-06-13 18:41After SFT warm-up, Model only generate <short>?
- Issue comment#5541wsy2025-06-12 08:02After SFT warm-up, Model only generate <short>?
- Issue comment#5CurryxIaoHu2025-06-12 04:29After SFT warm-up, Model only generate <short>?
- Issue comment#3VainF2025-06-11 16:39使用Qwen-1.5B采样short answer的细节
- Issue comment#3CurryxIaoHu2025-06-10 06:51使用Qwen-1.5B采样short answer的细节
- Issue comment#4s20146282025-06-07 14:10can i run the experiment using 4 v100 32GB gpu
- Issue comment#5VainF2025-06-05 07:38After SFT warm-up, Model only generate <short>?
- Issue comment#4s20146282025-06-05 07:18can i run the experiment using 4 v100 32GB gpu
- Issue comment#5Rinnolo2025-06-05 05:58After SFT warm-up, Model only generate <short>?
- Issue comment#5541wsy2025-06-05 02:19After SFT warm-up, Model only generate <short>?
- Issue comment#5541wsy2025-06-05 02:19After SFT warm-up, Model only generate <short>?
- Issue comment#4s20146282025-06-04 12:43can i run the experiment using 4 v100 32GB gpu
- Issue comment#5VainF2025-06-04 12:21After SFT warm-up, Model only generate <short>?
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 127 stars here means stars gained during the window, not the repo's star count.