modify from_pretrained param

inference.py

@@ -26,9 +26,7 @@ def load_model(
     tokenizer = AutoTokenizer.from_pretrained(model_name)
 
     model = AutoModelForCausalLM.from_pretrained(
-        model_name=model_name,
-        torch_dtype=dtype,
-        device_map="auto"
+        pretrained_model_name_or_path=model_name
     )
 
     model.eval() # Set model to evaluation mode