Updated custom handler

handler.py

@@ -1,10 +1,26 @@
 from typing import Dict, List, Any
+from transformers import (
+    AutoModelForCausalLM,
+    AutoTokenizer)
+import torch
+
+model = AutoModelForCausalLM.from_pretrained(
+                "sjster/test_medium",
+                trust_remote_code=True,
+                quantization_config=None,
+                torch_dtype=torch.float,     # data type is float
+                device_map="auto",
+            )
 
 class EndpointHandler():
     def __init__(self, path=""):
         # Preload all the elements you are going to need at inference.
-        # pseudo:
-         self.model= load_model(path)
+         self.model = AutoModelForCausalLM.from_pretrained(
+                path,
+                trust_remote_code=True,
+                quantization_config=None,
+                torch_dtype=torch.float,     # data type is float
+                device_map="auto",
 
     def __call__(self, data: Dict[str, Any]) -> List[Dict[str, Any]]:
         """