bugdaryan

/

Code-Llama-2-13B-instruct-text2sql

like 27

Won't load in Oobabooga... Seems to be related to the tokenizer also.

2023-10-27 09:05:11 ERROR:Failed to load the model.
Traceback (most recent call last):
File "/media/x/NV0/text-generation-webui-main/modules/ui_model_menu.py", line 201, in load_model_wrapper
shared.model, shared.tokenizer = load_model(shared.model_name, loader)
File "/media/x/NV0/text-generation-webui-main/modules/models.py", line 87, in load_model
tokenizer = load_tokenizer(model_name, model)
File "/media/x/NV0/text-generation-webui-main/modules/models.py", line 106, in load_tokenizer
tokenizer = AutoTokenizer.from_pretrained(
File "/home/x/anaconda3/envs/textgen/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py", line 751, in from_pretrained
return tokenizer_class.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs)
File "/home/x/anaconda3/envs/textgen/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 2017, in from_pretrained
return cls._from_pretrained(
File "/home/x/anaconda3/envs/textgen/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 2249, in _from_pretrained
tokenizer = cls(*init_inputs, **init_kwargs)
File "/home/x/anaconda3/envs/textgen/lib/python3.10/site-packages/transformers/models/code_llama/tokenization_code_llama.py", line 163, in init
self.sp_model = self.get_spm_processor()
File "/home/x/anaconda3/envs/textgen/lib/python3.10/site-packages/transformers/models/code_llama/tokenization_code_llama.py", line 190, in get_spm_processor
with open(self.vocab_file, "rb") as f:
TypeError: expected str, bytes or os.PathLike object, not NoneType