Update handler.py

handler.py

@@ -18,4 +18,6 @@ class EndpointHandler:
         # ignoring parameters! Default to configs in generation_config.json.
         messages = [{"role": "user", "content": inputs}]
         response = self.model.chat(self.tokenizer, messages)
+        if torch.backends.mps.is_available():
+            torch.mps.empty_cache()
         return [{'generated_text': response}]