Update app.py

app.py

@@ -66,6 +66,7 @@ def decode(tokenizer, encoding):
 @spaces.GPU
 def update_options(input, num_tokens):
     tokenized_prompts = tokenizer.encode([input], True, False)
+    print("Processed prompt")
     alive_gens, _ = model.sup_generate(prompt_tokens=tokenized_prompts, 
                                             smoothing="geom",
                                             max_gen_len=num_tokens, 
@@ -78,6 +79,7 @@ def update_options(input, num_tokens):
                                             ngrams=ngrams,
                                             get_time=False,
                                             penalty=200)
+    print("Generated")
     gens = alive_gens[0].reshape(n_drafts, -1)
     return decode(tokenizer, gens[0]), decode(tokenizer, gens[1]), decode(tokenizer, gens[2])
 
@@ -105,4 +107,4 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
         return curr + txt
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch(share=True)