lqzxt/Time-R1
Time-R1 is a two-stage reinforcement fine-tuning framework that trains large language models to perform slow-thinking, step-by-step reasoning for accurate and explainable time series forecasting.
This project helps data scientists and analysts make more accurate future predictions from their time series data, such as sales figures, stock prices, or sensor readings. It takes your historical time series data as input and produces highly accurate forecasts, along with the step-by-step reasoning behind those predictions. It's designed for professionals who need reliable, explainable forecasts for decision-making.
Use this if you are a data scientist or analyst looking to significantly improve the accuracy and explainability of your time series forecasts using a sophisticated, 'slow-thinking' AI approach.
Not ideal if you need a quick, off-the-shelf forecasting solution without diving into advanced AI model training or have limited computational resources for large language model fine-tuning.
Stars
94
Forks
11
Language
Python
License
—
Category
Last pushed
Jan 28, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/lqzxt/Time-R1"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
cvs-health/uqlm
UQLM: Uncertainty Quantification for Language Models, is a Python package for UQ-based LLM...
PRIME-RL/TTRL
[NeurIPS 2025] TTRL: Test-Time Reinforcement Learning
sapientinc/HRM
Hierarchical Reasoning Model Official Release
tigerchen52/query_level_uncertainty
query-level uncertainty in LLMs
reasoning-survey/Awesome-Reasoning-Foundation-Models
✨✨Latest Papers and Benchmarks in Reasoning with Foundation Models