Update app.py

app.py

@@ -13,9 +13,16 @@ def predict(input, history=[]):
 
     # append the new user input tokens to the chat 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=500,
+                            pad_token_id=tokenizer.eos_token_id,
+                            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
     response = tokenizer.decode(history[0]).split("<|endoftext|>")