Update app.py

app.py

@@ -3,7 +3,6 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 
 model_name = "Llama-2-7b-finetuned-with-QLoRa"
 
-# Load model and tokenizer
 @st.cache_resource
 def load_model_and_tokenizer(model_name):
     model = AutoModelForCausalLM.from_pretrained(model_name)
@@ -34,7 +33,7 @@ def main():
     # Generate button
     if st.sidebar.button("Generate Response"):
         with st.spinner("Generating response..."):
-            response = generate_response(topic)
+            response = generate_response(f"[INST] {topic} [/INST]" )
         st.subheader(f"Generated response on '{topic}':")
         st.write(response)