Change model to run on cuda

handler.py

@@ -5,7 +5,7 @@ import torch
 class EndpointHandler:
     def __init__(self, path=""):
         self.processor = AutoProcessor.from_pretrained(path)
-        self.model = MusicgenForConditionalGeneration.from_pretrained(path)
+        self.model = MusicgenForConditionalGeneration.from_pretrained(path, torch_dtype=torch.float16).to("cuda")
     
     def __call__(self, data: Dict[str, Any]) -> Dict[str, str]:
         text_input = data.pop("inputs", data)