gpt2_wiki40b_ja / tokenizer_config.json
rfutrell's picture
Upload tokenizer
88d694d
raw
history blame contribute delete
583 Bytes
{
"additional_special_tokens": [
"<eop>",
"<eod>"
],
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "<cls>",
"do_lower_case": false,
"eos_token": "</s>",
"keep_accents": false,
"mask_token": {
"__type": "AddedToken",
"content": "<mask>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false
},
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"remove_space": true,
"sep_token": "<sep>",
"tokenizer_class": "XLNetTokenizer",
"unk_token": "<unk>"
}