roberta-base-thai-spm-upos / tokenizer_config.json
KoichiYasuoka's picture
model improved
4861a26
{
"added_tokens_decoder": {
"0": {
"content": "[CLS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "[SEP]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "[MASK]",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "[CLS]",
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"do_lower_case": false,
"eos_token": "[SEP]",
"keep_accents": true,
"mask_token": "[MASK]",
"max_length": 510,
"model_max_length": 512,
"pad_token": "[PAD]",
"remove_space": true,
"sep_token": "[SEP]",
"stride": 0,
"tokenizer_class": "RemBertTokenizerFast",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "[UNK]"
}