bert-30M-cased / tokenizer_config.json
hieunguyen1053's picture
add tokenizer
15a6c0c
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "/Users/hieunguyen/Coding/learning/masked-language-model/huggingmodel/cased", "tokenizer_class": "BartphoTokenizer"}