Update app.py

app.py

@@ -1,19 +1,9 @@
 import gradio as gr
 from transformers import pipeline
 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/distilbert-base-uncased-squadv1.1-sparse-80-1X4-block"
-# 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")
 
 
 def predict(context,question):
@@ -44,7 +34,7 @@ def predict(context,question):
 
 md = """This prediction model is designed to answer a question about a given input text--reading comprehension. The model does not just answer questions in general -- it only works from the text that you provide. However, automated reading comprehension can be a valuable task.
 
-The model is based on the Zafrir et al. (2021) paper: [Prune Once for All: Sparse Pre-Trained Language Models](https://arxiv.org/abs/2111.05754). The model can be found [here](https://huggingface.co/Intel/bert-base-uncased-squadv1.1-sparse-80-1x4-block-pruneofa). It has had weight pruning and model distillation applied to create a sparse weight pattern that is maintained even after fine-tuning has been applied. According to Zafrir et al. (2016), their "results show the best compression-to-accuracy ratio for BERT-Base". This model is still in FP32, but can be quantized to INT8 with the [Intel® Neural Compressor](https://github.com/intel/neural-compressor). An INT8 version of this model can actually be found [here on Hugging Face](https://huggingface.co/Intel/distilbert-base-uncased-squadv1.1-sparse-80-1x4-block-pruneofa-int8). 
+The model is based on the Zafrir et al. (2021) paper: [Prune Once for All: Sparse Pre-Trained Language Models](https://arxiv.org/abs/2111.05754). The model can be found [here](https://huggingface.co/Intel/bert-base-uncased-squadv1.1-sparse-80-1x4-block-pruneofa). It has had weight pruning and model distillation applied to create a sparse weight pattern that is maintained even after fine-tuning has been applied. According to Zafrir et al. (2016), their "results show the best compression-to-accuracy ratio for BERT-Base". This model is still in FP32, but can be quantized to INT8 with the [Intel® Neural Compressor](https://github.com/intel/neural-compressor). 
 
 The training dataset used is the English Wikipedia dataset (2500M words), and then fine-tuned on the SQuADv1.1 dataset containing 89K training examples, compiled by Rajpurkar et al. (2016): [100, 000+ Questions for Machine Comprehension of Text](https://arxiv.org/abs/1606.05250).