KimMeen/Time-LLM
[ICLR 2024] Official implementation of " 🦙 Time-LLM: Time Series Forecasting by Reprogramming Large Language Models"
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.
Stars
2,563
Forks
453
Language
Python
License
Apache-2.0
Category
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.
Related models
om-ai-lab/VLM-R1
Solve Visual Understanding with Reinforced VLMs
bytedance/SALMONN
SALMONN family: A suite of advanced multi-modal LLMs
NVlabs/OmniVinci
OmniVinci is an omni-modal LLM for joint understanding of vision, audio, and language.
fixie-ai/ultravox
A fast multimodal LLM for real-time voice
bytedance/video-SALMONN-2
video-SALMONN 2 is a powerful audio-visual large language model (LLM) that generates...