Update app.py

app.py

@@ -11,7 +11,8 @@ device = "cuda" if torch.cuda.is_available() else "cpu"
 
 # Load adapter-based model
 print("Loading model...")
-tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH)
+tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH, config="tokenizer_config.json")
+
 model = AutoModelForCausalLM.from_pretrained(MODEL_PATH, torch_dtype=torch.float16 if device == "cuda" else None)
 model.to(device)
 print("Model loaded successfully.")