git-base-finetune-Aug142023_03 / tokenizer_config.json
wangjin2000's picture
copy from pretrained model.
f9f7348
raw
history blame
453 Bytes
{
"cls_token": "[CLS]",
"do_lower_case": true,
"mask_token": "[MASK]",
"model_input_names": [
"input_ids",
"attention_mask"
],
"model_max_length": 512,
"name_or_path": "bert-base-uncased",
"pad_token": "[PAD]",
"processor_class": "GitProcessor",
"sep_token": "[SEP]",
"special_tokens_map_file": null,
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}