Updating the CUDA instruction

Added example code to use GPU (CUDA) instead of CPU.

README.md

@@ -241,6 +241,15 @@ from nemo.collections.speechlm2.models import SALM
 model = SALM.from_pretrained('nvidia/canary-qwen-2.5b')
 ```
 
+```python
+#To run with CUDA
+from nemo.collections.speechlm2.models import SALM
+import torch
+device = torch.device("cuda")
+
+model = SALM.from_pretrained('nvidia/canary-qwen-2.5b').bfloat16().eval().to(device)
+```
+
 ## Input: 
 
 **Input Type(s):** Audio, text prompt <br>