Transformers
crypto
deep-learning
time-series
forecasting
transformer
state-space-models
open-source
scaling-laws
Instructions to use duonlabs/apogee-21.3M-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use duonlabs/apogee-21.3M-base with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("duonlabs/apogee-21.3M-base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update handler.py
Browse files- handler.py +1 -1
handler.py
CHANGED
|
@@ -86,7 +86,7 @@ class EndpointHandler:
|
|
| 86 |
pair, freq = inputs["pair"], inputs["frequency"]
|
| 87 |
pair = "".join(pair.split("/"))
|
| 88 |
pair = f"binance.{pair.upper()}" if "." not in pair else pair
|
| 89 |
-
timestamps = torch.tensor(inputs["timestamps"])
|
| 90 |
samples = torch.tensor([inputs["open"], inputs["high"], inputs["low"], inputs["close"], inputs["volume"]], dtype=torch.float32).T.contiguous()
|
| 91 |
steps = data.pop("steps", 4)
|
| 92 |
n_scenarios = data.pop("n_scenarios", 32)
|
|
|
|
| 86 |
pair, freq = inputs["pair"], inputs["frequency"]
|
| 87 |
pair = "".join(pair.split("/"))
|
| 88 |
pair = f"binance.{pair.upper()}" if "." not in pair else pair
|
| 89 |
+
timestamps = torch.tensor(list(map(int, inputs["timestamps"])))
|
| 90 |
samples = torch.tensor([inputs["open"], inputs["high"], inputs["low"], inputs["close"], inputs["volume"]], dtype=torch.float32).T.contiguous()
|
| 91 |
steps = data.pop("steps", 4)
|
| 92 |
n_scenarios = data.pop("n_scenarios", 32)
|