0
stars
5
commits
2
linked in READMEs
Sep 1, 2026
updated
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.
Contributors
5 commits
Similar repos
Linked in READMEs
0
stars
5
commits
2
linked in READMEs
Sep 1, 2026
updated
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.
Similar repos
Linked in READMEs
Contributors
5 commits