ibm-granite

/

granite-3.1-2b-instruct

like 45

Follow

IBM Granite 1.26k

granite model: granite-3.1-8b-instruct
tokenizer version: tokenizers 0.19.1 py311h6640629_0 conda-forge
Error traceback:
File "/dccstor/askpower/eknath/askpbot2/runAnyllm.py", line 268, in
main()
File "/dccstor/askpower/eknath/askpbot2/runAnyllm.py", line 243, in main
init_llm(p.configfile)
File "/dccstor/askpower/eknath/askpbot2/runAnyllm.py", line 193, in init_llm
setup(config)
File "/dccstor/askpower/eknath/askpbot2/runAnyllm.py", line 97, in setup
tokenizer = AutoTokenizer.from_pretrained(model_path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/dccstor/askpower/conda_askp/envs/askpenv/lib/python3.11/site-packages/transformers/models/auto/tokenization_auto.py", line 897, in from_pretrained
return tokenizer_class.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/dccstor/askpower/conda_askp/envs/askpenv/lib/python3.11/site-packages/transformers/tokenization_utils_base.py", line 2271, in from_pretrained
return cls._from_pretrained(
^^^^^^^^^^^^^^^^^^^^^
File "/dccstor/askpower/conda_askp/envs/askpenv/lib/python3.11/site-packages/transformers/tokenization_utils_base.py", line 2505, in _from_pretrained
tokenizer = cls(*init_inputs, **init_kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/dccstor/askpower/conda_askp/envs/askpenv/lib/python3.11/site-packages/transformers/models/gpt2/tokenization_gpt2_fast.py", line 99, in init
super().init(
File "/dccstor/askpower/conda_askp/envs/askpenv/lib/python3.11/site-packages/transformers/tokenization_utils_fast.py", line 115, in init
fast_tokenizer = TokenizerFast.from_file(fast_tokenizer_file)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Exception: data did not match any variant of untagged enum ModelWrapper at line 244953 column 3
(askpenv) [eknath@cccxl008 /dccstor/askpower/eknath/askpbot2]$python runAnyllm.py -c ./newconfig.yaml
Initializing LLM .. from config file: ./newconfig.yaml...Traceback (most recent call last):
File "/dccstor/askpower/eknath/askpbot2/runAnyllm.py", line 269, in
main()
File "/dccstor/askpower/eknath/askpbot2/runAnyllm.py", line 244, in main
init_llm(p.configfile)
File "/dccstor/askpower/eknath/askpbot2/runAnyllm.py", line 193, in init_llm
setup(config)
File "/dccstor/askpower/eknath/askpbot2/runAnyllm.py", line 97, in setup
tokenizer = AutoTokenizer.from_pretrained(model_path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/dccstor/askpower/conda_askp/envs/askpenv/lib/python3.11/site-packages/transformers/models/auto/tokenization_auto.py", line 897, in from_pretrained
return tokenizer_class.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/dccstor/askpower/conda_askp/envs/askpenv/lib/python3.11/site-packages/transformers/tokenization_utils_base.py", line 2271, in from_pretrained
return cls._from_pretrained(
^^^^^^^^^^^^^^^^^^^^^
File "/dccstor/askpower/conda_askp/envs/askpenv/lib/python3.11/site-packages/transformers/tokenization_utils_base.py", line 2505, in _from_pretrained
tokenizer = cls(*init_inputs, **init_kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/dccstor/askpower/conda_askp/envs/askpenv/lib/python3.11/site-packages/transformers/models/gpt2/tokenization_gpt2_fast.py", line 99, in init
super().init(
File "/dccstor/askpower/conda_askp/envs/askpenv/lib/python3.11/site-packages/transformers/tokenization_utils_fast.py", line 115, in init
fast_tokenizer = TokenizerFast.from_file(fast_tokenizer_file)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Exception: data did not match any variant of untagged enum ModelWrapper at line 244953 column 3

Any help would be appreciated