cantonese-chinese-translation / tokenizer_config.json
raptorkwok's picture
Training in progress, step 1000
f1be6d5
raw
history blame
469 Bytes
{
"bos_token": "[CLS]",
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": false,
"eos_token": "[EOS]",
"mask_token": "[MASK]",
"model_max_length": 1000000000000000019884624838656,
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"tokenizer_file": null,
"unk_token": "[UNK]"
}