t0-alpha-onnx-int8 / README.md
TobiasPitters's picture
Upload README.md with huggingface_hub
8c43adf verified
|
Raw
History Blame Contribute Delete
1.25 kB
---
license: apache-2.0
base_model: theforecastingcompany/t0-alpha
tags:
- time-series
- forecasting
- onnx
- onnxruntime
- quantized
- zero-shot
---
# t0-alpha (int8 ONNX)
int8 ONNX export of [theforecastingcompany/t0-alpha](https://huggingface.co/theforecastingcompany/t0-alpha) (Apache-2.0), quantized as: dynamic per-channel QInt8.
int8 output verified within 15.2% of forecast spread (mean 3%) of the official `T0Forecaster.predict()`. Unofficial export, not
affiliated with or endorsed by the model authors.
## Contract
| input | dtype | shape | notes |
|---|---|---|---|
| `context` | float32 | `['batch', 512]` | NaN = missing; left-pad short series with NaN |
Output `quantiles`: float32 `['batch', 64, 5]`. Quantile levels: `[0.1, 0.25, 0.5, 0.75, 0.9]`.
One forward pass. Left-pad short series with NaN (the model is missing-aware; padding is exactly equivalent to the natural-length call). Median is level index 2. Univariate graph; for the multivariate `group_ids` variant run `scripts/export_t0_onnx.py --grouped`.
See `manifest.json` for the machine-readable contract and the artifact's
sha256. `LICENSE` is Apache-2.0; when the upstream repo ships a `NOTICE`
file it is republished here unchanged, as the license requires.