Can't load DeBERTa-v3 tokenizer

[maiiabocharova]

from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("microsoft/deberta-v3-base")

Gives me an error
ValueError: This tokenizer cannot be instantiated. Please make sure you have sentencepiece installed in order to use this tokenizer.
But sentencepiece is already installed

Also tried

!pip install deberta
from DeBERTa import deberta
vocab_path, vocab_type = deberta.load_vocab(pretrained_id='base-v3')
tokenizer = deberta.tokenizers[vocab_type](vocab_path)

this gives me
TypeError: stat: path should be string, bytes, os.PathLike or integer, not NoneType

Please help, how can I use the tokenizer for deberta-base-v3?

[chrischowfy]

from transformers import DebertaV2Tokenizer, DebertaV2Model
tokenizer = DebertaV2Tokenizer.from_pretrained("microsoft/deberta-v3-base")
is work for me.

[maiiabocharova]

from transformers import DebertaV2Tokenizer, DebertaV2Model tokenizer = DebertaV2Tokenizer.from_pretrained("microsoft/deberta-v3-base") is work for me.

Thank you, I was able to initialize tokenizer, but later it gives me an error when providing text to tokenizer
tokenizer("Some text")
TypeError: 'NoneType' object is not callable

[chrischowfy]

It's weird. Maybe the text you tokenized wasn't processed properly

[maiiabocharova]

Hello, the issue was that I used colab and tokenizer needed sentencepiece to be installed. So the solution was to install sentencepiece and afterwards restart the runtime. (I didn't restart it at first)

Thank you sharing the model!