chenhan97/TimeLlama

The official repo of TimeLlama, an instruction-finetuned Llama2 series that improve complex temporal reasoning ability.

38
/ 100
Emerging

This project helps you predict future events and understand why those predictions are made, based on past events described in text. You input a document containing multiple events and a query about a potential future event, and it outputs a prediction (yes, no, or unsure) along with a clear, step-by-step explanation. This is ideal for anyone who needs to make informed decisions or analyze trends by understanding the temporal flow of information, such as business strategists, risk analysts, or researchers in social sciences.

No commits in the last 6 months.

Use this if you need to predict future outcomes from event data and require a clear, explainable rationale behind each prediction, rather than just a 'black box' answer.

Not ideal if your task involves simple fact retrieval, sentiment analysis, or predictions that do not rely on complex temporal relationships between events.

event-forecasting temporal-analysis predictive-modeling causal-inference risk-assessment
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

43

Forks

7

Language

Python

License

MIT

Last pushed

Nov 13, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/chenhan97/TimeLlama"

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