Update app.py

app.py

@@ -7,10 +7,11 @@ import torch
 @st.cache_resource
 def load_model():
     model_id = 'microsoft/Florence-2-large'
-    model = AutoModelForCausalLM.from_pretrained(model_id, trust_remote_code=True).eval()
+    model = AutoModelForCausalLM.from_pretrained(model_id, trust_remote_code=True).eval().to(torch.float32)
     processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)
     return model, processor
 
+# Load the model and processor globally
 model, processor = load_model()
 
 # Function to run the model
@@ -26,7 +27,7 @@ def run_example(task_prompt, image, text_input=None):
     inputs["pixel_values"] = inputs["pixel_values"].to(torch.float32)
 
     # Ensure the model is in float32 mode
-    model = model.to(torch.float32)
+    # The model has already been converted to float32 during loading, so this is not needed here.
 
     # Generate predictions
     generated_ids = model.generate(