Files
quora-distilbert-multilingu…/tokenizer_config.json

17 lines
578 B
JSON
Raw Permalink Normal View History

{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": false,
"mask_token": "[MASK]",
"model_max_length": 512,
"name_or_path": "../../../model/sbert/quora_duplicate_questions/output/training_MultipleNegativesRankingLoss-2022-12-30_16-09-30/",
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": "old_models/quora-distilbert-multilingual/0_Transformer/special_tokens_map.json",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "DistilBertTokenizer",
"unk_token": "[UNK]"
}