Time Series Forecasting
Transformers
Safetensors
tabby
feature-extraction
time-series
foundation-model
probabilistic-forecasting
quantile-regression
patchtst
custom_code
Instructions to use paris-noah/Tabby with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use paris-noah/Tabby with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("paris-noah/Tabby", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tools.py from paris-noah/Tabby: direct link, hf CLI and curl.
- Browser
- Download file 361 Bytes
-
https://huggingface.co/paris-noah/Tabby/resolve/main/tools.py
- Command line
-
hf download hf://paris-noah/Tabby/tools.py
-
curl -L -o tools.py https://huggingface.co/paris-noah/Tabby/resolve/main/tools.py
361 Bytes
| """Trimmed from models/tools.py: only what modeling_patchtst_fm.py imports.""" | |
| def count_parameters(model): | |
| total_params = sum(p.numel() for p in model.parameters()) | |
| grad_params = sum(p.numel() for p in model.parameters() if p.requires_grad) | |
| no_grad_params = total_params - grad_params | |
| return total_params, grad_params, no_grad_params | |