Downloads · 30 days
0
toto2-22m-onnx
sktime/toto2-22m-onnx
toto2-22m-onnx 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.
Unquantized fp32 ONNX export of Datadog/Toto-2.0-22m (Apache-2.0).
Access
Public
Updated Sep 1, 2026
Repo size
111 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx111 MB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Sep 1, 2026
- Updated
- Sep 1, 2026
- SHA
- 0748a88d
Base models
Model card
From the Hugging Face model README
Toto-2.0-22m (fp32 ONNX)
Unquantized fp32 ONNX export of Datadog/Toto-2.0-22m (Apache-2.0).
fp32 output verified within 0.0003% of forecast spread of the official toto2.Toto2Model.forecast(). Unofficial export, not
affiliated with or endorsed by the model authors.
Contract
| input | dtype | shape | notes |
|---|---|---|---|
context | float32 | ['variates', 2048] | NaN = missing; left-pad short series with NaN |
series_ids | int64 | ['variates'] | variates sharing an id are forecast jointly through variate-axis attention; distinct ids = independent |
Output quantiles: float32 ['variates', 96, 9]. Quantile levels: [0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9].
One parallel pass to 96 steps. Left-pad short series with NaN (missing-aware). Median is level index 4.
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