yam-peleg

/

Hebrew-Mistral-7B-200K

like 14

Hi, I'm running on Sagemaker (using the huggingface reccomended script) and getting this stacktrace on the Enpoint Deployment -

 File "/opt/conda/lib/python3.10/site-packages/text_generation_server/server.py", line 196, in serve_inner
    model = get_model(
  File "/opt/conda/lib/python3.10/site-packages/text_generation_server/models/__init__.py", line 377, in get_model
    return FlashMistral(
  File "/opt/conda/lib/python3.10/site-packages/text_generation_server/models/flash_mistral.py", line 526, in __init__
    super(FlashMistral, self).__init__(
  File "/opt/conda/lib/python3.10/site-packages/text_generation_server/models/flash_mistral.py", line 310, in __init__
    tokenizer = LlamaTokenizerFast.from_pretrained(
  File "/opt/conda/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 2029, in from_pretrained
    return cls._from_pretrained(
  File "/opt/conda/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 2261, in _from_pretrained
    tokenizer = cls(*init_inputs, **init_kwargs)
  File "/opt/conda/lib/python3.10/site-packages/transformers/models/llama/tokenization_llama_fast.py", line 124, in __init__
    super().__init__(
  File "/opt/conda/lib/python3.10/site-packages/transformers/tokenization_utils_fast.py", line 111, in __init__
    fast_tokenizer = TokenizerFast.from_file(fast_tokenizer_file)

Exception: data did not match any variant of untagged enum ModelWrapper at line 205277 column 3

Both StackOverflow and HF discussions seems to think the solution to this will come from training with a PreTokenizer:
Huggingface comment with suggested solution
@yam-peleg if you have any ideas