Japanese
character_tokenizer_jis_v2 / tokenizer_config.json
rtakeda's picture
Upload 4 files
42980a5 verified
Raw
History Blame Contribute Delete
1.6 kB
{
"add_prefix_space": false,
"added_tokens_decoder": {
"0": {
"content": "[PAD]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "[UNK]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "[CLS]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "[SEP]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"6": {
"content": "[MASK]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"cls_token": "[CLS]",
"eos_token": "</s>",
"mask_token": "[MASK]",
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"unk_token": "[UNK]",
"clean_up_tokenization_spaces": false,
"model_max_length": 2048,
"tokenizer_class": "CharacterTokenizer",
"auto_map": {
"AutoTokenizer": [
"tokenizer.CharacterTokenizer",
null
]
}
}