DeepSeekMath: 在开放语言模型中突破数学推理的极限
active 2024-02-06 → 2026-06-25 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 871 days from 2024-02-06 to 2026-06-25. Pushes: 6 total, peak 3 in a day. Pull requests: 5 total, peak 1 in a day. Issues: 45 total, peak 9 in a day. Comments: 56 total, peak 15 in a day. Stars: 2,803 total, peak 242 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 |
|---|---|---|---|---|
| ZhihongShao | 12 | 3 | 0 | 5 |
| GanjinZero | 7 | 0 | 0 | 5 |
| hzwer | 6 | 0 | 0 | 3 |
| brando90 | 3 | 0 | 0 | 2 |
| yapdianang | 3 | 0 | 0 | 1 |
| DeepSeekPH | 3 | 0 | 0 | 3 |
| guoday | 3 | 1 | 1 | 1 |
| cyzhh | 3 | 0 | 0 | 2 |
| hxypqr | 2 | 0 | 0 | 2 |
| AceCHQ | 2 | 0 | 0 | 0 |
| Wangpeiyi9979 | 2 | 0 | 0 | 2 |
| mohhao | 2 | 0 | 0 | 1 |
| ctkqiang | 2 | 0 | 0 | 2 |
| longwenao | 2 | 0 | 0 | 2 |
| ThatOneCalculator | 2 | 0 | 0 | 1 |
| DolbyUUU | 2 | 0 | 0 | 1 |
| liyy96 | 2 | 0 | 0 | 1 |
| ChengpengLi1003 | 2 | 0 | 0 | 1 |
| pkuzqh | 2 | 2 | 0 | 0 |
| beichenzbc | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Pull request#47this-vishalsingh2026-02-17 05:23
- Issue#44fatimaelzahraslimani-creator2025-12-14 11:16théorme de girsanov
- Issue comment#38LiuRicky2025-09-11 11:33DPO的梯度系数推导不够严格？
- Issue comment#34ctkqiang2025-09-06 16:45Mathai
- Issue comment#29ctkqiang2025-07-23 00:36Any Plan to release the code of GRPO?
- Issue comment#29sunyufan12152025-07-21 08:37Any Plan to release the code of GRPO?
- Pull request#41jayeshthk2025-06-19 11:58
- Issue comment#36ctkqiang2025-04-18 17:06想入职你们公司，当个跑腿的都行
- Issue comment#23HaoRenkk1232025-04-16 03:28关于sft阶段中数据拼接的问题
- Issue comment#21ThugyBoy2025-04-14 11:56Unable to get evaluation results
- Issue comment#39DolbyUUU2025-03-31 13:45Model Size Choices in Evaluation
- Issue comment#39pranitdandewarofficial2025-03-29 11:48Model Size Choices in Evaluation
- Issue comment#38liyy962025-03-17 08:14DPO的梯度系数推导不够严格？
- Issue comment#38longwenao2025-03-17 07:29DPO的梯度系数推导不够严格？
- Issue comment#40longwenao2025-03-17 07:27关于强化学习GRPO训练的问题
- Issue#40kyle1413772025-03-13 12:36关于强化学习GRPO训练的问题
- Issue#39DolbyUUU2025-03-13 09:15Model Size Choices in Evaluation
- Issue comment#29chaitanya1chawla2025-03-12 03:14Any Plan to release the code of GRPO?
- Issue#38liyy962025-02-25 08:54DPO的梯度系数推导不够严格？
- Issue#37itmorn2025-02-14 17:17论文里PPO的公式写错了
- Issue#36155657636732025-02-14 07:14想入职你们公司，当个跑腿的都行
- Issue comment#29owlsan492025-02-08 08:53Any Plan to release the code of GRPO?
- Issue#35KholmogorovEA2025-02-01 23:10D
- Issue comment#17CameronJRidgley2025-01-30 16:37[fixed] the merging output is incorrect, when parallel_num=1
- Issue comment#17felixArbucias2025-01-30 16:37[fixed] the merging output is incorrect, when parallel_num=1
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 2,803 stars here means stars gained during the window, not the repo's star count.