prompt-extend-chinese-gpt / tokenizer_config.json
svjack's picture
Upload with huggingface_hub
b5eceb5
raw
history blame
570 Bytes
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": false,
"mask_token": "[MASK]",
"model_max_length": 1024,
"name_or_path": "uer/gpt2-chinese-cluecorpussmall",
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": "/home/featurize/.cache/huggingface/hub/models--uer--gpt2-chinese-cluecorpussmall/snapshots/7c87595de655dc7b0fbfaa545ae413a118063d0b/special_tokens_map.json",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}