KimMeen/Time-LLM

[ICLR 2024] Official implementation of " 🦙 Time-LLM: Time Series Forecasting by Reprogramming Large Language Models"

56
/ 100
Established

This project helps operations engineers, financial analysts, and market researchers predict future values based on historical trends, such as energy consumption or stock prices. It takes in your existing time series data, like a spreadsheet of daily sales or hourly sensor readings, and outputs accurate forecasts for upcoming periods. Anyone who needs to make informed decisions by understanding future patterns in their data would use this.

2,563 stars.

Use this if you need highly accurate predictions for various time series data, leveraging the advanced capabilities of large language models.

Not ideal if you prefer simpler, more traditional statistical methods for forecasting or if your data is not in a structured time series format.

predictive-analytics financial-forecasting demand-forecasting operations-planning market-trend-analysis
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

2,563

Forks

453

Language

Python

License

Apache-2.0

Last pushed

Oct 15, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/KimMeen/Time-LLM"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.