Pre-trained, Scalable, High-performance Reward Models via Policy Discriminative Learning.
active 2025-07-08 → 2026-02-01 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 209 days from 2025-07-08 to 2026-02-01. Pushes: 4 total, peak 3 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 12 total, peak 3 in a day. Comments: 6 total, peak 2 in a day. Stars: 95 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 |
|---|---|---|---|---|
| RowitZou | 4 | 1 | 0 | 1 |
| BeastyZ | 3 | 0 | 0 | 1 |
| moshouxiaomu | 3 | 0 | 0 | 1 |
| UmeanNever | 3 | 3 | 0 | 0 |
| kokolerk | 2 | 0 | 0 | 1 |
| Hasuer | 2 | 0 | 0 | 1 |
| zhouchunpong | 1 | 0 | 0 | 0 |
| lmx760581375 | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#9Hasuer2025-09-26 07:01Training framework used for pretraining and SFT
- Issue comment#9RowitZou2025-09-26 06:56Training framework used for pretraining and SFT
- Issue#9Hasuer2025-09-24 15:12Training framework used for pretraining and SFT
- Issue#8zhouchunpong2025-08-18 06:57使用OpenAI库来访问API
- Issue#7RowitZou2025-08-04 06:49rag eval
- Issue comment#6RowitZou2025-07-24 05:19Pretrain阶段有考虑过选择某个模型不同step的ckpt来作为对比学习的原材料么？
- Issue#7Kenwwww2025-07-24 01:09rag eval
- Issue#6caogang2025-07-23 10:12Pretrain阶段有考虑过选择某个模型不同step的ckpt来作为对比学习的原材料么？
- Issue comment#5BeastyZ2025-07-18 07:09vLLM支持
- Issue#5BeastyZ2025-07-18 07:09vLLM支持
- Issue#5BeastyZ2025-07-18 07:07vLLM支持
- Issue#3RowitZou2025-07-17 02:03May I ask if you have any plans to open source the pre-training data
- Issue comment#2kokolerk2025-07-16 02:51question about the reference settings
- Issue#4moshouxiaomu2025-07-14 09:17奖励输出范围疑问
- Issue#3lmx7605813752025-07-14 07:48May I ask if you have any plans to open source the pre-training data
- Issue#2kokolerk2025-07-14 07:28question about the reference settings
- Issue comment#1moshouxiaomu2025-07-10 02:37多轮对话与长system prompt适配询问
- Issue#1moshouxiaomu2025-07-09 08:48多轮对话与长system prompt适配询问
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 95 stars here means stars gained during the window, not the repo's star count.