Time Series Forecasting
Transformers
Safetensors
foundation models
pretrained models
time series foundation models
time series
time-series
timeseries
forecasting
observability
Eval Results (legacy)
Instructions to use Datadog/Toto-Open-Base-1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Datadog/Toto-Open-Base-1.0 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Datadog/Toto-Open-Base-1.0", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from Datadog/Toto-Open-Base-1.0: direct link, hf CLI and curl.
- Browser
- Download file 582 Bytes
-
https://huggingface.co/Datadog/Toto-Open-Base-1.0/resolve/eb5aa18de4f19370261a0ca59b2494c1d0517f96/config.json
- Command line
-
hf download hf://Datadog/Toto-Open-Base-1.0@eb5aa18de4f19370261a0ca59b2494c1d0517f96/config.json
-
curl -L -o config.json https://huggingface.co/Datadog/Toto-Open-Base-1.0/resolve/eb5aa18de4f19370261a0ca59b2494c1d0517f96/config.json
582 Bytes
| { | |
| "patch_size": 64, | |
| "stride": 64, | |
| "embed_dim": 768, | |
| "num_layers": 12, | |
| "num_heads": 12, | |
| "mlp_hidden_dim": 3072, | |
| "dropout": 0.1, | |
| "spacewise_every_n_layers": 12, | |
| "scaler_cls": "<class 'model.scaler.CausalPatchStdMeanScaler'>", | |
| "output_distribution_classes": [ | |
| "<class 'model.distribution.MixtureOfStudentTsOutput'>" | |
| ], | |
| "spacewise_first": false, | |
| "output_distribution_kwargs": { | |
| "k_components": 24 | |
| }, | |
| "use_memory_efficient_attention": true, | |
| "stabilize_with_global": true, | |
| "scale_factor_exponent": 10.0 | |
| } |