Update README.md

README.md

@@ -60,6 +60,16 @@ model = PeftModel.from_pretrained(model, LORA_CHECKPOINT)
 model.to(torch.device("xpu" if torch.xpu.is_available() else "cpu"))
 ```
 
+Then, you can generate 911 operator responses by providing an input prompt:
+
+```python
+prompt = "911 Operator: 9-1-1, what's your emergency?\nCaller: There's a fire in my kitchen!\n911 Operator:"
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+outputs = model.generate(**inputs, max_new_tokens=100)
+response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+print(response)
+``
+
 ## Training Details
 
 ### Training Data