Update app.py

app.py

@@ -70,6 +70,8 @@ from transformers import T5Tokenizer, T5ForConditionalGeneration
 
 tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-xl")
 model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-xl", device_map = "auto")
+# Move the model to the GPU
+model = model.to('cuda')
 
 # We are running FP32!
 
@@ -91,8 +93,6 @@ def process():
     ##input_ids = tokenizer(my_text, return_tensors = "pt").input_ids.to("cuda")
 
     #From Here
-    # Move the model to the GPU
-    model = model.to('cuda')
 
     # User input
     user_input = st.text_input("Գրեք ձեր հարցը...", "")