RM-R1: Unleashing the Reasoning Potential of Reward Models
active 2025-05-06 → 2026-03-23 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 322 days from 2025-05-06 to 2026-03-23. Pushes: 20 total, peak 7 in a day. Pull requests: 4 total, peak 4 in a day. Issues: 8 total, peak 2 in a day. Comments: 8 total, peak 2 in a day. Stars: 72 total, peak 6 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 |
|---|---|---|---|---|
| GaotangLi | 30 | 20 | 2 | 5 |
| Neroxsh | 6 | 0 | 2 | 2 |
| iamjanvijay | 2 | 0 | 0 | 1 |
| LUMO666 | 1 | 0 | 0 | 0 |
| yhl48 | 1 | 0 | 0 | 0 |
| socialism-redstar | 1 | 0 | 0 | 0 |
| krishnakanthnakkav2 | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#11GaotangLi2026-01-31 21:38Question on Using RM-R1 with Single-Response Inputs
- Issue#11krishnakanthnakkav22026-01-27 08:56Question on Using RM-R1 with Single-Response Inputs
- Issue#10yhl482025-08-18 22:08Question about custom verl trainer
- Issue#9iamjanvijay2025-08-14 00:48number of rollouts?
- Issue comment#9GaotangLi2025-08-13 02:14number of rollouts?
- Issue comment#9iamjanvijay2025-08-13 02:11number of rollouts?
- Issue#8socialism-redstar2025-07-06 06:42rlvr训练报错
- Issue comment#7Neroxsh2025-06-30 08:14response is “！！！” in qwen2.5-7B
- Issue comment#7GaotangLi2025-06-28 20:48response is “！！！” in qwen2.5-7B
- Issue#7Neroxsh2025-06-27 08:42response is “！！！” in qwen2.5-7B
- Issue#5LUMO6662025-06-27 07:45Have you used this method as reward model to train any RL experiments?
- Issue comment#5GaotangLi2025-06-26 04:33Have you used this method as reward model to train any RL experiments?
- Issue comment#6GaotangLi2025-06-26 04:20Evaluation scripts on RM-Bench and RMB
- Issue#2GaotangLi2025-06-06 04:18python version
- Issue comment#2Neroxsh2025-06-06 00:26python version
- Pull request#3GaotangLi2025-06-02 20:50
- Pull request#4GaotangLi2025-06-02 20:49
- Pull request#4Neroxsh2025-06-02 11:18
- Pull request#3Neroxsh2025-06-02 11:17
- Issue#1Neroxsh2025-05-28 05:06cant find rubric_rm.verl.trainer.main_ppo
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 72 stars here means stars gained during the window, not the repo's star count.