Update app.py

app.py

@@ -1,11 +1,12 @@
 import gradio as gr
 from transformers import AutoModelForQuestionAnswering, pipeline,AutoTokenizer
-from optimum.onnxruntime import ORTModelForQuestionAnswering
+import torch
 def question_answer(context, question):
   model_checkpoint = "letrunglinh/qa_pnc"
+  device = "cuda" if torch.cuda.is_available() else "cpu"
   tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
   model = pipeline('question-answering', model=model_checkpoint,
-  tokenizer=tokenizer)
+  tokenizer=tokenizer).to(device)
   to_predict = [
     {
         "question": question,