runtime error

Exit code: 1. Reason: tokenizer_config.json: 0%| | 0.00/152 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 152/152 [00:00<00:00, 1.24MB/s] config.json: 0%| | 0.00/508 [00:00<?, ?B/s] config.json: 100%|██████████| 508/508 [00:00<00:00, 3.76MB/s] vocab.txt: 0%| | 0.00/213k [00:00<?, ?B/s] vocab.txt: 100%|██████████| 213k/213k [00:00<00:00, 47.0MB/s] special_tokens_map.json: 0%| | 0.00/112 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 112/112 [00:00<00:00, 81.4kB/s] model.safetensors: 0%| | 0.00/433M [00:00<?, ?B/s] model.safetensors: 100%|█████████▉| 433M/433M [00:01<00:00, 375MB/s] model.safetensors: 100%|█████████▉| 433M/433M [00:01<00:00, 361MB/s] Some weights of the model checkpoint at deepset/bert-base-cased-squad2 were not used when initializing BertForQuestionAnswering: ['bert.pooler.dense.bias', 'bert.pooler.dense.weight'] - This IS expected if you are initializing BertForQuestionAnswering from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model). - This IS NOT expected if you are initializing BertForQuestionAnswering from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model). Device set to use cpu Traceback (most recent call last): File "/home/user/app/app.py", line 45, in <module> iface = gr.Interface( TypeError: Interface.__init__() missing 1 required positional argument: 'inputs'

Container logs: