Update app.py

app.py

@@ -21,7 +21,7 @@ MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 
 if torch.cuda.is_available():
     model_id = "CreitinGameplays/ConvAI-9b"
-    model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto", auth_token=hf_token)
+    model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto", token=hf_token)
     tokenizer = AutoTokenizer.from_pretrained(model_id)
 
 @spaces.GPU