Update app.py

app.py

@@ -16,7 +16,7 @@ device = "cuda" if torch.cuda.is_available() else "cpu"
 
 # Load tokenizer and base model
 tokenizer = AutoTokenizer.from_pretrained(model_name)
-base_model = AutoModelForCausalLM.from_pretrained(
+model = AutoModelForCausalLM.from_pretrained(
     model_name,
     torch_dtype="auto",
     device_map="auto"