chinese_roberta_L-10_H-128 / tokenizer_config.json
hhou435's picture
First version of the chinese_roberta_L-10_H-128 model and tokenizer.
c047318
raw
history blame
216 Bytes
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512}