update app.py

app.py

@@ -71,12 +71,12 @@ top_k = st.sidebar.slider("Top-K: Controls model's sampling space.", min_value=1
 top_p = st.sidebar.slider("Top-P", min_value=0.1, max_value=1.0, value=top_p)
 repetition_penalty = st.sidebar.slider("Repetition Penalty: Discourages token repitition during generation.", min_value=1.0, max_value=10.0, value=repetition_penalty)
 length_penalty = st.sidebar.slider("Length Penalty: Discourages poor output as token length grows.", min_value=0.1, max_value=10.0, value=length_penalty)
-
+do_sample = st.sidebar.checkbox("Do_sample: Enable sampling for richer generation.")
 
 generation_config = {
     "max_length": max_length,
     "num_beams": num_beams,
-    "do_sample": True,
+    "do_sample": bool(do_sample),
     "temperature": temperature,
     "top_k": top_k,
     "top_p": top_p,