update app.py

app.py

@@ -36,8 +36,11 @@ def submit():
 
 # prompt = "How long will it take for the poc to finish?"
 # inputs = tokenizer(prompt, return_tensors="pt")
+
+max_tokens = st.sidebar.slider("Max Tokens", min_value = 16, max_value = 64, value = 32)
+
 model, tokenizer = get_model()
-generation_config = GenerationConfig(max_new_tokens=32, 
+generation_config = GenerationConfig(max_new_tokens=max_tokens, 
                         num_beams=4, 
                         early_stopping=True,
                         no_repeat_ngram_size=2,