Update app.py

app.py

@@ -15,8 +15,15 @@ def predict(input, history=[]):
     bot_input_ids = torch.cat([torch.LongTensor(history), new_user_input_ids], dim=-1)
 
     # generate a response 
-    history = model.generate(bot_input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id).tolist()
-
+    history = model.generate(
+                            bot_input_ids,
+                            max_length=1000,
+                            pad_token_id=tokenizer.eos_token_id,
+                            no_repeat_ngram_size=3,
+                            top_p = 0.92,
+                            top_k = 50
+                            ).tolist()
+                            
     # convert the tokens to text, and then split the responses into lines
     response = tokenizer.decode(history[0]).split("<|endoftext|>")
     response = [(response[i], response[i+1]) for i in range(0, len(response)-1, 2)]  # convert to tuples of list