VHHBERT / tokenizer_config.json
tsurubee's picture
Upload model and tokenizer
9bb7c0a verified
{
"added_tokens_decoder": {
"0": {
"content": "<s>",
"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": "</s>",
"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": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"clean_up_tokenization_spaces": true,
"cls_token": "<s>",
"do_basic_tokenize": false,
"do_lower_case": false,
"mask_token": "<mask>",
"model_max_length": 1000000000000000019884624838656,
"never_split": null,
"pad_token": "<pad>",
"sep_token": "</s>",
"strip_accents": null,
"tokenize_chinese_chars": false,
"tokenizer_class": "BertTokenizer",
"unk_token": "<unk>"
}