chinese_danmaku_roberta / tokenizer_config.json
WUJUNCHAO's picture
add chinese roberta model for danmaku
91cf67b
raw
history blame
510 Bytes
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": false,
"mask_token": "[MASK]",
"model_max_length": 512,
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": "/home/derekfw/.cache/huggingface/hub/models--uer--chinese_roberta_L-8_H-512/snapshots/ad32c8ad55b3ddbda96f18ec686edfa39817d1ec/special_tokens_map.json",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}