Create app.py

app.py

@@ -0,0 +1,78 @@
+from deepsparse import Pipeline
+import time
+import gradio as gr
+
+markdownn = '''
+# Text Classification Pipeline with DeepSparse
+DeepSparse is sparsity-aware inference runtime offering GPU-class performance on CPUs and APIs to integrate ML into your application. DeepSparse provides sparsified pipelines for computer vision and NLP. 
+The pipelines are similar to Hugging Face pipelines but are faster because they have been pruned and quantized. Here is a sample code for a question-answering pipeline: 
+```
+from deepsparse import Pipeline
+pipeline = pipeline.create(task="text-classification", model_path="zoo:nlp/text_classification/bert-base_cased/pytorch/huggingface/mnli/pruned90_quant-none")
+inference = pipeline(text)
+print(inference)
+```
+'''
+task = "text-classification"
+dense_classification_pipeline = Pipeline.create(
+        task=task,
+        model_path="zoo:nlp/text_classification/bert-base_cased/pytorch/huggingface/mnli/base-nonee",
+    )
+
+sparse_classification_pipeline = Pipeline.create(
+        task=task,
+        model_path="zoo:nlp/text_classification/bert-base_cased/pytorch/huggingface/mnli/pruned90_quant-none",
+    )
+def run_pipeline(text):
+    dense_start = time.perf_counter()
+    
+    dense_output = dense_qa_pipeline([text])
+    dense_result = dict(dense_output)
+    dense_end = time.perf_counter()
+    dense_duration = (dense_end - dense_start) * 1000.0
+
+    sparse_start = time.perf_counter()
+    
+    sparse_output = sparse_qa_pipeline([text])
+    sparse_result = dict(sparse_output)
+    sparse_end = time.perf_counter()
+    sparse_duration = (sparse_end - sparse_start) * 1000.0
+    
+    return sparse_result, sparse_duration, dense_result, dense_duration
+
+
+with gr.Blocks() as demo:
+    gr.Markdown(markdownn)
+    
+    with gr.Row():
+        text = gr.Text(label="Text")
+       
+    with gr.Row():
+        with gr.Column():
+            dense_duration = gr.Number(label="Dense Latency (ms):")
+            dense_answers = gr.Textbox(label="Dense model answer")
+            
+        with gr.Column():
+            sparse_duration = gr.Number(label="Sparse Latency (ms):")
+            sparse_answers = gr.Textbox(label="Sparse model answers")
+
+    btn = gr.Button("Submit")
+    btn.click(
+        run_pipeline,
+        inputs=[text],
+        outputs=[sparse_answers,sparse_duration,dense_answers,dense_duration],
+    )
+
+   
+    gr.Examples(
+        [
+            ["DeepSparse is sparsity-aware inference runtime offering GPU-class performance on CPUs and APIs to integrate ML into your application"],
+            ["SparseML is a Library for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models"],
+            ["Gradio is an open-source Python package that allows you to quickly create easy-to-use, customizable UI components for your ML model, any API, or even an arbitrary Python function using a few lines of code. You can integrate the Gradio GUI directly into your Jupyter notebook or share it as a link with anyone."],
+        ],
+        inputs=[text],
+    )
+
+
+if __name__ == "__main__":
+    demo.launch()