Fixing local mistake

handler.py

@@ -27,13 +27,11 @@ class EndpointHandler:
 
         self.device = "cuda" if torch.cuda.is_available() else "cpu"
 
-        # self.tokenizer = AutoTokenizer.from_pretrained(path)
-        # self.model = AutoModelForCausalLM.from_pretrained(path, device_map="auto", 
-        #                                                   offload_folder='offload',
-        #                                                   trust_remote_code=True,
-        #                                                   load_in_8bit=True)
-        self.tokenizer = tokenizer
-        self.model = model
+        self.tokenizer = AutoTokenizer.from_pretrained(path)
+        self.model = AutoModelForCausalLM.from_pretrained(path, device_map="auto", 
+                                                          offload_folder='offload',
+                                                          trust_remote_code=True,
+                                                          load_in_8bit=True)
 
     def __call__(self, data: Dict[str, Any]) -> Dict[str, Any]: