Official Pytorch Implementation for MathGLM 同学们写了一个MathGLM paper，网页链接，在数学的数据上训练了一下，只需要20亿参数，数学任务可以做得很好，也不需要去overfitting榜单，甚至超过GPT-4。不过。。。。。。怎么说呢，模型一下子变成了一个专用模型，通用能力减弱了。。。。算是一个探索性工作，模型和代码也开源出来了在github上，所有的结果可以重现
active 2023-09-10 → 2026-01-13 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 857 days from 2023-09-10 to 2026-01-13. Pushes: 10 total, peak 4 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 11 total, peak 2 in a day. Comments: 8 total, peak 1 in a day. Stars: 249 total, peak 25 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 |
|---|---|---|---|---|
| zyang-16 | 11 | 10 | 0 | 1 |
| maxsu | 3 | 0 | 0 | 1 |
| muelletm | 3 | 0 | 0 | 1 |
| zhouyonglong | 3 | 0 | 0 | 2 |
| kaibush | 1 | 0 | 0 | 1 |
| hsbhc | 1 | 0 | 0 | 0 |
| Pobby321 | 1 | 0 | 0 | 0 |
| vincywong | 1 | 0 | 0 | 0 |
| wujingbo-web | 1 | 0 | 0 | 0 |
| Ricky24680 | 1 | 0 | 0 | 1 |
| black-zero358 | 1 | 0 | 0 | 1 |
| coldwater2000 | 1 | 0 | 0 | 0 |
| RebelYoung | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#12hsbhc2024-10-21 01:47作者打算开源Arithmetic Training Dataset吗
- Issue comment#5kaibush2023-12-27 08:19Using sat framework inference mathglm-10B to report an error
- Issue#11vincywong2023-12-25 16:25下载了MathGLM-2B模型，在Arithmetic上执行inference.sh报错
- Issue comment#6black-zero3582023-11-17 04:52ResolvePackageNotFound: - deepspeed=0.6.0 - icetk==0.0.7
- Issue comment#6Ricky246802023-11-15 07:45ResolvePackageNotFound: - deepspeed=0.6.0 - icetk==0.0.7
- Issue#9Pobby3212023-10-11 00:58inference 报错
- Issue comment#8zyang-162023-10-10 11:41按照env.yml的要求安装环境，执行inference.sh报错
- Issue comment#5zhouyonglong2023-10-03 01:18Using sat framework inference mathglm-10B to report an error
- Issue comment#5zhouyonglong2023-10-02 07:44Using sat framework inference mathglm-10B to report an error
- Issue#7zhouyonglong2023-09-26 07:10ModelScope上的Demo报error
- Issue#6RebelYoung2023-09-26 03:56ResolvePackageNotFound: - deepspeed=0.6.0 - icetk==0.0.7
- Issue comment#1maxsu2023-09-24 06:19Add a category theory benchmark
- Issue#1maxsu2023-09-24 06:19Add a category theory benchmark
- Issue#5coldwater20002023-09-23 11:51Using sat framework inference mathglm-10B to report an error
- Issue#4wujingbo-web2023-09-18 06:39MathGLM-ChatGLM2-6B 清华云盘还没有上传模型文件~~
- Issue comment#2muelletm2023-09-15 07:07License
- Issue#3muelletm2023-09-15 07:01Data Generation Code
- Issue#2muelletm2023-09-15 06:54License
- Issue#1maxsu2023-09-13 21:43Add a category theory benchmark
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 249 stars here means stars gained during the window, not the repo's star count.