pert-qa / tokenizer_config.json
cgt's picture
Training in progress, step 500
f4fb9c2
raw
history blame
463 Bytes
{
"cls_token": "[CLS]",
"do_lower_case": true,
"mask_token": "[MASK]",
"name_or_path": "hfl/chinese-pert-large",
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": "/home/cgt/.cache/huggingface/hub/models--hfl--chinese-pert-large/snapshots/2e523595cb3d0d157f847cd0ec1b3914c8740fe1/special_tokens_map.json",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}