Update README.md

README.md

@@ -24,6 +24,64 @@ MOMENT is a family of foundation models for general-purpose time-series analysis
 
 For details on MOMENT models, training data, and experimental results, please refer to the paper [MOMENT: A Family of Open Time-series Foundation Models](https://arxiv.org/pdf/2402.03885.pdf).
 
+# Usage
+
+Install the package using:
+```bash
+pip install git+https://github.com/moment-timeseries-foundation-model/moment-test.git
+```
+
+To load the pre-trained model for one of the tasks, use one of the following code snippets:
+
+**Forecasting**
+```python
+from moment import MOMENTPipeline
+
+model = MOMENTPipeline.from_pretrained(
+    "AutonLab/MOMENT-1-large", 
+    model_kwargs={
+        'task_name': 'forecasting',
+        'forecast_horizon': 96
+    },
+)
+model.init()
+```
+
+**Classification**
+```python
+from moment import MOMENTPipeline
+
+model = MOMENTPipeline.from_pretrained(
+    "AutonLab/MOMENT-1-large", 
+    model_kwargs={
+        'task_name': 'classification',
+        'n_channels': 1,
+        'num_class': 2
+    },
+)
+model.init()
+```
+
+**Anomaly Detection/Imputation/Pre-training**
+```python
+from moment import MOMENTPipeline
+
+model = MOMENTPipeline.from_pretrained(
+    "AutonLab/MOMENT-1-large", 
+    model_kwargs={"task_name": "reconstruction"},
+)
+mode.init()
+```
+
+**Embedding**
+```python
+from moment import MOMENTPipeline
+
+model = MOMENTPipeline.from_pretrained(
+    "AutonLab/MOMENT-1-large", 
+    model_kwargs={'task_name': 'embedding'},
+)
+```
 
 ## Model Details