theforecastingcompany
/

t0-alpha

Time Series Forecasting

probabilistic-forecasting

foundation-models

pretrained-models

model_hub_mixin

pytorch_model_hub_mixin

Eval Results (legacy)

Model card Files Files and versions

LTMeyer commited on 3 days ago

Commit

b7c130e

·

unverified ·

1 Parent(s): 01a3e2f

doc: restore emojis section headers

Files changed (1) hide show

README.md +7 -7

README.md CHANGED Viewed

@@ -75,7 +75,7 @@ Known-future covariates can include calendar features, planned events, holidays,
 Forecasts should be treated as probabilistic estimates, not guarantees.
-## Forecasting With Covariates
 `t0` leverages covariate information, in the past and future when available, to improve its forecast.
@@ -105,7 +105,7 @@ pip install "tfc-t0[evaluation]"
 pip install "tfc-t0[plot]"
 ```
-## Quickstart
 The simplest path is a univariate forecast through `predict`:
@@ -161,7 +161,7 @@ out.median     # (2, 64)
 - Longer horizons use autoregressive rollout.
 - Returned forecasts are finite `float32` tensors on the model's device.
-## Architecture
 `t0` is a decoder-style patch transformer.
@@ -194,13 +194,13 @@ At inference, target and historical variates are normalized with causal running
 Users should also evaluate `t0-alpha` on their own historical backtests. Useful checks include quantile loss, CRPS, MASE, empirical quantile coverage, calibration, and breakdowns by frequency, horizon, domain, history length, and covariate availability.
-## Public API
 - `T0Forecaster`: The actual PyTorch module class.
 - `Forecast`: return object encapsulating forecasted quantiles.
 - `T0Config`: dataclass to configure the model.
-## Lineage and Attributions
 `t0` builds on ideas from open-source forecasting models. We gratefully acknowledge:
@@ -213,7 +213,7 @@ Code-level attributions are listed in [`NOTICE`](NOTICE), all under Apache-2.0.
 Training compute and carbon emissions are not currently reported.
-## Citation
 ```bibtex
 @misc{tfc-t0,
@@ -224,7 +224,7 @@ Training compute and carbon emissions are not currently reported.
 }
 ```
-## License
 Apache-2.0. See [`LICENSE`](LICENSE) and [`NOTICE`](NOTICE).

 Forecasts should be treated as probabilistic estimates, not guarantees.
+## 📈 Forecasting With Covariates
 `t0` leverages covariate information, in the past and future when available, to improve its forecast.
 pip install "tfc-t0[plot]"
 ```
+## 🚀 Quickstart
 The simplest path is a univariate forecast through `predict`:
 - Longer horizons use autoregressive rollout.
 - Returned forecasts are finite `float32` tensors on the model's device.
+## 🏗️ Architecture
 `t0` is a decoder-style patch transformer.
 Users should also evaluate `t0-alpha` on their own historical backtests. Useful checks include quantile loss, CRPS, MASE, empirical quantile coverage, calibration, and breakdowns by frequency, horizon, domain, history length, and covariate availability.
+## 🧰 Public API
 - `T0Forecaster`: The actual PyTorch module class.
 - `Forecast`: return object encapsulating forecasted quantiles.
 - `T0Config`: dataclass to configure the model.
+## 🧬 Lineage and Attributions
 `t0` builds on ideas from open-source forecasting models. We gratefully acknowledge:
 Training compute and carbon emissions are not currently reported.
+## 📚 Citation
 ```bibtex
 @misc{tfc-t0,
 }
 ```
+## ⚖️ License
 Apache-2.0. See [`LICENSE`](LICENSE) and [`NOTICE`](NOTICE).