Update app.py

app.py

@@ -20,14 +20,11 @@ def predict(input):
     # tokenize the new input sentence
     new_user_input_ids = tokenizer.encode(input + tokenizer.eos_token, return_tensors='pt')
 
-    # 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(new_user_input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id).tolist()
 
     # convert the tokens to text, and then split the responses into the right format
     response = tokenizer.decode(history[0]).split("<|endoftext|>")
     return response[1]
 
-gr.Interface(fn = predict, inputs = ["textbox"], outputs = ["text"],allow_flagging = "manual",title = title, description = description, article = article ).launch(enable_queue=True)  # customizes the input component
+gr.Interface(fn = predict, inputs = ["textbox"], outputs = ["text"],allow_flagging = "manual",title = title, description = description, article = article, examples=[["What are you doing?"], ["Where should we time travel to?"]] ).launch(debug=True)