runtime error

Exit code: 1. Reason: �██▋ | 1.54G/4.15G [00:08<00:08, 323MB/s] Fetching 43 files: 67%|██████▋ | 29/43 [00:08<00:04, 3.30it/s] Fetching 43 files: 100%|██████████| 43/43 [00:08<00:00, 4.89it/s] Loading Talker Model... Loading Decoder Model... Download complete: 100%|██████████| 4.15G/4.15G [00:08<00:00, 323MB/s] Traceback (most recent call last): File "/app/app.py", line 25, in <module> tokenizer = AutoTokenizer.from_pretrained( model_path, trust_remote_code=True, use_fast=False # This often helps with custom Qwen tokenizers in restricted environments ) File "/usr/local/lib/python3.13/site-packages/transformers/models/auto/tokenization_auto.py", line 823, in from_pretrained return tokenizer_class.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs) ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.13/site-packages/transformers/tokenization_utils_base.py", line 1740, 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 1930, in _from_pretrained tokenizer = cls(*init_inputs, **init_kwargs) File "/usr/local/lib/python3.13/site-packages/transformers/tokenization_utils_tokenizers.py", line 376, in __init__ raise ValueError( ...<5 lines>... ) ValueError: Couldn't instantiate the backend tokenizer from one of: (1) a `tokenizers` library serialization file, (2) a slow tokenizer instance to convert or (3) an equivalent slow tokenizer class to instantiate and convert. You need to have sentencepiece or tiktoken installed to convert a slow tokenizer to a fast one. Download complete: 100%|██████████| 4.15G/4.15G [00:15<00:00, 272MB/s]

Container logs: