Update app.py

app.py

@@ -152,7 +152,7 @@ def load_models_and_documents():
         llm = vllm.LLM(
             model_path, 
             tensor_parallel_size=1,
-            max_model_len=16384,
+            max_model_len=12288,
             trust_remote_code=True,
             enforce_eager=True,
             quantization='awq',