Mac-no-no-cmrc2018-embeddings-no / tokenizer_config.json
Anonymous-2024's picture
Training in progress epoch 0
7615be9
raw
history blame contribute delete
519 Bytes
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"name_or_path": "hfl/chinese-macbert-base",
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": "/home/wsk/.cache/huggingface/hub/models--hfl--chinese-macbert-base/snapshots/a986e004d2a7f2a1c2f5a3edef4e20604a974ed1/special_tokens_map.json",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}