all-MiniLM-L6-v2-spelling-correction / tokenizer_config.json
karakastarik's picture
Upload tokenizer_config.json with huggingface_hub
7b2b32b
raw
history blame
517 Bytes
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"model_max_length": 512,
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": "/home/ubuntu/.cache/huggingface/hub/models--sentence-transformers--all-MiniLM-L6-v2/snapshots/7dbbc90392e2f80f3d3c277d6e90027e55de9125/special_tokens_map.json",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}