|
{
|
|
"add_prefix_space": true,
|
|
"added_tokens_decoder": {
|
|
"0": {
|
|
"content": "<pad>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"1": {
|
|
"content": "<unk>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"2": {
|
|
"content": "[CLS]",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"3": {
|
|
"content": "[SEP]",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"4": {
|
|
"content": "[MASK]",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
}
|
|
},
|
|
"bos_token": "[CLS]",
|
|
"clean_up_tokenization_spaces": true,
|
|
"cls_token": "[CLS]",
|
|
"do_lower_case": true,
|
|
"eos_token": "[SEP]",
|
|
"keep_accents": false,
|
|
"mask_token": "[MASK]",
|
|
"max_length": 512,
|
|
"model_max_length": 512,
|
|
"pad_token": "<pad>",
|
|
"remove_space": true,
|
|
"sep_token": "[SEP]",
|
|
"stride": 0,
|
|
"tokenizer_class": "AlbertTokenizer",
|
|
"truncation_side": "left",
|
|
"truncation_strategy": "longest_first",
|
|
"unk_token": "<unk>"
|
|
}
|
|
|