Update app.py

app.py

@@ -19,18 +19,18 @@ 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)
+    bot_input_ids = torch.cat([chat_history_ids, new_user_input_ids], dim=-1) if step > 0 else new_user_input_ids
 
     # generate a response
     history = model.generate(
-        bot_input_ids, max_length=200, pad_token_id=tokenizer.eos_token_id
+        bot_input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id
     ).tolist()
 
     # convert the tokens to text, and then split the responses into lines
     response = tokenizer.decode(history[0]).split("<|endoftext|>")
     # print('decoded_response-->>'+str(response))
     response = [
-        (response[i], response[i + 1]) for i in range(0, len(response) - 1, 2)
+        (response[i], response[i + 1]) for i in range(5, len(response) - 1, 2)
     ]  # convert to tuples of list
     # print('response-->>'+str(response))
     return response, history