Welcome to the official YHat Labs organization on Hugging Face!
YHat Labs builds foundation models for time series and tabular data, and systems that forecast real-world events. Our models are served through a hosted API; this organization holds their model cards and benchmark records.
The Chakra model family
| Model | Data | What it does | Availability |
|---|---|---|---|
| ChakraTS | time series | zero-shot probabilistic forecasting: nine quantiles per step, known-future covariates, any regular frequency | API, commercial |
| ChakraTS-Lab | time series | research configuration of ChakraTS, used for benchmark entries | evaluation on request |
| ChakraTab | tables | classification and regression on tabular data | coming |
Benchmarks
We evaluate on the public leaderboards under their official protocols and publish the result files and the notebooks that regenerate them: GIFT-Eval and fev-bench for time series, TabArena for tabular. Benchmark data is never used for anything other than scoring.