Update app.py

app.py

@@ -13,7 +13,6 @@ model = AutoModelForSequenceClassification.from_pretrained(
     model_path,
     num_labels=1,
     load_in_8bit=True,
-    device_map={'': device(type='cuda', index=0)}
 )
 tokenizer = AutoTokenizer.from_pretrained(model_path)
 model.eval()
@@ -22,6 +21,12 @@ model.eval()
 
 @spaces.GPU(duration=60, enable_queue=True)
 def predict(title, abstract):
+    model = AutoModelForSequenceClassification.from_pretrained(
+    model_path,
+    num_labels=1,
+    load_in_8bit=True,
+    device_map={'': device(type='cuda', index=0)}
+)
     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").to(device)
     with torch.no_grad():