bert-tweet-base-italian-uncased / tokenizer_config.json
osiria's picture
Upload 5 files
e7a5836
raw
history blame
446 Bytes
{
"bos_token": "[CLS]",
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"eos_token": "[SEP]",
"mask_token": {
"__type": "AddedToken",
"content": "[MASK]",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 1000000000000000019884624838656,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}