sentence-bert-base-ja-mean-tokens-v2 / tokenizer_config.json
sonoisa's picture
Fix Japanese Sentence-BERT model
a3370d3
raw
history blame
466 Bytes
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "do_lower_case": false, "do_word_tokenize": true, "do_subword_tokenize": true, "word_tokenizer_type": "mecab", "subword_tokenizer_type": "wordpiece", "never_split": null, "mecab_kwargs": null, "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "/content/model/", "tokenizer_class": "BertJapaneseTokenizer"}