roberta-base-thai-syllable-upos / tokenizer_config.json
KoichiYasuoka's picture
initial release
4587d90
raw
history blame
299 Bytes
{"do_lower_case": false, "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>", "tokenize_chinese_chars": true, "strip_accents": false, "model_max_length": 416, "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}