Update app.py

app.py

@@ -12,6 +12,10 @@ from model import load_model
 from gen import get_output_batch, StreamModel
 from utils import generate_prompt, post_processes_batch, post_process_stream, get_generation_config, common_post_process
 
+generation_config = get_generation_config(
+    "./generation_config_default.yaml"
+)
+
 model, tokenizer = load_model(
     base="decapoda-research/llama-13b-hf",
     finetuned="chansung/alpaca-lora-13b"