Update app.py

app.py

@@ -1,9 +1,3 @@
-# import subprocess
-# subprocess.run(
-#     'pip install flash-attn --no-build-isolation', 
-#     env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, 
-#     shell=True
-# )
 from threading import Thread
 import torch
 from PIL import Image
@@ -15,7 +9,7 @@ import time
 
 
 os.environ["HF_HUB_ENABLE_HF_TRANSFER"] = "1"
-
+MODEL_LIST = ["openbmb/MiniCPM-Llama3-V-2_5","openbmb/MiniCPM-Llama3-V-2_5-int4"]
 HF_TOKEN = os.environ.get("HF_TOKEN", None)
 MODEL_ID = os.environ.get("MODEL_ID")
 MODEL_NAME = MODEL_ID.split("/")[-1]