all-MiniLM-L12-v2-embedding-all / tokenizer_config.json
LLukas22's picture
Auto Upload
fdcf374
raw
history blame
580 Bytes
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"model_max_length": 512,
"name_or_path": "sentence-transformers/all-MiniLM-L12-v2",
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": "/home/jovyan/_huggingface-shared/hub/models--sentence-transformers--all-MiniLM-L12-v2/snapshots/9e16800aed25dbd1a96dfa6949c68c4d81d5dded/special_tokens_map.json",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}