Update app.py

app.py

@@ -5,7 +5,7 @@ from threading import Thread
 import spaces
 
 @spaces.GPU
-def food_safety_query(prompt):
+def load_model_tokenizer():
     from unsloth import FastLanguageModel
     # Model configuration
     model_name = "yasserrmd/food_safety"  
@@ -21,7 +21,12 @@ def food_safety_query(prompt):
         load_in_4bit=load_in_4bit,
     )
     FastLanguageModel.for_inference(model)  # Enable faster inference
+    return  model, tokenizer
 
+model, tokenizer = load_model_tokenizer()
+
+@spaces.GPU
+def food_safety_query(prompt):
 
     messages = [
         {"role": "system", "content": "You are an AI assistant with expertise in food safety. Your primary goal is to provide precise, actionable, and scientifically accurate responses to queries about food safety practices, standards, and regulations. Focus on offering guidance based on global food safety standards, such as HACCP, ISO 22000, and FDA guidelines. Your responses should address hygiene, contamination prevention, food handling, storage, production processes, and safety protocols with practical and specific advice."},
@@ -61,9 +66,9 @@ def food_safety_query(prompt):
         yield output
 
 
-# Gradio interface
+
 with gr.Blocks() as app:
-    gr.Markdown("""# Food Safety Query App\nEnter your questions related to food safety, and the model will provide detailed responses in real-time.
+    gr.Markdown("""# Food Safety App\nEnter your questions related to food safety, and the assistant will provide detailed responses.
     """)
     prompt = gr.Textbox(label="Enter your query:", placeholder="E.g., What hygiene practices should milk-producing factories follow?")
     submit_button = gr.Button("Get Response")