|
{
|
|
"added_tokens_decoder": {
|
|
"0": {
|
|
"content": "[PAD]",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100": {
|
|
"content": "[UNK]",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"101": {
|
|
"content": "[CLS]",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"102": {
|
|
"content": "[SEP]",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"103": {
|
|
"content": "[MASK]",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
}
|
|
},
|
|
"clean_up_tokenization_spaces": true,
|
|
"cls_token": "[CLS]",
|
|
"do_basic_tokenize": true,
|
|
"do_lower_case": true,
|
|
"mask_token": "[MASK]",
|
|
"model_input_names": [
|
|
"input_ids",
|
|
"attention_mask"
|
|
],
|
|
"model_max_length": 512,
|
|
"never_split": null,
|
|
"pad_token": "[PAD]",
|
|
"processor_class": "BlipProcessor",
|
|
"sep_token": "[SEP]",
|
|
"strip_accents": null,
|
|
"tokenize_chinese_chars": true,
|
|
"tokenizer_class": "BertTokenizer",
|
|
"unk_token": "[UNK]"
|
|
}
|
|
|