ru-document-tokenizer / tokenizer_config.json
abletobetable's picture
Upload tokenizer
02d5021
raw
history blame contribute delete
507 Bytes
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": false,
"mask_token": "[MASK]",
"model_max_length": 4096,
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": "/root/.cache/huggingface/hub/models--aware-ai--mobilebert-squadv2/snapshots/ea7dda1f800bfa1cd7b8ecc54368395f735b4b24/special_tokens_map.json",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "MobileBertTokenizer",
"unk_token": "[UNK]"
}