bert-base-tweetner7-2021 / tokenizer_config.json
asahi417's picture
add tokenizer
fb42208
raw
history blame
442 Bytes
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "name_or_path": "cner_output/model/baseline_2021/bert_base/best_model", "special_tokens_map_file": "cner_output/model/baseline_2021/bert_base/model_pmzjpl/epoch_10/special_tokens_map.json", "tokenizer_class": "BertTokenizer"}