Update app.py

app.py

@@ -11,12 +11,12 @@ a Llama 2 model with 70B parameters fine-tuned for chat instructions.
 # Initialize client
 
 
-# with st.sidebar:
-#     system_promptSide = st.text_input("Optional system prompt:")
-#     temperatureSide = st.slider("Temperature", min_value=0.0, max_value=1.0, value=0.9, step=0.05)
-#     max_new_tokensSide = st.slider("Max new tokens", min_value=0.0, max_value=4096.0, value=4096.0, step=64.0)
-#     ToppSide = st.slider("Top-p (nucleus sampling)", min_value=0.0, max_value=1.0, value=0.6, step=0.05)
-#     RepetitionpenaltySide = st.slider("Repetition penalty", min_value=0.0, max_value=2.0, value=1.2, step=0.05)
+with st.sidebar:
+    system_promptSide = st.text_input("Optional system prompt:")
+    temperatureSide = st.slider("Temperature", min_value=0.0, max_value=1.0, value=0.9, step=0.05)
+    max_new_tokensSide = st.slider("Max new tokens", min_value=0.0, max_value=4096.0, value=4096.0, step=64.0)
+    ToppSide = st.slider("Top-p (nucleus sampling)", min_value=0.0, max_value=1.0, value=0.6, step=0.05)
+    RepetitionpenaltySide = st.slider("Repetition penalty", min_value=0.0, max_value=2.0, value=1.2, step=0.05)
 
 
     
@@ -59,7 +59,7 @@ if prompt := st.chat_input("Ask LLama-2-70b anything..."):
     # Add user message to chat history
     st.session_state.messages.append({"role": "human", "content": prompt})
 
-    response = predict(prompt)#,system_promptSide,temperatureSide,max_new_tokensSide,ToppSide,RepetitionpenaltySide)
+    response = predict(prompt, system_promptSide,temperatureSide,max_new_tokensSide,ToppSide,RepetitionpenaltySide)
     # Display assistant response in chat message container
     with st.chat_message("assistant", avatar='🦙'):
         st.markdown(response)