Fix: move inputs to model device in inference example to avoid "same device" error

Ensures inputs and model tensors reside on the same device before generation to avoid RuntimeError.

README.md

@@ -116,6 +116,7 @@ inputs = processor.apply_chat_template(
     return_dict=True,
     return_tensors="pt"
 )
+inputs = inputs.to(model.device)
 
 # Inference: Generation of the output
 generated_ids = model.generate(**inputs, max_new_tokens=128)