Update app.py

app.py

@@ -8,21 +8,24 @@ from PIL import Image
 
 import spaces
 
-# Model configuration
-model_id = "TheFinAI/FinLLaVA"
-device = "cuda:0"
-load_8bit = False
-load_4bit = False
+parser = argparse.ArgumentParser()
+parser.add_argument("--model-path", type=str, default="TheFinAI/FinLLaVA")
+parser.add_argument("--device", type=str, default="cuda:0")
+parser.add_argument("--conv-mode", type=str, default="llama_3")
+parser.add_argument("--temperature", type=float, default=0)
+parser.add_argument("--max-new-tokens", type=int, default=512)
+parser.add_argument("--load-8bit", action="store_true")
+parser.add_argument("--load-4bit", action="store_true")
+args = parser.parse_args()
 
-# Load the pretrained model
+# load model
 tokenizer, llava_model, image_processor, context_len = load_pretrained_model(
-    model_id, 
+    args.model_path, 
     None, 
     'llava_llama3', 
-    load_8bit, 
-    load_4bit, 
-    device=device
-)
+    args.load_8bit, 
+    args.load_4bit, 
+    device=args.device)
 
 @spaces.GPU
 def bot_streaming(message, history):