Update main.py

main.py

@@ -36,25 +36,24 @@ from ultralytics import YOLO
 #except:
     #yolo_model = YOLO("best.pt")
 
-from transformers import AutoProcessor, AutoModelForCausalLM
-
-processor = AutoProcessor.from_pretrained(
-    "microsoft/Florence-2-base", trust_remote_code=True
-)
 
+# Correctly load the processor and model for Blip-2
 try:
-    model = AutoModelForCausalLM.from_pretrained(
+    processor = AutoProcessor.from_pretrained("microsoft/Florence-2-base", trust_remote_code=True)
+    model = Blip2ForConditionalGeneration.from_pretrained(
         "microsoft/OmniParser",
-        torch_dtype=torch.float16,
-        trust_remote_code=True,
+        torch_dtype=torch.float16,  # Assuming you're using a GPU
+        trust_remote_code=True
     ).to("cuda")
-except:
-    model = AutoModelForCausalLM.from_pretrained(
+except Exception as e:
+    print(f"Error loading caption model: {e}")
+    processor = AutoProcessor.from_pretrained("microsoft/Florence-2-base", trust_remote_code=True)
+    model = Blip2ForConditionalGeneration.from_pretrained(
         "microsoft/OmniParser",
         torch_dtype=torch.float16,
-        trust_remote_code=True,
-    )
-caption_model_processor = {"processor": processor, "model": model}
+        trust_remote_code=True
+    ).to("cpu")  # Fallback to CPU if CUDA fails
+
 print("finish loading model!!!")
 
 app = FastAPI()