TinyCast (fp32 ONNX)
Unquantized fp32 ONNX export of raws-labs/tinycast (Apache-2.0).
fp32 output verified within 0.0003% of forecast spread of the official TinyCastPredictor.predict(), 15-block rollouts included. Unofficial export, not
affiliated with or endorsed by the model authors.
Contract
| input | dtype | shape | notes |
|---|---|---|---|
context |
float32 | ['batch', 2048] |
not supported - impute first (np.interp), left-pad with the FIRST value |
Output quantiles: float32 ['batch', 48, 9]. Quantile levels: [0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9].
One 48-step AR block per call. For longer horizons feed the raw median (index 4) back into the context and rerun; sort each step's 9 deciles ascending before use (official TinyCastPredictor semantics).
See manifest.json for the machine-readable contract and the artifact's
sha256.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for sktime/tinycast-onnx
Base model
raws-labs/tinycast