Update app.py

app.py

@@ -19,13 +19,14 @@ def predict(input, history=[]):
     new_user_input_ids = tokenizer.encode(
         input + tokenizer.eos_token, return_tensors="pt"
     )
-    attentionMask = torch.ones(new_user_input_ids.shape, dtype=torch.long)
+    #attentionMask = torch.ones(new_user_input_ids.shape, dtype=torch.long)
+    
     # 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=4000, pad_token_id=tokenizer.eos_token_id, attention_mask = attentionMask
+        bot_input_ids, max_length=4000, pad_token_id=tokenizer.eos_token_id
     ).tolist()
 
     # convert the tokens to text, and then split the responses into lines