Time Series Forecasting
Safetensors
PyTorch
MLX
tfc-t0
time-series
forecasting
probabilistic-forecasting
foundation-models
pretrained-models
transformer
multivariate
known-future-covariates
open-weights
covariates
apple-silicon
model_hub_mixin
pytorch_model_hub_mixin
Eval Results (legacy)
Instructions to use theforecastingcompany/t0-alpha with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use theforecastingcompany/t0-alpha with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download theforecastingcompany/t0-alpha --local-dir t0-alpha
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download config.json from theforecastingcompany/t0-alpha: direct link, hf CLI and curl.
- Browser
- Download file 250 Bytes
-
https://huggingface.co/theforecastingcompany/t0-alpha/resolve/main/config.json
- Command line
-
hf download hf://theforecastingcompany/t0-alpha/config.json
-
curl -L -o config.json https://huggingface.co/theforecastingcompany/t0-alpha/resolve/main/config.json
250 Bytes
| { | |
| "dropout": 0.1, | |
| "embed_dim": 512, | |
| "group_every_n": 3, | |
| "mlp_hidden_dim": 2048, | |
| "num_heads": 8, | |
| "num_layers": 24, | |
| "patch_size": 32, | |
| "quantile_levels": [ | |
| 0.1, | |
| 0.25, | |
| 0.5, | |
| 0.75, | |
| 0.9 | |
| ], | |
| "scaler_use_arcsinh": true | |
| } |