transformer-lm-japanese-0.1b / tokenizer_config.json
fukugawa's picture
Upload tokenizer
01799ff verified
{
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"30000": {
"content": "[CLS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"30001": {
"content": "[SEP]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"30002": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"30003": {
"content": "[MASK]",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"auto_map": {
"AutoTokenizer": [
"tokenization_transformerlm.TransformerLMTokenizer",
null
]
},
"bos_token": "[CLS]",
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"do_lower_case": true,
"eos_token": "[SEP]",
"keep_accents": false,
"mask_token": "[MASK]",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"remove_space": true,
"sep_token": "[SEP]",
"sp_model_kwargs": {},
"tokenizer_class": "TransformerLMTokenizer",
"unk_token": "<unk>"
}