Update app.py

app.py

@@ -15,11 +15,9 @@ with st.sidebar:
     system_prompt_input = st.text_input("Optional system prompt:")
     temperature_slider = st.slider("Temperature", min_value=0.0, max_value=1.0, value=0.9, step=0.05)
     max_new_tokens_slider = st.slider("Max new tokens", min_value=0.0, max_value=4096.0, value=4096.0, step=64.0)
-    topp_slider = st.slider("Top-p (nucleus sampling)", min_value=0.0, max_value=1.0, value=0.6, step=0.05)
-    repetition_penalty_slider = st.slider("Repetition penalty", min_value=0.0, max_value=2.0, value=1.2, step=0.05)
 
 # Prediction function
-def get_llama2_response(user_message, system_prompt, temperature, max_new_tokens, topp, repetition_penalty):
+def get_llama2_response(user_message, system_prompt, temperature, max_new_tokens, topp=0.6, repetition_penalty=1.2):
     with st.status("Requesting Llama-2"):
         st.write("Requesting API...")
         response = llama2_client.predict(
@@ -57,9 +55,7 @@ if user_input := st.chat_input("Ask Llama-2-70B anything..."):
         user_input,
         system_prompt_input,
         temperature_slider,
-        max_new_tokens_slider,
-        topp_slider,
-        repetition_penalty_slider
+        max_new_tokens_slider
     )
     # Display assistant response in chat message container
     with st.chat_message("assistant", avatar='🦙'):