MiniLM / tokenizer_config.json
Kishal's picture
Upload tokenizer_config.json
45e1818
raw
history blame
566 Bytes
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"model_max_length": 512,
"name_or_path": "/home/.cache/torch/sentence_transformers/sentence-transformers_all-MiniLM-L12-V2/",
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": "/home/.cache/torch/sentence_transformers/sentence-transformers_all-MiniLM-L12-V2/special_tokens_map.json",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}