Update app.py

app.py

@@ -1,19 +1,19 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
 from model import load_model, load_tokenizer
 from utils import clean_output, get_shap_values
 import torch
 import shap
 import matplotlib.pyplot as plt
 
-tokenizer = load_tokenizer()
+"""
+For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
+"""
+client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+
+# Load model and tokenizer once
 model = load_model()
+tokenizer = load_tokenizer()
 
 def gradio_generate(context, num_questions, max_length):
     input_prompt = f"generate question: {context.strip()}"