Update app.py

app.py

@@ -10,19 +10,15 @@ model = AutoModelForSequenceClassification.from_pretrained(model_path, num_label
 
 tokenizer = AutoTokenizer.from_pretrained(model_path)
 
-device = "cuda"
-
-model.eval()
 
 @spaces.GPU
 def predict(title, abstract):
-    model.to(device)
+    model.eval()
     text = f'''Given a certain paper, Title: {title}\n Abstract: {abstract}. \n Predict its normalized academic impact (between 0 and 1):'''
     inputs = tokenizer(text, return_tensors="pt")
+    inputs = inputs.to("cuda")
     with torch.no_grad():
-        outputs = model(**inputs.to(device))
-    print("Model device:", next(model.parameters()).device)
-    print("Inputs device:", inputs.device)
+        outputs = model(**inputs)
     probability = torch.sigmoid(outputs.logits).item()
     # reason for +0.05: We observed that the predicted values in the web demo are generally around 0.05 lower than those in the local deployment (due to differences in software/hardware environments). Therefore, we applied the following compensation in the web demo. Please do not use this in the local deployment.
     if probability + 0.05 >=1.0: