Update app.py

app.py

@@ -10,20 +10,23 @@ def generate_prompts(user_input):
         template=f"Just list 10 quetion prompts for {user_input} and don't put number before each of the prompts."
     )
     config = {'max_new_tokens': 2048, 'temperature': 0.7, 'context_length': 4096}
-
-    model_name = "TheBloke/Mistral-7B-Instruct-v0.1-GGUF"
-    model = AutoModelForCausalLM.from_pretrained(model_name)
-    tokenizer = AutoTokenizer.from_pretrained(model_name)
-
-    llm = CTransformers(model, tokenizer)
-
+    llm = CTransformers(model="https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF",
+                        config=config,
+                        threads=os.cpu_count())
     hub_chain = LLMChain(prompt = prompt_template, llm = llm)
+
     input_data = {"Question": user_input}
-    
-    generated_prompts = hub_chain.run(input_data)  
+
+    # Here you would integrate your prompt template with your model
+    # For demonstration, this is just a placeholder
+    generated_prompts = hub_chain.run(input_data)  # Modify this part based on how you run the model
     questions_list = generated_prompts.split('\n') 
+    
+
     formatted_questions = "\n".join(f"Question: {question}" for i, question in enumerate(questions_list) if question.strip())
     questions_list = formatted_questions.split("Question:")[1:]
+
+    
     return questions_list
 
 def answer_question(prompt):