Update app.py

app.py

@@ -1,11 +1,3 @@
-import subprocess
-subprocess.run(
-    'pip install flash-attn --no-build-isolation',
-    env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"},
-    shell=True
-)
-subprocess.run(["pip", "install", "-i", "https://pypi.org/simple/", "bitsandbytes"], check=True)
-from threading import Thread
 import torch
 from PIL import Image
 import gradio as gr
@@ -36,8 +28,9 @@ CSS = """
 
 model = AutoModel.from_pretrained(
     MODEL_ID,
+    torch_dtype=torch.float16,
     trust_remote_code=True
-)
+).to(0)
 tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, trust_remote_code=True)
 model.eval()