Time Series Forecasting
Transformers
Safetensors
Timer-S1
time series
time-series
forecasting
foundation models
pretrained models
time series foundation models
custom_code
Instructions to use bytedance-research/Timer-S1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bytedance-research/Timer-S1 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("bytedance-research/Timer-S1", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -76,7 +76,7 @@ batch_size, lookback_length = 64, 11520
|
|
| 76 |
seqs = torch.randn(batch_size, lookback_length).to(model.device)
|
| 77 |
|
| 78 |
# Note that Timer-S1 generates predictions at fixed quantile levels
|
| 79 |
-
forecast_length =
|
| 80 |
|
| 81 |
output = model.generate(seqs, max_new_tokens=forecast_length, revin=True)
|
| 82 |
|
|
|
|
| 76 |
seqs = torch.randn(batch_size, lookback_length).to(model.device)
|
| 77 |
|
| 78 |
# Note that Timer-S1 generates predictions at fixed quantile levels
|
| 79 |
+
forecast_length = 256
|
| 80 |
|
| 81 |
output = model.generate(seqs, max_new_tokens=forecast_length, revin=True)
|
| 82 |
|