google-research/timesfm
timesfm
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
Builder
google-research
google-research • individual
Stars
20,342
Using upstream star count
Forks
1,983
Using upstream fork count
Open Issues
0
Activity Score
0/100
0 commits in 30d
Created
Apr 29, 2024
Project creation date
README Summary
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
Community Evaluation
Loading…AI Dev Skills
Unmapped
Foundation Model ArchitectureMulti-variate Time Series ModelingPre-trained Model Fine-tuningSelf-Supervised LearningTime Series AnalysisTransformer ArchitectureZero-shot Forecasting
Tags
Foundation Model ArchitectureMulti-variate Time Series ModelingPre-trained Model Fine-tuningSelf-Supervised LearningTime Series AnalysisTransformer ArchitectureZero-shot ForecastingForkedHuggingFaceJAXNumPyPyTorchPythonResearch / Papers
Taxonomy
Deployment Context
Modalities
Skill Areas
Recent Activity
Updated 2 months ago
7 Days
0
30 Days
0
90 Days
4
Quality
research- Quality
- high
- Maturity
- research
Categories
Learning ResourcesPrimaryData Science & AnalyticsFoundation ModelsModel TrainingSearch & Knowledge
PM Skills
Developer Platform
Languages
Python100.0%
Timeline
- Project created
- Apr 29, 2024
- Forked
- Mar 12, 2026
- Your last push
- 2 months ago
- Upstream last push
- 22 days ago
- Tracked since
- Mar 12, 2026
Similar Repos
pgvector cosine similarity · $0
Loading…