Update app.py

app.py

@@ -16,14 +16,13 @@ def predict(input, history=[]):
     
     # generate a response 
     history = model.generate(bot_input_ids,
-                            max_length=1000,
+                            max_length=200,
                             pad_token_id=tokenizer.eos_token_id,
-                            #no_repeat_ngram_size=3,
-                            #num_beams = 3,
-                            #do_sample=True,
-                            #top_k=20,
-                            #top_p=0.8,
-                            #temperature=0.8
+                            no_repeat_ngram_size=3,
+                            do_sample=True,
+                            top_k=100,
+                            top_p=0.7,
+                            temperature = 0.8
                             ).tolist()
 
     # convert the tokens to text, and then split the responses into the right format