Permission Denied

#1
by ahmedghani - opened

from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("hkunlp/from_all_T5_large_prefix_spider_with_cell_value2")

model = AutoModel.from_pretrained("hkunlp/from_all_T5_large_prefix_spider_with_cell_value2")

-------------------------------------------- ERROR --------------------------------------------

File "/home/user/anaconda3/envs/test/lib/python3.8/site-packages/transformers/tokenization_utils_base.py", line 1850, in _from_pretrained
tokenizer = cls(*init_inputs, **init_kwargs)
File "/home/user/anaconda3/envs/test/lib/python3.8/site-packages/transformers/models/t5/tokenization_t5_fast.py", line 128, in init
super().init(
File "/home/user/anaconda3/envs/test/lib/python3.8/site-packages/transformers/tokenization_utils_fast.py", line 107, in init
fast_tokenizer = TokenizerFast.from_file(fast_tokenizer_file)
Exception: Permission denied (os error 13)

NLP Group of The University of Hong Kong org

Hi,

This weight relies on the code of prefix-tuning which don't exists in huggingface AutoTokenizer and AutoModel. To load this weight, see UnifiedSKG official code and colab demo.

Hope these information helpful!

Thanks!

ahmedghani changed discussion status to closed

Sign up or log in to comment