Skip to content

thuml/Large-Time-Series-Model

View on GitHub ↗Related repositories →

fork from Official code of "Timer: Generative Pre-trained Transformers Are Large Time Series Models" (ICML 2024) and used for satellite data adaptation

active 2025-03-192026-07-04 (UTC)

Partial coverage11,365 / 12,234 hourly files (93%) · 2 absent upstream · 867 failed, retryable2025-03-192026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
248
Pushes
17
Pull requests
0
Issues
16
Stars
178
Forks
19

Activity over time

Daily event counts in the loaded window

Line chart, 473 days from 2025-03-19 to 2026-07-04. Pushes: 17 total, peak 4 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 16 total, peak 5 in a day. Comments: 18 total, peak 6 in a day. Stars: 178 total, peak 4 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
WenWeiTHU271506
Auditor12343002
jjjge2002
Luckier10082001
donghuang-cyber2001
RCR-LYY1000
AyumiTPK1000
wxc7771000
hackeren1001
Hzx16171000
yiyahei-eng1000
geasyheart1001
tbwang-clound1001
DawsonPeres1001
lim1164552675-ship-it1001

Recent activity

Latest issues, pull requests and releases

  • Issue#72AyumiTPK2026-01-19 10:25
    Can Timer run without a GPU?
  • Issue comment#71DawsonPeres2026-01-09 08:17
    feat(data): 添加数据清洗脚本和更新.gitignore配置
  • Issue comment#61lim1164552675-ship-it2025-12-22 07:56
    逆归一化开启后报错问题
  • Issue comment#68Luckier10082025-10-27 04:28
    训练自己数据模型的代码有示例吗
  • Issue#70Luckier10082025-10-25 17:10
    请问想做时序预测大模型的话,需要多少算力资源呢
  • Issue comment#69hackeren2025-09-12 09:59
    sundial目前不支持多变量时序预测吗?
  • Issue comment#68geasyheart2025-09-10 07:14
    训练自己数据模型的代码有示例吗
  • Issue#69wxc7772025-09-03 09:10
    sundial目前不支持多变量时序预测吗?
  • Issue#67yiyahei-eng2025-08-13 02:12
    异常点检测报错
  • Issue#65WenWeiTHU2025-07-21 08:48
    关于finetune_rate的疑问
  • Issue comment#66WenWeiTHU2025-07-21 08:46
    预测步长
  • Issue#64WenWeiTHU2025-07-21 08:42
    drop_last设置
  • Issue#66Hzx16172025-07-16 06:39
    预测步长
  • Issue#64RCR-LYY2025-06-26 03:40
    drop_last设置
  • Issue#63WenWeiTHU2025-06-02 18:53
    Sundial Code
  • Issue#60WenWeiTHU2025-05-26 07:49
    interpolation model
  • Issue comment#63WenWeiTHU2025-05-26 07:48
    Sundial Code
  • Issue comment#63tbwang-clound2025-05-20 03:28
    Sundial Code
  • Issue comment#59Auditor12342025-05-18 08:23
    What is the setup of anomaly detection checkpoints?
  • Issue#59Auditor12342025-05-18 08:23
    What is the setup of anomaly detection checkpoints?
  • Issue comment#62WenWeiTHU2025-05-18 07:57
    关于Timer的疑问
  • Issue comment#60WenWeiTHU2025-05-18 07:47
    interpolation model
  • Issue comment#59WenWeiTHU2025-05-18 07:47
    What is the setup of anomaly detection checkpoints?
  • Issue comment#57WenWeiTHU2025-05-18 07:46
    微调后预测指定步长
  • Issue comment#61WenWeiTHU2025-05-18 07:45
    逆归一化开启后报错问题

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 178 stars here means stars gained during the window, not the repo's star count.