MedNERN-CR-JA / tokenizer_config.json
gabrielandrade2's picture
Update model with additional negative examples, improve support scripts
576d564
{
"cls_token": "[CLS]",
"do_lower_case": false,
"do_subword_tokenize": true,
"do_word_tokenize": true,
"jumanpp_kwargs": null,
"mask_token": "[MASK]",
"mecab_kwargs": null,
"model_max_length": 512,
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": null,
"subword_tokenizer_type": "wordpiece",
"sudachi_kwargs": null,
"tokenizer_class": "NER_tokenizer_BIO",
"unk_token": "[UNK]",
"word_tokenizer_type": "mecab",
"auto_map": [
"NER_medNLP.NER_tokenizer_BIO",
null
],
"num_entity_type": "43"
}