albertina-1b5-portuguese-ptbr-encoder / tokenizer_config.json
jarodrigues's picture
Upload 5 files
46d2a85 verified
{
"added_tokens_decoder": {
"0": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "[CLS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "[SEP]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "[UNK]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"128000": {
"content": "[MASK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "[CLS]",
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"do_lower_case": false,
"eos_token": "[SEP]",
"mask_token": "[MASK]",
"model_max_length": 512,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"sp_model_kwargs": {},
"split_by_punct": false,
"tokenizer_class": "DebertaV2Tokenizer",
"unk_token": "[UNK]",
"vocab_type": "spm"
}