Skip to content

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 2023-08-30 → 2026-01-13 (UTC)

Complete coverage27,350 / 27,350 hourly files (100%) · 2 absent upstream2023-08-15 → 2026-09-27 (UTC)
Events
421
Pushes
36
Pull requests
0
Issues
14
Stars
330
Forks
28

Activity over time

Daily event counts in the loaded window

Line chart, 868 days from 2023-08-30 to 2026-01-13. Pushes: 36 total, peak 19 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 14 total, peak 3 in a day. Comments: 9 total, peak 1 in a day. Stars: 330 total, peak 29 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

ContributorContributionsPushesPRsComments
zyang-16383602
zhouyonglong4002
maxsu3001
muelletm3001
Pobby3212000
kaibush1001
hsbhc1000
vincywong1000
wujingbo-web1000
huangyn-pku1000
Ricky246801001
black-zero3581001
coldwater20001000
RebelYoung1000

Recent activity

Latest issues, pull requests and releases

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 330 stars here means stars gained during the window, not the repo's star count.