splade / tokenizer_config.json
fschlatt's picture
initial commit
650ead0
{
"add_marker_tokens": false,
"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
}
},
"attend_to_doc_expanded_tokens": [
false
],
"attend_to_query_expanded_tokens": false,
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"do_lower_case": true,
"doc_expansion": false,
"doc_length": 256,
"doc_token": "[DOC]",
"mask_token": "[MASK]",
"model_max_length": 512,
"pad_token": "[PAD]",
"query_expansion": false,
"query_length": 32,
"query_token": "[QUE]",
"sep_token": "[SEP]",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}