Update app.py

app.py

@@ -1,8 +1,5 @@
 import gradio as gr
 
-import torch
-device = "cuda" if torch.cuda.is_available() else "cpu"
-
 from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
 
 tokenizer = AutoTokenizer.from_pretrained("Einmalumdiewelt/T5-Base_GNAD")
@@ -11,11 +8,9 @@ model.to(device)
 
 
 def summarize(inputs):
-  with torch.no_grad():
-    # with a max_length of 200, the model has a chance to encapsule lots of information
-    preds = model.generate(**inputs,max_length=200,min_length=100)
-    # we decode the predictions to store them
-    decoded_predictions = tokenizer.batch_decode(preds, skip_special_tokens=True)
+  preds = model.generate(**inputs,max_length=200,min_length=100)
+  # we decode the predictions to store them
+  decoded_predictions = tokenizer.batch_decode(preds, skip_special_tokens=True)
   # each batches predictions are appended to the list   
   return decoded_predictions