Downloads · 30 days
0
tinycast-onnx-int8
sktime/tinycast-onnx-int8
tinycast-onnx-int8 is a machine learning model from sktime. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
int8 ONNX export of raws-labs/tinycast (Apache-2.0), quantized as: dynamic per-channel QInt8, MatMul-only; dilated convs and interface projections kept fp32 (measured recipe).
Access
Public
Updated Sep 1, 2026
Repo size
1.6 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx1.6 MB · 99%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Sep 1, 2026
- Updated
- Sep 1, 2026
- SHA
- 6bef0734
Base models
Model card
From the Hugging Face model README
TinyCast (int8 ONNX)
int8 ONNX export of raws-labs/tinycast (Apache-2.0), quantized as: dynamic per-channel QInt8, MatMul-only; dilated convs and interface projections kept fp32 (measured recipe).
int8 verified within 4.1% of forecast spread of the official TinyCastPredictor.predict(), 15-block rollouts included (fp32 export within 0.0003%). 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.
- License
- apache-2.0
- Created
- Sep 1, 2026
- Updated
- Sep 1, 2026