auslaw-embed-v1.0 / tokenizer_config.json
adlumal's picture
Initial commit
4d1a6d4
raw
history blame
562 Bytes
{
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"model_max_length": 512,
"name_or_path": "/root/.cache/torch/sentence_transformers/BAAI_bge-small-en/",
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": "/root/.cache/torch/sentence_transformers/BAAI_bge-small-en/special_tokens_map.json",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}