ms-marco-MiniLM-L-12-v2 / tokenizer_config.json
lrodrigues's picture
upload
67d0e3a
raw
history blame
366 Bytes
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"model_max_length": 512,
"name_or_path": "microsoft/MiniLM-L12-H384-uncased",
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"strip_accents": null,
"tokenize_chinese_chars": true,
"unk_token": "[UNK]"
}