trying without distilbert model

app.py

@@ -4,15 +4,15 @@ import time
 import neural_compressor
 from optimum.intel.neural_compressor import IncQuantizedModelForQuestionAnswering
 
-# model_id = "Intel/bert-base-uncased-squadv1.1-sparse-80-1x4-block-pruneofa"
-model_id = "Intel/distilbert-base-uncased-squadv1.1-sparse-80-1x4-block-pruneofa-int8"
+model_id = "Intel/bert-base-uncased-squadv1.1-sparse-80-1x4-block-pruneofa"
+# model_id = "Intel/distilbert-base-uncased-squadv1.1-sparse-80-1x4-block-pruneofa-int8"
 int8_model = IncQuantizedModelForQuestionAnswering.from_pretrained(model_id)
 
 # sparse_qa_pipeline = pipeline(task="question-answering",model="Intel/bert-base-uncased-squadv1.1-sparse-80-1x4-block-pruneofa")
 # sparse_qa_pipeline = pipeline(task="question-answering",model="Intel/distilbert-base-uncased-squadv1.1-sparse-80-1x4-block-pruneofa-int8")
 
-# dense_qa_pipeline = pipeline(task="question-answering",model="csarron/bert-base-uncased-squad-v1")
-dense_qa_pipeline = pipeline(task="question-answering",model="distilbert-base-uncased-distilled-squad")
+dense_qa_pipeline = pipeline(task="question-answering",model="csarron/bert-base-uncased-squad-v1")
+# dense_qa_pipeline = pipeline(task="question-answering",model="distilbert-base-uncased-distilled-squad")
 
 
 def predict(context,question):