tohoku-nlp
/

bert-base-japanese-char-whole-word-masking

Fill-Mask Transformers PyTorch TensorFlow JAX

Japanese bert Inference Endpoints

Model card Files Files and versions Community

bert-base-japanese-char-whole-word-masking / tokenizer_config.json

singletongue's picture

Updates incorrect tokenizer configuration file (#2)

7650a07 verified about 2 months ago

raw history blame contribute delete

No virus

120 Bytes

{"do_lower_case": false, "word_tokenizer_type": "mecab", "subword_tokenizer_type": "character", "model_max_length": 512}