runtime error

Exit code: 1. Reason: ou. If you want to use the new behaviour, set `legacy=False`. This should only be set if you understand what it means, and thoroughly read the reason why this was added as explained in https://github.com/huggingface/transformers/pull/24565 - if you loaded a llama tokenizer from a GGUF file you can ignore this message. Traceback (most recent call last): File "/app/app.py", line 11, in <module> tokenizer = AutoTokenizer.from_pretrained(model_id) File "/usr/local/lib/python3.13/site-packages/transformers/models/auto/tokenization_auto.py", line 1175, in from_pretrained return tokenizer_class_fast.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs) ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.13/site-packages/transformers/tokenization_utils_base.py", line 2113, in from_pretrained return cls._from_pretrained( ~~~~~~~~~~~~~~~~~~~~^ resolved_vocab_files, ^^^^^^^^^^^^^^^^^^^^^ ...<9 lines>... **kwargs, ^^^^^^^^^ ) ^ File "/usr/local/lib/python3.13/site-packages/transformers/tokenization_utils_base.py", line 2359, in _from_pretrained tokenizer = cls(*init_inputs, **init_kwargs) File "/usr/local/lib/python3.13/site-packages/transformers/models/llama/tokenization_llama_fast.py", line 154, in __init__ super().__init__( ~~~~~~~~~~~~~~~~^ vocab_file=vocab_file, ^^^^^^^^^^^^^^^^^^^^^^ ...<10 lines>... **kwargs, ^^^^^^^^^ ) ^ File "/usr/local/lib/python3.13/site-packages/transformers/tokenization_utils_fast.py", line 139, in __init__ fast_tokenizer = convert_slow_tokenizer(self, from_tiktoken=True) File "/usr/local/lib/python3.13/site-packages/transformers/convert_slow_tokenizer.py", line 1857, in convert_slow_tokenizer elif transformer_tokenizer.vocab_file.endswith("tekken.json"): ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ AttributeError: 'NoneType' object has no attribute 'endswith'

Container logs: